Conference Agenda

We present the first quantitative evidence of systematic daily dead tree branch movement under field conditions, which has been previously only observed qualitatively. Using a boreal forest Permanent Laser Scanning (PLS) dataset, we investigated whether such movement can be detected and characterized in 3D laser scans. We link branch anatomy and geometry with environmental drivers, leading to the hypothesis that branch bending is proportional to wood moisture content. Hourly point clouds collected over 3.5 days from 17 dead branches (16 coniferous), attached mainly to living trees, were analyzed under calm weather conditions. We developed a novel workflow that tracks movement via non-rigid registration, calculates the angle between each branch and the vertical, and quantifies branch movement uncertainties across epochs. After accounting for time lags, these movements were related to the modeled wood moisture content using a linear mixed model. Clear and consistent daily movement was detected in all branches, with a mean amplitude of 21 cm and an average delay of 3.5 hours relative to moisture content changes. All branches moved downward during the day and upward at night, except one deciduous branch displaying the opposite pattern, consistent with our theoretical framework. The linear mixed model revealed a significant positive linear relationship between branch movement and wood moisture content. Our findings confirm that daily dead tree branch movement is primarily hygroscopic and demonstrate its effective detection using operational PLS. These insights open new possibilities for monitoring tree vitality using hypertemporal 3D sensing.

Tree growth determines how much CO2 is sequestered from the atmosphere and temporarily stored in woody biomass. At the same time tree growth is affected by increasing temperatures, more frequent drought periods, late frosts and other extreme events associated with climate change. While continuous measurements of radial (secondary) tree growth using dendrometers are well established, monitoring of shoot elongation (primary growth) has largely been neglected because suitable measurement techniques are lacking. As a result, the effects of climate change on primary tree growth remain insufficiently understood. This work aims at reconstructing native deciduous trees in 3D as a basis for measuring and monitoring shoot elongation over entire tree canopies. Here we explored the use of low-cost UAV photogrammetry and of a multi-camera CraneCam system under real-world conditions. Data were collected in two study areas over an entire growing season. We present sensor evaluations, photogrammetric data acquisition and processing strategies. A special focus is placed on the analysis of the resulting photogrammetric 3D point clouds in terms of accuracy, resolution and completeness. Results demonstrate 3D point accuracies of 5-6 mm for entire trees using consumer-grade UAVs weighing less than 250 g and a 3D reconstruction completeness between 92% and 98% depending on the UAV type. The paper introduces a novel 3D-printed ground-truth branch to evaluate the capability to reconstructing fine-detail structures such as thin tree shoots. Finally, we discuss operational challenges and initial experiments towards a skeletonization of entire trees based on photogrammetric point clouds.

Urban trees provide critical cooling benefits and regulate microclimates in cities, yet their three-dimensional thermal behaviour remains difficult to visualize and communicate to stakeholders. Traditional approaches rely on 2D thermal imagery analyzed on desktop screens, lacking spatial context and the capability for temporal monitoring across phenological stages. This work presents a pipeline combining Gaussian Splatting with augmented reality to enable immersive, on-site visualization of urban tree thermal patterns.

We captured thermal infrared (TIR) images of silver linden trees (Tilia tomentosa) at the University of Strasbourg using a FLIR T560 thermal camera. The TIR images were preprocessed and then processed using MILo (Mesh-In-the-Loop Gaussian Splatting), generating 3D thermal meshes with approximately 3 million vertices. The reconstruction is validated against reference thermal point clouds acquired with a terrestrial laser scanner equipped with an integrated thermal camera, assessing both geometric completeness and thermal attribute fidelity.

The thermal meshes are deployed in a mobile augmented reality application, allowing users to visualize temperature distributions directly overlaid on physical trees in the field. This work demonstrates the first application of 3D Gaussian Splatting to thermal vegetation modelling, providing an engaging educational tool to communicate urban trees' cooling role while offering researchers a platform for detailed thermal analysis and forest health monitoring.

To robustly support glacier calving monitoring at high temporal resolution and enable future AI-based calving forecasts, this study presents an optimized Multi-Epoch Multi-Imagery (MEMI) strategy for automated 4D point cloud model generation. To date, the dataset comprises over 160,000 images acquired since December 2024 by an autonomous multi-camera system operating at 30 min intervals at Glacier Perito Moreno (GPM), Argentina. Despite high scene variability and harsh environmental conditions, the proposed MEMI workflow effectively addresses constraints imposed by continuous glacier motion and image degradation. The enhanced strategy aims to generate precise dense clouds with high alignment accuracy and computational efficiency, forming the basis for subsequent analysis of glacier front evolution. To achieve this, various parameter configurations are evaluated, including AI-based image masking and adaptive, optimized alignment-adjustment settings. Results from a representative eight-day subset show that variations in the tie point computation strategy lead to measurable differences in alignment-adjustment efficiency, with the best configuration being about 11 % faster than the least efficient one. By contrast, adaptive alignment-adjustment consistently improves alignment accuracy. Moreover, masking enhances both image quality checking and reconstruction quality, and, albeit modestly, improves pre-failure deformation analysis. Furthermore, daily seasonal responses to alignment are observed, as accuracy varies with solar illumination relative to the camera positions. Applying the optimal configuration to 260 MEMI projects in under 42 h produced 518 high-precision dense clouds and detected calving retreat magnitudes of up to 17.5 m, demonstrating the robustness and scalability of the proposed MEMI strategy for high-temporal-resolution 4D point cloud generation.

Daily satellite-derived nighttime lights (NTL) are increasingly used to monitor electricity disruption and recovery, but their reliability in tropical regions is constrained by persistent cloud cover and intermittent observation. This study adopts a diagnostic-first framework that treats observability as a prerequisite for interpretation, determining when daily NTL signals are sufficiently supported to reflect underlying grid dynamics. Using NASA’s VIIRS Black Marble product, we quantify spatial and temporal completeness and radiance stability across the Samar–Leyte sub-grid in the Philippines. Results show that observations are highly intermittent and spatially heterogeneous, with urban areas providing more stable and interpretable signals, while rural regions remain noise-dominated.

To assess whether reliability-qualified NTL reflects electricity demand, DNB-BRDF radiance is aligned with hourly load data from the National Grid Corporation of the Philippines (NGCP) using settlement-based masks derived from GHSL SMOD. Alignment is evaluated using correlation, error, and retained coverage, combined into a composite score. Strongest agreement occurs under low to mid-range valid-pixel thresholds and within urban-focused masks, which balance signal fidelity and temporal continuity at the cost of reduced coverage. Replication across four additional Visayas sub-grids shows that optimal threshold–mask configurations vary by region, reflecting differences in cloud regime and settlement structure.

These results establish explicit conditions under which daily NTL can be interpreted as a proxy for grid dynamics. The framework provides a reproducible basis for reliability-qualified analysis using globally available datasets and can be tested in other cloud-prone regions where ground-based data are limited.

The maintenance of airport pavements is critical to ensuring the safety and efficiency of air operations. Conventional inspection methods are often time-consuming, subjective, and prone to inconsistencies in data collection. Recent advances in unmanned aerial vehicle (UAV) photogrammetry offer a potential alternative for improving inspection efficiency and measurement accuracy.

This study evaluates the applicability of UAV-based photogrammetry for the detection and quantification of pavement distresses under conditions representative of airport infrastructure. Image data were acquired at different flight altitudes and overlap configurations and processed using Structure-from-Motion techniques to generate high-resolution orthomosaics and Digital Elevation Models (DEMs). The resulting datasets were analyzed to identify, delineate, and classify deterioration types and severity levels.

The results indicate that a flight altitude of 10 m combined with 80% longitudinal and 70% transversal overlap provides an optimal balance between spatial resolution and operational efficiency. Under unobstructed conditions, photogrammetric analysis detected more than 98% of existing distresses and enabled more precise geometric delineation compared to traditional field-based methods. Undetected distresses were primarily associated with shadowed or obstructed areas, highlighting the influence of environmental conditions on detection performance.

Overall, the findings demonstrate that UAV-based photogrammetry is a reliable and efficient approach for pavement condition assessment, with significant potential to enhance data quality and reduce inspection time in airport infrastructure management.

3D change detection is essential for monitoring infrastructure, environmental dynamics, and natural hazards. However, existing algorithms are often evaluated on single-scene datasets, and their generalization across varied real-world scenes remains largely unexplored due to the absence of a universal benchmark. To address this issue, we propose MultiChange3D, a multi-scene, multi-sensor 3D change detection dataset for identifying geometric changes in 3D space. The dataset provides registered pairs of point clouds with ground-truth geometric change labels, enabling standardized evaluation across different methods. To demonstrate the use of the MultiChange3D dataset, we benchmark an initial set of approaches on a subset of the dataset. The evaluated methods include classical Euclidean distance-based methods (C2C, M3C2), 3D displacement estimation-based approaches (F2S3, Landslide-3D), and deep learning-based classification methods (KPConv, EF-KPConv, PGN3DCD). Quantitative and qualitative analyses indicate the strengths and limitations of the evaluated methods, highlighting the challenges in cross-scene generalization under variations in point density, scale, and types of changes. The full dataset and evaluation code is openly available at: https://github.com/3DOM-FBK/multichange3d.

Quantifying topographic dynamics from 3D point cloud time series is essential for geoscientific applications. However, laser scanning data typically varies between epochs in point density due to differing survey properties. These irregularities present a challenge for change detection, particularly across multi-temporal and multi-modal data. We propose a new approach, adaptive temporal aggregation, as an extension of the Multiscale Model to Model Cloud Comparison (M3C2) algorithm. Driven by a local point density requirement, our method employs both a spatial and a temporal neighborhood. If a core point's neighborhood is too sparse for M3C2 estimation, an iterative temporal search progressively incorporates data from temporally adjacent epochs until the density requirement is met or a maximum temporal window is reached. This adaptive process ensures sufficient local density while preventing unnecessary temporal aggregation, a key advantage over global aggregation. We evaluated our method on a multi-modal dataset from the Mont-Saint-Michel Bay, France (38 irregular epochs, ~1 decade). Results demonstrate significantly improved change detection, increasing completeness by >13% (vs. standard M3C2) and accuracy by 31% (vs. fixed-window averaging). Our work provides a robust approach for enhancing 3D change detection algorithms for complex, real-world 4D datasets, enabling higher accuracy and completeness in analysing surface dynamics.

Bathymetric Laser Scanning (BLS) enables high-resolution mapping of underwater topography using green-wavelength laser pulses that penetrate the water column. However, precise georeferencing of the BLS data is affected by refraction at the air–water interface, which displaces submerged features and affects conventional strip adjustment methods. This paper introduces an integrated refraction-aware georeferencing workflow that combines refraction correction with trajectory and boresight optimization within a unified adjustment framework. Implemented using the scientific OPALS laser scanning software, the workflow starts with direct georeferencing of uncorrected laser returns, derives a water surface model, applies Snell’s law-based refraction correction, and performs iterative strip adjustment until convergence. The approach was validated using UAV-borne topo-bathymetric LiDAR data from Lake Alm (Almsee) in Upper Austria, captured with a \emph{RIEGL} VQ-840-GE sensor system. Comparative analysis across multiple processing scenarios demonstrates that the proposed integrated method significantly improves internal consistency between overlapping flight strips. The residual height discrepancies, quantified by the median absolute deviation were reduced from 4.5 cm using standard processing workflows to 2.1 cm with the integrated approach — an improvement exceeding 50%. A single processing pass was sufficient for the relatively calm conditions of the test site, though iterative refinement may benefit more dynamic water surfaces. The presented methodology is generic and can be embedded in any laser scanning framework supporting modular georeferencing and refraction correction.

Coastal defense structures, such as breakwaters and groynes are an integral part of coastal engineering. These structures reduce the impact of waves and decrease beach erosion, but due to the constant forces to which they are exposed, repeated monitoring and evaluation is vital to the analysis of their structural integrity. However, coastal defense structures are most often located in the turbulent waters of the surf zone, which characteristics pose severe challenges for current methods. For example, waves pose challenges for image-based analysis, shallow-water limits sonar-based measurements, and currents, represent hazardous environments for surveying personnel. Here, recent advances in topo-bathymetric LiDAR have improved the ability to map data above and below the water surface within the same survey. In the field of structural engineering, point cloud data is already a commonly used information, and thus its applications in the monitoring of coastal defense structures present a natural extension of existing structural monitoring methods. Therefore, this study presents an automatic method for the detection of coastal defense structures with bathymetric LiDAR. The surveyed area consists of multiple groynes located along the Polish coast, which were surveyed using an airplane-based topo-bathymetric LiDAR scanner. The presented method then leverages the echo ratio and repeated clustering to extract the groynes from the data. We evaluate the extracted structures in comparison to manually annotated data. The results of this evaluation display a balanced accuracy of 92%, indicating an overall match with the reference data, but showing challenges and improvements for future work.

A state-of-the-art LiDAR sensor is assessed in terms of the accuracy, described as the sum of trueness and precision, of terrestrial and submerged points. The reference, against which the LiDAR data are evaluated, are conducted with a total station and can be assumed to show an uncertainty of less than 1 cm even for the submerged points. We find that the GNSS-based data set shows a systematic bias of about (-4, 7, 7) cm which can be defined as trueness and does not represent the quality of the LiDAR sensor but mostly of geo-referencing. The precision, which is a measure mostly influenced by the LiDAR sensor itself, is at 0.8 to 2.0 cm for terrestrial points and slightly worse with 1.1 to 2.6 cm for bathymetric points. Our study considers depths of up to 3 m and uses more than 300 points for the assessment.

Worldwide coastal areas comprise environmental triple points (air, land and seawater) that cope with coastal risks at unprecedented rates of change. Wind- and wave-related acute hazards add up to the chronic sea-level rise on interface zones that increasingly host human population and assets. Those societal challenges need to be overcome using the most discriminant and finest remote sensors.

We present an innovative two-step methodology to produce an ultra-high spatial resolution (UHSR) topobathymetry using a fusion of a RGB camera mounted on an aerial drone with a multispectral satellite imagery provided with very high temporal resolution. The fusion relied on a DJI Zenmuse P1 (0,08 m pixel size) borne by a DJI Marice 300 RTK, the PlanetScope SuperDove imagery, provided with eight bands at 3 m, and linear or nonlinear (neural network with two hidden layers endowed with three neurons, each) regression. Once the fusion achieved, both topography and bathymetry were mapped using, either the digital surface model (DSM) derived from the drone-derived photogrammetry, or the DSM combined with the UHSR SuperDove imagery. Both datasets served as predictors to model a digital topobathymetric terrain LiDAR response using linear or neural network regression.

The best drone-satellite fusion was completed by the bandwise neural network regression, ranging from R2test of 0,79 for the purple to 0,94 for the red edge band. The UHSR topobathymetry has been mapped by merging the topography and the bathymetry, distinctly predicted by the combination of the DSM with the UHSR Superdove imagery (R2test of 0,68 and 0,92, respectively).

Rocky coastal environments are ecologically important areas where land and sea processes interact in complex ways. Monitoring these zones is challenging, as they include steep cliffs, partially submerged features, and narrow transition areas where traditional surveying methods often struggle. Several European environmental directives now emphasize the need for regular observation of these coastal systems, increasing demand for practical and accessible surveying tools.

This work presents the development and initial testing of a small uncrewed surface vehicle (USV) designed to collect images above and below the water surface at the same time. The platform is based on a commercially available catamaran-style drone and carries two GoPro cameras mounted on a rigid vertical rod, with one camera positioned above the water and the other just below it. Both cameras are synchronized using GPS time, and the system incorporates a PPK-capable GNSS receiver for improved positioning. The payload is wireless and modular, allowing the platform to be deployed quickly.

The main contribution of the system is its ability to document the air–water boundary in a single pass, reducing issues related to changing meteorological and sea conditions. The paper also discusses how the platform was tested at a rocky site in Sardinia and outlines the types of data that can be obtained for environmental mapping.

The approach aims to offer a low-cost, flexible option for coastal monitoring.

Underwater laser scanners and air-borne laser scanners offer considerable potential for high-resolution monitoring of fine-scale underwater structures in shallow, clear waters. An underwater laser scanner mounted on a vessel is used for kinematic data acquisition in coastal waters. Additionally they are surveyed by an air-borne laser scanner. In this investigation, the resulting point clouds from both systems are analyzed in terms of their performance and achievable relative geometric quality.

The spatial accuracy and resolution of Multibeam Echosounder data are inherently lower than those of high-resolution underwater LiDAR measurements. However, while Multibeam Echosounder provides wide coverage and extensive historical availability, LiDAR is costly and covers relatively small areas. In this study, we propose an innovative approach to enhance Multibeam Echosounder resolution using a Super-Resolution Generative Adversarial Network with direct comparison to LiDAR data for accuracy assessment. The methodology involves converting Multibeam Echosounder data into grayscale format using various depth gradient techniques, analyzing differences in submarine geomorphology through calculations of slope and aspect, and evaluating statistical accuracy. The results show that the Super-Resolution Generative Adversarial Network model successfully improves Multibeam Echosounder resolution, producing data that closely correspond to LiDAR measurements, particularly in flat, sandy seabed areas. In contrast, regions with complex or rocky terrain exhibited more pronounced deviations, especially in aspect metrics, emphasizing the challenges associated with maintaining topographic orientation throughout the resolution enhancement process. The main conclusion is that enhancing Multibeam Echosounder data using Super-Resolution Generative Adversarial Network enables broader utilization of existing datasets to generate high-resolution models, offering a more cost-effective and accurate solution for seafloor mapping in areas where LiDAR data are unavailable.

Geometric correction of satellite images is an essential pre-processing step for accurate geospatial analysis, but non-experts often face practical limitations because detailed sensor models and Ground Control Point data are not readily accessible. Traditional methods rely on physical sensor models or the Rational Function Model (RFM) using vendor-provided Rational Polynomial Coefficients (RPC). However, this information is often unavailable or lacks sufficient accuracy. This paper proposes a two-stage framework that utilizes AI matching technologies and open access data to automatically correct satellite images lacking georeferencing information. In Stage 1, a coarse Affine correction is executed using SuperPoint and LightGlue with an open basemap (Sentinel-2). In Stage 2, precise corresponding points are extracted through patch-based hierarchical LoFTR matching, and 3D GCPs are generated utilizing the SRTM. Subsequently, sensor-independent RPC are robustly estimated through the rpcfit library, and the final geometrically corrected image is generated through resampling.

This framework was verified by applying it to 4.8m resolution BlueBON satellite images that lack georeferencing information. In seven experimental regions with diverse geographical characteristics, an average Root Mean Square Error (RMSE) of 8.050m (1.68 pixels based on BlueBON resolution) referenced to the Sentinel-2 basemap, and an average of 9.02m (1.88 pixels) referenced to Google Maps, was achieved. This result demonstrates that it is possible to precisely correct 4.8m medium-resolution images using a 10m open basemap, providing a practical, accessible, and automated geometric correction solution for general users.

Star centroid localization accuracy fundamentally limits spacecraft attitude determination precision. Existing methods face a critical accuracy-efficiency trade-off: traditional intensity-weighted approaches achieve computational efficiency (<1 ms/star) but suffer from poor noise robustness, while Gaussian fitting and deep learning methods provide high accuracy at prohibitive computational costs. We address this fundamental limitation by developing a principled Bayesian Multi-Scale Adaptive Iteratively Weighted (BMAI) centroid localization algorithm that achieves high accuracy approaching theoretical limits while maintaining real-time computational efficiency. The algorithm integrates four key technical contributions: (1) SNR-adaptive window extraction with robust threshold estimation, (2) regularized iteratively weighted framework with proven convergence properties, (3) multi-scale fusion with SNR-dependent weighting, and (4) gradient-based refinement to mitigate systematic bias. Rigorous theoretical analysis establishes convergence guarantees, derives error bounds, and evaluates Cramér-Rao Lower Bound (CRLB) efficiency. Comprehensive evaluation on 16,500 synthetic star images across six diverse imaging scenarios demonstrates that under high-SNR conditions (SNR >25, n=2,000), BMAI achieves mean RMSE of 0.0120 pixels (95% CI: [0.0116, 0.0124] pixels), representing a 98.6% relative improvement over intensity-weighted centroiding (0.857 pixels), 35.8% improvement over Gaussian fitting (0.0187 pixels) and 95.3% improvement over CNN methods(0.2566 pixels). The algorithm maintains computational efficiency of 0.89ms per star—8.7× faster than Gaussian fitting—while achieving CRLB efficiency of 79.2%. Robustness analysis demonstrates stable performance across SNR range 3-100 with graceful degradation under challenging conditions. The BMAI algorithm fundamentally resolves the accuracy-efficiency trade-off in star centroid localization through principled Bayesian inference and multi-scale processing.

This paper presents a systematic investigation of the PhaseOne native IIQ format for drone and aerial cameras (in particular the recent iXM-RS250 and the iMX-GS120), focusing on the influence of different compression levels on geometric, radiometric and computational aspects of the photogrammetry pipeline. The aim of the presented research and experiments is to demonstrate the actual quality of these (compressed) images for photogrammetric purposes.

Small format multi-head cameras are becoming available and can be flown on light drones to provide simple access to oblique and nadir views of built-up areas. A number of missions with different parameters (flying height, etc.) are investigated to understand the trade-offs in applying those sensors and question the established accuracy laws. We investigate and quantify the ability to completely cover the facades using those sensors in the different scenarios.

In recent years, commercial small optical satellites, e.g., Skysat, BlackSky, and PlanetScope, have become widely used for a variety of Earth remote sensing applications, providing high-resolution images with sub-meter resolution. They are operated in a constellation of multiple satellites, which compensates for the spatial and temporal limitations of traditional satellite observations. Moreover, their data acquired during stereo viewing have been experimentally used to generate digital surface models (DSMs). The CE-SAT-IE is a small optical satellite developed by Japan’s commercial company Canon Electronics Inc. (CE) and was launched on 17 February 2024, by Japan Aerospace Exploration Agency’s (JAXA’s) H3 launch vehicle test flight no.2. It is equipped with an optical frame sensor derived from a commercial off-the-shelf (COTS) camera Canon EOS R5. The ground sampling distance (GSD) is 0.8 m with a scene size of 6.5 km × 4.3 km. The calibration and validation of the sensor are being conducted in collaboration between CE and JAXA, drawing on JAXA’s extensive experience with past satellites. The geometric and radiometric performance of the sensor is analysed in detail, and the results will be used for its subsequent mission, which may involve a constellation for stereo observation to generate high-quality DSMs. This paper reports initial results for geometric calibration and validation of the sensor using ground control points (GCPs) and the experimental generation of DSMs from stereo observation images using the calibrated parameters.

This paper presents a novel hybrid calibration pipeline that jointly estimates the spatial and temporal alignment between a handheld laser scanner and a smartphone camera without any hardware synchronization. The method combines deep-learning-based target detection with classical geometric calibration using 2D-3D correspondences derived from black and white hourglass planar targets. Target centers are precisely localized in both the RGB images and the 3D point cloud using a symmetric templatematching scheme, enabling robust solution of the perspective-n-point (PnP) problem for spatial calibration.

To address the lack of hardware synchronization, we introduce a temporal calibration method that exploits geometric correspondences between rendered intensity images and camera frames.

On a Lixel L2 Pro scanner with a Huawei P20 Pro camera, the pipeline achieves a median Reprojection error of 0.76 px for static calibration and 2.19 px across 91 dynamic evaluations. The approach enables accurate image-pointcloud fusion for scanners without syncronisation interfaces and provides a foundation for colorization, image analysis, and redensification of laser data.

LunarDEM2025 is a lunar topography model (±60°) created by fusing JAXA’s SLDEM2013, CAS’s CE2TMap2015 and NASA’s LOLA laser altimetry tracks. A tile-based, terrain-aware co-registration aligns photogrammetric DEMs to LOLA points, while a slope-constrained residual-compensation filter eliminates striping, voids and artefacts. The resulting dataset shows visibly smoother relief, smaller vertical biases and fewer tile-boundary discontinuities than its predecessor SLDEM2015. The product is ready for landing-site analysis, rover path planning and various other applications.

After completing the 1:2,500,000-scale (1:2.5 M) lunar geologic atlas, our team began exploring the techniques and work flows for compiling larger scale lunar geological maps. Geologic maps integrate multidimensional information such as lithology, structure, and geologic age. Using the Copernicus crater region (0°–16°N, 30°W–10°W) as a case study, this research develops a 1:1,000,000-scale (1:1 M) regional geologic map and, in turn, explores the lithologic and structural classification systems applicable to lunar geologic maps at different scales. Based on imagery, topography, spectral, gravity, and sample data, we analyze geologic features including impact craters, impact basins, compositions, and structures, and subsequently delineate geological units. In the study area, the Copernicus crater and Imbrium basin represent the most prominent geological events and can serve as benchmarks for relative age determination. The cross-cutting relationships among geological units, together with existing absolute age constraints (from isotopic dating and crater size-frequency distribution chronology), are used to establish the stratigraphic relationships among mapped features and layers, ultimately producing a regional geologic map. Based on this map, the geological evolution history of the region is reconstructed.

High-accuracy planetary mapping products are increasingly required for landing-site assessment, precision navigation, and future surface operations on the Moon and Mars. Although massive orbital remote sensing images are available, the geometric accuracy and spatial resolution of many existing mapping products is still insufficient for engineering applications. A major bottleneck is large-scale bundle adjustment, whose reliability is strongly affected by data quality, control network strength, as well as engineering experience. Compared with Earth observation photogrammetry, planetary mapping faces great challenges such as heterogeneous sensor models, complex illumination, sparse absolute control. This paper summarizes a practical quality control framework for large-scale bundle adjustment of planetary remote sensing images. The workflow is divided into four coupled stages: data preprocessing, control network construction, parameter setting, and accuracy evaluation. The framework is distilled from previous planetary mapping studies, open-source software platforms and our practical experience in processing tens of thousands of planetary images. Experiments using LRO NAC datasets demonstrate that satisfactory bundle adjustment results can be achieved when the proposed strategy is applied. The framework improves the overall efficiency, controllability, and reliability of large-scale planetary photogrammetric processing.

China has successfully carried out the Chang'e-1 to Chang'e-6 lunar missions and the Tianwen-1 Mars mission. In these missions, planetary photogrammetry and remote sensing technologies provide timely spatio-temporal information services across all phases of the missions, playing a crucial supporting role in ensuring the mission safety and scientific output. In the current era of artificial intelligence (AI), the deep integration of photogrammetry and remote sensing, geomatics, and artificial intelligence is gradually evolving into Spatio-Temporal Intelligence (STI). This paper presents an overview of the advances and applications of STI in China’s lunar and Mars explorations, and discuss the future directions of STI in deep space exploration.

Based on microwave radiometer (MRM) data from China's Chang'e (CE)-1/2 satellites, the Brightness Temperature Difference (TBD) technique offers a method for probing lunar regolith properties. However, its global application is compromised by systematic latitudinal biases and an unverified link to subsurface deposits.

This study introduces a novel parameter, the effective TBD (TBDeff), to overcome these limitations. The methodology first defines an equivalent TBD (eTBD), simulating the TBD for a location as if it were on the lunar equator to mitigate latitudinal effects. Recognizing inherent limitations in this simulation, a supplementary parameter (sup_TBD) is derived. TBDeff is then developed by integrating sup_TBD with the observed TBD (TBDobs) from CE-2 data.

Results demonstrate that TBDeff successfully removes latitudinal bias on a global scale, enabling clearer discrimination between lunar maria and highlands. Furthermore, extensive low-TBDeff signals in polar regions (>85°) suggest a new potential for detecting subsurface deposits in permanently shadowed areas.

Crucially, correlation analysis with (FeO+TiO₂) abundance reveals that TBDeff exhibits a significantly stronger relationship with regolith composition than traditional TBD or simple brightness temperatures (TB), especially at lower frequencies (reaching a correlation coefficient of 0.86 at 3.0 GHz). This confirms that (FeO+TiO₂) abundance is a key factor influencing the dielectric properties of subsurface materials, a effect previously obscured by latitudinal interference. The TBDeff method thus provides a more reliable tool for interpreting lunar composition from microwave data.

This study analyzed and compared in situ spectral obtained by the Chang’E-3(CE-3) and Chang’E-4(CE-4) rovers, laboratory spectra of Chang’E-5(CE-5) soils and remote sensing spectra. The remote sensing spectra exhibit significantly darker and shallower absorption features than laboratory or in situ spectra, reflecting highly weathered nature of the undisturbed lunar surface. The spectral upturn even just right >2 μm can be contributed by thermal emission, revealing micro-scale temperature variations and low thermal inertia of lunar soils. CE-5 sample spectra show significantly higher reflectance and absorption depths than in situ and remote sensing, indicating samples are fresh and couldn’t represent pristine/true lunar surface. The CE-5 samples provide a new ground truth for estimating the TiO2 content of young basalts, which have the largest uncertainty in TiO2 content. Contrary to traditional opinion, CE-3 in situ spectra revealed that the effect on the spectral slope caused by space weathering is wavelength-dependent: the visible slope (VS) decreases not increases. The optical effects of space weathering and TiO2 are identical: both reduce albedo and blue the spectra. This suggests that a new TiO2 abundance algorithm is needed.

Miniaturized UAV laser scanning systems have advanced rapidly over the past decade, especially in the low-cost sector. DJI entered this field with the Zenmuse L-series, integrating GNSS/INS with compact scanners. While the first-generation L1 showed moderate precision, the L2 improved notably through reduced beam divergence. In November 2025, DJI released the Zenmuse L3. In this contribution, we assess its performance.

The main upgrade from L2 to L3 lies in the LiDAR unit: L3 uses a single 1535 nm laser instead of multiple 905 nm diodes, offers a symmetric 0.25 mrad beam divergence, and supports pulse repetition rates from 350 kHz to 2 MHz. High PRR operation is limited to altitudes ≤50 m due to missing multiple-time-around resolution. Scan modes include linear, non-repetitive, and a new star-shaped pattern.

L2 and L3 were tested at three sites in Lower Austria covering a warehouse, power-lines, and forests. Flights were conducted at 80 m AGL (350 kHz) and, for the warehouse, 50 m AGL (2 MHz). Precision, strip consistency, point density, feature separability, and vegetation penetration were evaluated using the scientific software OPALS.

L3 data showed sharper edges, reduced noise, and higher separability, yielding spline-fit residuals of 0.9 cm versus 2.6 cm for L2 for reconstructing a double-threaded power-line. Ground point coverage in forests increased from 18 % (L2) to 51 % (L3). Strip height differences are around 2 cm for both sensors and L3 achieved sub-centimeter precision on sealed surfaces. Overall, L3 offers substantial gains in spatial resolution, precision, and vegetation penetration.

Intrinsic calibration of rotating multi-beam lidars (RMBL) enables more precise measurements. We calibrated our sensor to improve its geometric and radiometric accuracy using a rotating tilted platform. The rotating mechanism widens the field of view of each lidar channel and allows all lasers of the sensor to measure the same areas in a room containing planar wall and floor sections. Therefore, we can collect measurements for geometric and radiometric calibration with minimal amount of calibration targets. Furthermore, we used data based numerical minimization to estimate the calibration parameters for all 128 lidar channels in our RMBL sensor. For the intrinsic geometric calibration of the sensor, we estimated the elevation and azimuth angles of each laser. For the radiometry, we estimated a linear model for each laser to correct the intensity measurement. For a linear model, two different known diffuse reflectance targets are sufficient for the radiometric calibration. We tested our methods in two different environments, in an office room and a longer corridor. We showed that the methods can improve the precision of the RMBL sensor significantly. Regarding geometry, we were able to reduce the error on average from 16.1 mm to 15.1 mm (6.2% improvement). For radiometry, we were able to improve the reflectance measuring accuracy on average from 9.5% errors down to -0.9% errors (91% improvement).

In recent years, laser scanning has evolved into a core surveying technology for 3D mapping, both statically from stationary scan positions (terrestrial laser scanning, TLS) and kinematically from moving platforms (kinematic laser scanning, KLS). Consequently, there is a growing demand for methods that efficiently and coherently support both static and kinematic data acquisition modes. This contribution presents a tightly-coupled approach for the co-registration of TLS and KLS data, which simultaneously integrates GNSS positions, inertial measurements, planar features extracted from both static and kinematic point clouds, and control information in a joint non-linear least-squares adjustment. This is neither just a transformation of the kinematic onto the static point cloud nor a simple correction of the trajectory in e.g., a strip adjustment, but rather a tightly coupled adjustment of static and kinematic data. This approach avoids the need for additional survey control for kinematic data by leveraging the static scan data as a proxy, enabling accurate georeferencing even in scenarios where the individual datasets cannot be reliably tied to control points. Results show that the co-registration notably improves the relative consistency of kinematic datasets with respect to a static reference. Such co-registration enables new use-cases for multi-modal data acquisition, such as change-detection in repeated kinematic data acquisitions with respect to a static reference dataset, or more flexible ways of integrating ground control in kinematic surveys.

This study investigates the use of a distributed asynchronous lidar system for augmented position and orientation determination in Global Navigation Satellite Systems (GNSS) denied environments. An asynchronous lidar design is one in which the laser transmitter and detectors/receivers are disconnected and carried on separate platforms. This unique geometry offers observational redundancy that can be used to estimate the trajectory of the receiver platforms. The paper presents the results of simulation experiments, first examining single epoch solutions and then considers estimates of position and orientation along simulated flight trajectories. The results show that as long as the laser transmitter is operated above the GNSS denied environment, the system is able to simultaneously estimate position and orientation for multiple receiver drones, even for extended periods of GNSS outages. The accuracy of position and orientation estimation is dependent on the exact flight path and the number of lidar receivers in the solution, but with favorable geometry the accuracy of position estimation can approach that provided by a high precision GNSS solution.

This work extends our initial proof-of-concept via emulations on the benefits of relative spatial constraints between imagery and lidar point clouds in a factor graph based optimization with satellite positioning (GNSS) and raw inertial readings (Mouzakidou et al., 2025). Here, we demonstrate practically the automatic extraction and integration of 2D-3D correspondences established in the 3D domain within rough natural terrain flown over by an aircraft with sensors of high quality. We show that considering cross-domain (i.e. 2D-3D) constraints enables the calibration of internal camera parameters and its boresight on job, i.e. within mapping flight configurations, where conventional approaches fail. The common optimization of raw IMU data with such constraints improves the respective agreements between the lidar and image dense clouds, achieving consistency at ground resolution level, which is not the case for the conventional (standard) processing of acquired data.

Visual-inertial odometry (VIO) plays a key role in modern navigation and mapping systems.

For their successful integration, an initialization phase, in which IMU-related bias factors are estimated, becomes a fundamental step.

Without one, the subsequent nonlinear estimation of the platform pose may fail to converge or completely diverge.

As reliance on visual and inertial information may exhibit instability due to error accumulation with time, incorporating absolute positioning information through global navigation satellite system (GNSS) measurements, may enhance its robustness and accuracy.

Accordingly, GNSS and visual-inertial initialization frameworks have been receiving growing attention in recent years where current strategies tend to follow a loosely-coupled formulation that first initializes the VIO trajectory, and then aligns it with GNSS measurements.

Such strategies are multi-stage, nonlinear, and computationally expensive, motivating us to introduce an alternative framework in which GNSS position is integrated with the raw visual-inertial measurements to form absolute translation constraints.

Accordingly, we achieve a closed-form, linear and globally consistent drift-free solution which is computationally efficient and requires neither 3D reconstruction nor nonlinear refinement, as common approaches do.

Testing our initialization formulation on benchmark multi-sensor datasets, results show that we outperform current baselines while exhibiting robustness in challenging scenarios.

Shortwave infrared (SWIR) imaging from uncrewed aerial vehicles (UAVs) remains rare despite strong sensitivity to canopy water and protein. We present the first field validation of a six-band VNIR/SWIR multi-camera system designed for plot-scale monitoring of winter wheat using mid-sized UAVs. The payload utilized narrow bandpass filters (910, 980, 1100, 1200, 1510, and 1650 nm; FWHM 10–12 nm) and was operated at an altitude of approximately 30 meters above ground level, achieving a ground sampling distance of approximately 4 cm. Empirical line calibration, employing in-scene gray panels, was validated against material-distinct panels and spectroradiometer measurements. The spectral response functions were approximated using Gaussian convolution due to the narrow passbands. Five bands (980–1650 nm) exhibited excellent performance: empirical line model fits achieved R² values approaching 1.000 (RMSE = 0.003–0.009), independent panel validation demonstrated near-unity slopes (R² = 0.998–0.999; RMSE = 0.005–0.013), and plot-level canopy measurements (n=36) maintained strong agreement between camera and spectroradiometer (slopes = 0.943–1.079; R² = 0.58–0.85; RMSE = 0.010–0.023). Two SWIR normalized ratio indices exhibited robust cross-sensor agreement: NRI[1100,1200] (R² ≈ 0.93) and NRI[1650,1510] (R² ≈ 0.90). The 910 nm channel displayed systematic errors (slope = 0.442±0.040 for plots; MAPE ≈ 33%) due to identified out-of-band leakage from incomplete long-wave blocking, leading to its exclusion from accuracy claims. Mitigation strategies include higher optical density short-pass blocking and system-level spectral response function verification. The filter-reconfigurable payload provides quantitative reflectance and robust SWIR indices at the plot scale by integrating panel-anchored empirical line modeling with bandpass-aware harmonization, thereby advancing operational SWIR monitoring capabilities for precision agriculture applications.

This contribution presents PanX.4, a gyrocopter-borne six-band VNIR multicamera system developed within the KIBI project on AI-based identification and classification of protected plant communities (mFUND, FKZ 19F2276) to support cross-scale monitoring at Natura 2000 sites. The system is designed for spectral alignment with Sentinel-2 MSI bands B02–B06 and B08 and is integrated into a tri-sensor airborne suite on the FlugKit carrier platform together with a high-resolution RGB camera and a complementary six-band VNIR–SWIR imaging system. Using system-level spectral response characterization and spectral band adjustment factor (SBAF) analysis based on 1,057 ECOSTRESS spectra, the study quantifies the harmonization quality between PanX.4 and Sentinel-2A, S2B, and S2C. All bands achieved R² > 0.99, while comparative screening of alternative spectral configurations showed that careful band design is critical, particularly in the red-edge region. An additional inter-satellite sensitivity analysis further indicates that harmonization should account for band-dependent differences between Sentinel-2 units when multitemporal airborne and satellite observations are combined. To support multitemporal habitat monitoring, the paper also analyzes 86,947 first-mowing observations from 2017 to 2024 and derives a three-window acquisition concept synchronized with pre-mowing, post-regrowth, and senescence phases. This creates an operationally relevant framework for planning repeated airborne campaigns that can support validation, boundary refinement, and future machine-learning workflows for habitat classification. The contribution therefore establishes the sensor-design, spectral-harmonization, and temporal-planning basis for Sentinel-2-consistent airborne monitoring at sub-meter resolution. Operational airborne image products and in-flight validation are beyond the present contribution and form the next step for future deployment.

Atmospheric correction of large-scale aerial imagery remains a major challenging, mainly due to the difficulty of accurately estimating atmospheric parameters within the images. This study proposes a novel atmospheric correction method based on satellite-derived Surface Reflectance (SR). The method is a semi-empirical linear correction approach that leverages Pseudo-Invariant Features (PIFs) as reference points. Experimental results show that, the proposed method achieves performance comparable to radiative transfer models approach when accurate atmospheric parameters are available, and provides more reliable corrections when such parameters are uncertain or unavailable.

Spectral unmixing estimates the fractional abundances of materials, having associated spectra called endmembers, in pixels acquired by imaging spectrometers. Validation of abundance estimation methods typically relies on synthetic data or comparisons to results obtained by other algorithms. This study considers results of typical abundance estimation algorithms on the DLR HySU (HyperSpectral Unmixing) benchmark dataset, which contains actual imaging spectrometer data acquired over several arrangements of known-size material patches for physically traceable validation. Abundance estimates are compared against measured target areas in pixels with different degrees of mixtures. We evaluate least squares and sparse unmixing methods across different noise scenarios on real data, and by contaminating the library through addition of non-relevant endmembers. Additionally, as a way to approximate hard sparsity constraints, we enforce cardinality constraints on endmember subsets, identifying those minimizing abundance errors relative to the full library. Results suggest that fully constrained least squares yields usually the best results, but struggles in cases of highly mixed pixels. Finally, we test quantization of abundance values as a way to enforce sparsity in non-negative least squares with limited but encouraging results. Overall, the increase in accuracy of results enforcing sparse solutions support the use of computationally efficient sparse unmixing methods in practical scenarios, part of which may become feasible if quantum computing capabilities improve in the future.

The Pelican satellite constellation, first launched by Planet Labs in 2025, continues the high-resolution imaging capability established by the SkySat program. The change to pushbroom sensor in Pelican presents new geometric challenges: satellite attitude variations and platform instabilities during acquisitions can produce band misregistration and geolocation errors that degrade downstream products. This paper presents an operational workflow developed for Pelican imagery, validated on Pelican-2, a technology demonstration satellite. The approach exploits the dual-panchromatic focal plane configuration to independently measure satellite wobble to greater accuracy than on onboard attitude sensors, combined with selective bundle adjustment and B-spline spatial correction to achieve sub-pixel band alignment without dense ground control points. Validation on 963 Pelican-2 scenes demonstrates sub-pixel band-to-band registration accuracy (RMSE < 0.12 px) and 4 m CE90 geolocation accuracy. Applications illustrate the potential for operational geoscience workflows: earthquake surface displacement mapping of the March 2025 Myanmar M7.7 rupture detects 4.0 m co-seismic offsets on the Sagaing Fault with minimal post-processing, and digital surface model generation from an opportunistic multi view acquisition yields preliminary elevation products free of jitter artifacts, demonstrating operational feasibility for constellation-scale processing.

Initial applications showcase operational potential: earthquake surface displacement mapping detects 4.0 m co-seismic offsets from the March 2025 Myanmar M7.7 rupture with minimal post-processing; digital surface model generation yields elevation products free of jitter artifacts. Results establish feasibility for constellation-scale processing and inform next-generation Pelican development.

Remote sensing change detection (RSCD) aims to identify pixel-wise surface changes from co-registered bi-temporal images. However, many deep learning–based RSCD methods rely solely on change-map annotations and underuse the semantic information in non-changing regions, which limits robustness under illumination variation, off-nadir views, and scarce labels.

This paper presents ChangeDINO, an end-to-end multiscale Siamese framework for optical building change detection. The model fuses a lightweight backbone stream with features transferred from a frozen DINOv3, yielding semantic- and context-rich pyramids even on small datasets. A spatial–spectral differential transformer decoder then exploits multi-scale absolute differences as change priors to highlight true building changes and suppress irrelevant responses. Finally, a learnable morphology module refines the upsampled logits to recover clean boundaries. Experiments on four public benchmarks demonstrate that ChangeDINO achieves strong accuracy and robustness under cross-temporal appearance variations, yielding cleaner building boundaries with improved data efficiency.

Multi-class building change detection in high-resolution aerial imagery is essential for urban monitoring, yet remains challenging due to severe class imbalance and the limited representational capacity of encoders trained from scratch. We propose Hie-DinoMamba, a novel architecture that integrates a frozen 1.1B-parameter DINOv3-L encoder—pre-trained on the SAT-493M satellite dataset—with a newly designed Hierarchical Mamba FPN decoder. To bridge the domain gap between satellite pre-training and aerial imagery without incurring prohibitive computational costs, we adapt the encoder using parameter-efficient Low-Rank Adaptation (LoRA), updating only a small fraction of parameters while preserving the encoder's rich pre-trained knowledge. The decoder fuses multi-scale feature pairs from both time points via channel-wise concatenation and 1×1 projection, then refines them in a top-down manner using Visual State Space Model (VSSM) blocks that capture long-range spatial context with linear complexity. A dual-loss strategy decouples semantic classification (Focal Loss) from boundary delineation (Focal Tversky + Dice Loss), optimizing each objective at a different hierarchical level. On a 4-class aerial building change detection benchmark (41,548 image pairs, 0.1 m resolution, Seoul), Hie-DinoMamba achieves a state-of-the-art mIoU of 65.12% and Kappa of 75.77%, improving over the strongest baseline by 2.1 percentage points. An ablation study confirms that LoRA adaptation is the most critical component. Qualitative analysis further demonstrates robust generalization to geographically unseen regions.

This study presents a stepwise optimization pipeline for high-resolution building change detection in dense urban environments using imagery from CAS500-1, Korea’s national land observation satellite. A dataset of 3,816 bi-temporal patch pairs from 29 urban regions was constructed to support model development and evaluation. A Mamba-based architecture, incorporating efficient global context modeling, was adopted as the baseline for binary change detection.

To enhance performance, the pipeline introduced three sequential optimization stages. First, normalization techniques suited for 12-bit radiometric imagery were compared, including percentile-based scaling, gamma adjustment, and logarithmic transformation. Second, augmentation strategies were evaluated, contrasting standard geometric augmentation with extended optical and temporal augmentation designed to improve generalization in structurally complex urban environments. Third, multiple ensemble strategies, ranging from simple averaging to confidence-weighted and hierarchical aggregation, were examined to overcome the limitations of individual model sizes.

Model performance was assessed using a comprehensive set of pixel-level, change-pixel-level, contour-based, and object-based metrics to ensure robust evaluation of both spatial precision and structural consistency. Experimental results showed that gamma-based normalization, comprehensive augmentation, and selected ensemble strategies each contributed measurable improvements. Combining these optimized components yielded a final hierarchical ensemble that improved the F1-Score from 0.7629 to 0.8070, representing a substantial gain over the baseline model.

Overall, this work provides a validated and extensible optimization strategy for high-resolution satellite-based change detection, offering practical guidance for operational applications and adaptability to future ensemble configurations across diverse architectures.

Recent advances in geospatial foundation models have enabled scalable and transferable solutions for Earth observation (EO) tasks, which can make them good candidates to achieve the requirements mentioned above. Foundation models are types of large-scale artificial intelligence (AI) models trained on massive and diverse datasets. In the EO domain, these datasets may include imagery, elevation models, geographic coordinates, temporal tags, sensors spectral information, and descriptive metadata. These models excel at representation learning through self-supervised training, enabling them to capture rich descriptive features without requiring labelled data. Consequently, they can serve as powerful backbones for downstream tasks such as land-cover change monitoring.

Accordingly, this paper provides an overview of the development process of a geospatial foundation model, Planaura. It demonstrates how this model is best adapted to Canadian landscapes and how it is used to achieve the task of land-cover change detection. Planaura is now accessible publicly via the model hub at HuggingFace: [Link hidden for blind review process]

This paper presents a novel transformer-based framework for spatiotemporally dynamic spectral unmixing of multispectral satellite imagery. Spectral unmixing is essential for analyzing mixed pixels in remote sensing, especially in analyzing small objects such as narrow rivers when using coarse-resolution observations such as Sentinel-2 data. Most deep-learning based unmixing models typically account for a single scene and ignore the tempo-spatial variation of spectra and land-cover proportions.

To address this challenge, we introduce a unified deep learning architecture that leverages transformer attention mechanisms to exploit both spectral and auxiliary information causing spectral variations. The framework models the temporal and spatial evolution of abundances while simultaneously learning representative endmember spectra. By integrating cross-attention between spectral inputs, auxiliary variables, and temporal embeddings, the model can adapt to seasonal changes, illumination conditions, and scene-specific variability. The method is trained using synthetic mixtures derived from Sentinel-2 surface reflectance data.

Applied to monitoring small rivers with strong temporal, and spatial, and intrinsic variability, the proposed approach demonstrates improved accuracy in estimating water abundances and extracting water spectra in highly mixed river pixels (mixed with water and riverbank). The model effectively captures tempo-spatial transitions in water extent and sediment-laden river inflows, offering a more consistent representation than conventional unmixing techniques.

This work contributes a generalizable and end-to-end framework for handling dynamic unmixing scenarios in multispectral remote sensing. It provides new insights into the use of transformers for modeling spatiotemporal interactions and supports applications in environmental monitoring and water resource assessment.

Land cover classification (LCC) plays a crucial role in geoscientific research and resource monitoring applications. Compared

with traditional single-modal classification methods, multimodal fusion models can more effectively leverage the complementary

information of optical and synthetic aperture radar (SAR) imagery, thereby improving classification performance in complex scen-

arios. However, due to the significant differences in the imaging mechanisms of the two sensors, inconsistencies in radiometric

properties and spatial structures arise between optical and SAR images, posing challenges for cross-modal feature interaction and

fusion. To address this issue, we propose a multimodal optical–SAR fusion network (MOSFNet) for high-precision LCC, which

incorporates two core modules: the Feature Interaction Module (FIM) and the Feature Fusion Module (FFM). The FIM achieves

complementary feature interaction between optical and SAR images through channel splitting and cross concatenation, while in-

corporating a coordinate attention mechanism to enhance the responsiveness of key land cover regions. The FFM leverages a 2D

selective scan (SS2D) mechanism to implement bidirectional cross-modal feature alignment and gated fusion in the hidden state

space, enabling deep correlation and adaptive integration of optical and SAR features. Experiments on the WHU-OPT-SAR dataset

demonstrate that MOSFNet significantly outperforms existing methods in terms of classification accuracy and model generalization,

providing an efficient and robust solution for high-precision land cover mapping with multi-source remote sensing imagery.

Change detection in remote sensing imagery is a crucial method for obtaining dynamic information about land cover. However, pseudo-changes caused by seasonal variations pose a significant challenge to detection accuracy. Seasonal variations, such as vegetation phenology and snow cover, introduce global appearance differences that are often mistaken for actual land cover changes. This phenomenon is particularly prominent in long-term monitoring tasks, where pseudo-changes dominate the detection results. Addressing the issues of global appearance differences and multi-scale feature fusion induced by seasonal changes, We propose a novel Seasonal-Aware Scale-Semantic Consistency Alignment Change Detection Network (SSCANet) for remote sensing image change detection. This approach incorporates a Seasonal-Aware Scale Alignment (ASA) module and a Seasonal-Aware Semantic Guided Fusion (SGF) module. By employing spatial scale transformation and semantic alignment, it reduces information mismatch in multi-scale feature fusion and enhances the perception of details in change regions. Experiments conducted on the GZ-CD and CDD datasets demonstrate that SSCANet achieves overall accuracy with F1 scores of 89.21% and 97.82%, with precision rates of 89.02% and 98.37%, respectively. These results represent significant improvements over other methods, demonstrating that SSCANet outperforms its counterparts in both overall accuracy and seasonal robustness. The findings confirm that this approach effectively suppresses seasonal false changes, enhancing the accuracy and reliability of change detection.

Southwestern China’s complex terrain and climate make landslides frequent, especially along highways where numerous high, steep artificial slopes are formed during construction. These slopes often deform or fail within 1–2 rainy seasons due to intricate geology, severely affecting construction and infrastructure safety. An automated, real-time monitoring and early-warning system is therefore urgently needed.

Conventional techniques (leveling, GPS, crack meters) are limited by small coverage, low efficiency, high cost, and inability to detect regional or hidden deformations. Spaceborne InSAR offers wide-area, high-precision, all-weather monitoring but faces severe decorrelation noise from dense vegetation and atmospheric delay errors in mountainous regions.

This study developed advanced InSAR methods for artificial slopes along the Huali Highway (G4216) in Yunnan Province. Using TCPInSAR and >240 Sentinel-1 images (2015–2025), we retrieved surface deformation throughout pre-construction, construction, and post-construction phases. To overcome local challenges, two novel correction approaches were proposed: (1) a noise-reduction method based on spatial correlation estimation of deformation signals, effectively suppressing vegetation-induced decorrelation; and (2) an atmospheric correction technique using Singular Spectrum Analysis (SSA), significantly reducing delays caused by complex weather.

Results show the improved InSAR system successfully detected multiple deformation zones along the corridor and provided reliable early warnings for safety management. By addressing key technical bottlenecks, this work validates the practicality and effectiveness of advanced InSAR for automated slope stability monitoring in geologically and environmentally complex regions, offering valuable reference for similar large-scale infrastructure projects.

Meteorological control of L-band forest backscatter from the BorealScat-2 radar tower

How strongly do weather conditions imprint on L-band radar signals from forests at sub-daily time scales? This question is investigated using the BorealScat-2 tower experiment in the Svartberget Experimental Forest (northern Sweden). The system acquires fully polarimetric, tomographic radar data at P, UHF and L band every 30 minutes, providing height-resolved backscatter profiles from the ground, through the trunk zone, into the upper canopy. Within the shared footprint, an ICOS flux mast delivers continuous measurements of CO₂, water vapour and energy fluxes, together with radiation, vapour pressure deficit (VPD), temperature, wind and precipitation. Sap-flow sensors, dendrometers and soil water probes further characterise water storage and transport in trees and soils, offering an unusually detailed description of forest water dynamics.

The study will focus on L-band backscatter during late spring and summer, quantifying how diurnal amplitude, phase and vertical centre-of-mass in different height zones and polarisations relate to VPD, temperature, radiation and rainfall. It will specifically assess the relative roles of atmospheric demand, canopy wetness and soil water status in driving sub-daily L-band variability, and examine differences between co- and cross-polarised channels and between structural layers. Overall, the study aims to provide process-based insight into how specific meteorological drivers control sub-daily L-band radar variability in boreal forests, supporting the interpretation and modelling of future vegetation radar missions.

The digital elevation model (DEM) based on synthetic aperture radar interferometry (SAR, InSAR) technology have become an important data source for large-scale topographic mapping, but their characteristics vary with satellite systems and methodologies. In this paper, we conduct the cross-validation for the first time to compare the LuTan-1 raw DEM (LT-1 RDEM) and GaoFen-7 (GF-7) satellite laser altimetry data. Besides, we compared the penetration capabilities of SAR satellites including C-band SRTM and X-band TanDEM-X. The optically derived ZiYuan-3 (ZY-3) DEM was also included for multi-source cross-validation. Taking Guyuan County, Hebei Province, China (including four landform types: plains, tablelands, hills, and mountains) as the study area, we introduced GF-7 laser altimetry points (LAPs) as the verification benchmark to cross-validate the elevation accuracy of LT-1 RDEM, SRTM, TanDEM-X DEM (TanDEM), and ZY-3 DEM. The results indicate that: (1) Topographic relief has a significant impact on accuracy, and the RMSE of the DEMs in the study area generally increases sequentially with the intensification of topographic relief; (2) Benefiting from the 10-meter spatial resolution, LT-1 RDEM performs best in detail representation; (3) In terms of mean height error, LT-1 RDEM exhibits a general negative bias, confirming the stronger penetration capability of the L-band, and its elevation values may be closer to the true ground surface; (4) The RMSE of LT-1 RDEM in the study area is 1.958m, slightly larger than TanDEM’s 1.65m, but in fact, the accuracy of TanDEM as a digital surface model (DSM) may be systematically overestimated by laser altimetry data.

This study evaluates the operational capability of the Chinese LuTan-1 (LT-1) L-band SAR constellation for monitoring the Hong Kong–Zhuhai–Macao Bridge (HZMB), a representative sea-crossing bridge under a complex subtropical marine climate. Leveraging the advantages of L-band SAR—including strong resistance to decorrelation and a spatial resolution of up to 3 meters—we applied the Small Baseline Subset (SBAS) technique to 47 ascending and descending orbital images. To the best of our knowledge, this represents one of the first comprehensive deformation studies of the HZMB using the LT-1 constellation. A key aspect of our methodology is the cross-validation between multi-orbit datasets, which confirmed both the reliability of the measurements and the complementary distribution of coherent points due to SAR imaging geometry. The results indicate overall structural stability of the HZMB, with the maximum deformation localized at the Jianghai Navigation Bridge, showing a Line-of-Sight (LOS) displacement rate of –4.3 mm/yr. In contrast, the two artificial islands exhibited minor deformation, with LOS rates not exceeding –3.0 mm/yr. These findings validate LT-1 as a powerful and reliable tool for the operational health monitoring of large-scale coastal infrastructure.

LuTan-1 (LT-1) satellites have been launched for about 4 years. About 771,282 images have been distributed to the users of China till 29th October, 2025. Main application purpose of LT-1 is geohazard monitoring and geoinformation production. Interferometric capability is the primary consideration for LT-1. In this paper, we assessed the interferometric applications in the natural resource monitoring industry. First, we overviewed the status of LT-1, the main interferometric products were introduced as S2A, S2B, S3A, S4A, S5A, S5B and S5C. They are geometrically calibrated single look complex (SLC) image, interferometrically calibrated SLC, differential interferometric synthetic aperture radar (SAR, InSAR, DInSAR) products, stacking, MTInSAR, digital orthorectified image, and digital surface model, respectively. S2A are generated after geometric calibration, the geometric accuracy is about 1.53 after calibration. The baseline is then calibrated for helix bistatic formation data and generate S2B whose accuracy is better than 0.96 m. S3A, S4A and S5A are all used for deformation monitoring, the accuracy values of them are 2.7 mm, 8.6 mm/yr, and 3.7 mm. Geometric accuracy of S5B is 12.5 m, and the height accuracy of S5C is better than 4.7 m. More than 330 geohazards were detected in Guangdong province. The geohazards recognition rate in the field working stage increase from 28% to 47.24%. Even a prediction has been made to avoid disaster for a family and saved 3 people. The application effectiveness has been validated through those years.

The influence of soil moisture change on interference phase information is fully taken into account for accurate deformation monitoring in this research. Especially the effects have more prominent contribution to L-band SAR data. In order to obtain high-precision surface deformation information over agricultural area, the interference phase component caused by soil moisture change should be considered, and the optimal processing of interference phase information is achieved. The reliable interference phase information characterizing the surface deformation details is obtained, thus the natural surface deformation information with high precision can be achieved. Firstly, the penetration depth of different band SAR for agricultural soil was analyzed and simulated. And the sensitivity between penetration depth variation and different band SAR signals were discussed. The fact of soil moisture changes for interferometric phase contribution is confirmed, which provided the foundation for reliable deformation montoring considering the soil moisture variation effects, especially for L-band SAR data. The periodic irrigation for the wheat fields will induce soil moisture variation, which may result in the penetration depth change for radar electromagnetic wave. Therefore, the phase component was derived by the variation of soil moisture over the wheat fields. Multi-temporal Lutan-1 SAR data were acquired over ShanDong agricultural plain in China. The obvious ‘deformation details’ induced by the soil moisture change were acquired over the agricultural area, which demonstrated the effect of soil moisture variation for interference phase. Therefore, the accurate deformation details over agricultural area can be obtained by the combination of soil moisture information.

Asteroid exploration is crucial for understanding the solar system’s origin, but establishing a precise body-fixed coordinate system—relying on accurate rotation parameters—remains challenging. Conventional methods like ground-based light curve inversion often lack precision: for example, it yielded ±2° errors for Ceres’ pole and ±10° for Vesta’s, failing to meet demands for topographic mapping and navigation. This study proposes a refinement method combining stereo intersection angle optimization and grayscale threshold masking. First, using the camera’s interior orientation parameters and tie point coordinates, relative orientation of stereo image pairs is conducted to build a stereo model, followed by forward intersection to calculate intersection angles. Only pairs with favorable geometry (intersection angle >5°) are retained to avoid large position errors from nearly parallel sightlines. Second, a grayscale-based binary mask is created to separate the asteroid from the deep-space background, eliminating spurious edge features that cause mismatches; the SIFT algorithm then extracts and matches features exclusively within the masked region. Finally, an “exhaustive search” iteratively refines rotation parameters using optimized matched points. Validated on 127 Hayabusa2 ONC-T images of asteroid Ryugu (captured July 10, 2018, 2.11m/pixel), the method reduced 5,174 initial candidate pairs to 1,454 valid ones (137,191 matched points). After 4 iterations, refined parameters were RA=96.5° and Dec=-66.4°, with minimal errors (δRA=0.069°, δDec=0.0126°) against reference values (RA=96.431°, Dec=-66.387°). Compared to methods without the two strategies, mismatches dropped from 14,949 to 7,369, and forward intersection residuals decreased. Future work will integrate initial parameters into a bundle adjustment model for further refinement.

The lunar polar regions have emerged as core targets in lunar exploration, primarily due to the potential water ice resources stored within their permanently shadowed areas. However, the complex terrain and extreme illumination conditions in these polar regions present significant challenges to the navigation of lunar rovers—systems that previously relied on dead reckoning and visual matching techniques. To address this, active 3D sensors such as LiDAR will be integrated into future exploration missions.Simultaneous Localization and Mapping (SLAM) based on multi-sensor fusion via factor graphs can significantly enhance the localization robustness of rovers on the lunar surface. In this context, we propose the Lunar Scene Recognition Adaptive SLAM (LSRA-SLAM) method: a framework that leverages environment-aware pre-training to dynamically adjust factor-graph weights, thereby achieving more consistent fusion of stereo camera, LiDAR, and IMU measurements across diverse lunar scenarios. We also introduce a reinforcement learning-based online training strategy, which enables the network to robustly learn from the system's dynamic behaviors. Simulated experiments validate the effectiveness of the proposed LSRA-SLAM method.

Accurate crater mapping in lunar permanently shadowed regions (PSRs) is hindered by extreme low-light and low-resolution imagery. We present YOLOLens2.0, a unified, end-to-end deep learning framework designed for high-fidelity crater detection and terrain reconstruction in these challenging environments. The architecture integrates a Dense-Residual-Connected Transformer

(DRCT) for multimodal super-resolution (SR) with a YOLO-derived detection module and an affine calibrator to ensure geometric consistency at meter scale. Our framework exploits a bidirectional synergy where SR enhances feature discriminability for detection, while detection-driven supervision refines structural reconstruction. Validation on Kaguya data demonstrates a significant performance leap, achieving a Recall of 89.20% and an mAP@50 of 0.844 an improvement of over 33 percentage points in recall compared to the original YOLOLens. Out-of-distribution validation on ShadowCam imagery, performed without fine-tuning, confirms the model’s robustness and scalability. The framework successfully preserves quantitative elevation fidelity and supports detailed morphometric analyses, including the extraction of the crater size-frequency distributions (SFDs) that align with theoretical lunar production functions. YOLOLens2.0 provides a scalable, high-precision methodology for planetary mapping, offering critical insights for lunar surface evolution studies and future exploration missions.

Reliable localization across the full orbit-descent-ground chain in planetary exploration remains difficult because extreme differences in altitude, viewing geometry, resolution, and illumination cause cross-view image matching to fail. Traditional keypoint pipelines and unified Structure-from-Motion (SfM) struggle to establish robust correspondences across these heterogeneous Satellite-Descent-Ground datasets due to severe domain gaps.

To overcome these limitations, we propose a novel framework based on a joint semantic-geometric optimization paradigm. Rather than forcing a unified SfM pipeline across drastically different viewpoints, our method leverages independent intra-domain SfM outputs and telemetry data as structural priors. We introduce a differentiable rendering approach that tightly couples the optimization of 3D Gaussian Splatting (3DGS) scene parameters with learnable camera extrinsics. Furthermore, by integrating high-level semantic epipolar constraints derived from foundation models, our method dynamically refines initial cross-domain pose estimates during the rasterization loop. This joint formulation effectively bypasses the fragility of low-level pixel matching, enabling accurate and robust alignment across the vast baselines inherent to multi-stage planetary exploration image sequences.

Mars topographic data are crucial for quantitatively characterizing the Martian surface, supporting exploration missions, and enabling scientific study of surface processes. Photogrammetric processing of Mars orbital imagery is the most representative method for generating 3D terrain models, with bundle adjustment (BA) serving as the key step for mitigating inconsistencies in overlapping regions of different orbital images and further improving the spatial accuracy of the resulting DTMs. However, due to the texture-less surface of Mars and the absence of ground control points, the stability of BA is often compromised. Impact craters, which are prevalent on the Marian surface, have been utilized as an important semantic prior in various image analysis applications. They can also be used to assist the BA process for precision topographic mapping of the Martian surface.

This study introduces a novel BA method assisted by robust crater graph features to address this. The approach involves: (1) extracting craters using a deep learning model (YOLOv5) and constructing a stable graph structure via a minimum spanning tree; (2) establishing crater correspondences across different images based on graph features to generate robust tie points; and (3) formulating a strengthened BA equation with constraints from the graph's angular and edge relationships to mitigate geometric inconsistencies.

Experimental results indicate that the proposed method provides an effective solution for high-precision 3D mapping from Martian surface imagery with limited textures and significant illumination variation. By incorporating crater graph features, it enhances the precision and stability of BA, yielding high-precision topographic mapping results for various applications.

Surface roughness influences image contrast by altering illumination, which depends on the surface slope. We conducted Monte Carlo simulations of rough surfaces under both directly illuminated and secondary-illuminated lunar conditions. Our results indicate that PSR secondary illumination yields significantly lower contrast, characterized by soft, diffuse shading and negligible shadow fraction.

With the acceleration of global urbanization, dynamic change detection of urban buildings is vital for urban planning, resource management, and public safety. Traditional bi-temporal remote sensing-based methods fail to capture gradual building evolution and are prone to noise-induced missed detections and false alarms. While multi-temporal imagery provides continuous temporal information, its sequential and high-dimensional nature poses greater challenges. Existing deep learning models like CNNs excel at spatial feature extraction but lack temporal modeling, while LSTM/ConvLSTM struggles with spatial detail preservation and small-target recognition.

To address issues including insufficient temporal modeling, channel redundancy, weakened spatial attention, and small-target loss, this study proposes the Dual Attention-coupled ConvLSTM Network (DAL-UNet). Its encoder embeds a dual attention module: channel attention selects change-related features and suppresses redundancy, while spatial attention enhances key region responses to improve building edge and small-target discrimination. A fully convolutional LSTM module models temporal evolution while preserving spatial topology. The decoder adopts a dual-branch multi-task framework to optimize change feature upsampling and semantic segmentation, enhancing subtle change perception and spatial detail restoration.

Experiments on the SpaceNet7 dataset show DAL-UNet outperforms state-of-the-art methods, with maximum improvements of 13.04% in F1-score, 1.32% in Precision, and 16.52% in Kappa coefficient. It performs exceptionally in high-rise shadow areas and dense small-target regions, reducing shadow interference via attention mechanisms and alleviating class imbalance through class-weighted loss.

In the aftermath of a disaster, whether natural, industrial, or war-related, a rapid and accurate assessment of building damage is crucial for rescue forces to conduct an effective emergency response. Very high-resolution satellite imagery enables such assessments and serves as an important indicator for understanding the scale of destruction, supporting time-critical rescue operations, and guiding resource allocation. While deep learning models have shown promising results in automating building damage assessment (BDA) from pre- and post-disaster optical satellite imagery, they often fail to generalize to new disasters due to domain shifts. This paper studies the challenge of rapid domain adaptation for BDA in the context of the war in Ukraine. We create a new, challenging dataset annotated with damage grades across six cities in Ukraine, using pre- and post-disaster optical imagery. To facilitate rapid adaptation, we propose an efficient fine-tuning workflow using Low-Rank Adaptation. Our experiments show that this approach substantially improves performance in both out-of-domain and in-domain settings, presenting a practical and data-efficient study for deploying BDA models in time-critical emergency scenarios.

This study examines district-level urban expansion and ecological change in the Hills Shire LGA using multitemporal Landsat imagery, Shannon’s entropy, RSEI, and hotspot analysis to identify spatial patterns of growth and environmental stress.

Urban sprawl, characterized by land discontinuity, low population density, and inefficient land use, hinders sustainable urbanization, particularly in rapidly growing regions such as Bulacan, Philippines. This phenomenon places strain on existing infrastructure, contributes to environmental degradation, and exacerbates socio-economic disparities. While previous studies have analyzed urban sprawl, these often neglect the integration of socio-economic factors, thereby reducing the accuracy of their analysis and policy relevance for developing regions. This research seeks to analyze urban sprawl patterns within Bulacan through the integration of socio-economic variables and identify key factors driving this sprawl. The study employs urban sprawl analysis, using the Multidimensional Urban Sprawl Index (USI) to assess land discontinuity, population density, and land use efficiency. Additional analysis using fractal analysis and factor analysis through Geodetector was also employed. The study found a positive shift toward more efficient, compact growth in Bulacan from 2005 to 2020, though mild and severe sprawl remain ongoing challenges. Fractal analysis revealed that complex urban forms encourage infill, while open areas are prone to leapfrog development. Land use benefit and road access consistently drove sprawl, with key factors like population and proximity to the city center changing over time. The study recommends stricter enforcement of zoning regulations to mitigate fragmented growth and the integration of additional socio-economic indicators (e.g., GDP, employment rates, and land values) into future analysis.

This study demonstrated that a two-stage architecture—comprising a segmentation model followed by a classification model—is effective for embankment extraction. By constructing a large, wide-area training corpus from medium-resolution SPOT imagery, transfer learning to higher-resolution satellites (e.g., Pleiades) was readily achieved. For operational use, exhaustively proposing candidates with the AI model and inserting a brief human check (embankment/non-embankment) per candidate can reduce false positives while limiting missed detections, making the approach sufficiently practical for deployment.

Land-sea segmentation is crucial for tasks such as marine target detection and coastline extraction in remote sensing imagery. However, complex and diverse background environments and land-sea boundaries can easily lead to inaccurate segmentation. To address this issue, a high-precision land-sea segmentation model based on the deep Otsu method is proposed. This method first utilizes our proposed remote sensing image texture enhancement algorithm based on Retinex theory and the Canny operator to enhance the remote sensing image and its edge information, further improving the segmentation accuracy of the land-sea boundary. Then, we combine deep learning concepts, the maximum inter-class variance method, and our proposed density space clustering method based on the difference innovation optimization algorithm to propose a deep maximum inter-class variance method for segmenting the ocean and land in the image. Simultaneously, an adaptive multi-scale fragmentation region removal method is proposed to remove small, fragmented regions extracted during the segmentation process. Experimental results show that the proposed method achieves an overall prediction accuracy of 98.41% and an average intersection-union ratio of 96.07%, demonstrating its ability to effectively perform land-sea segmentation tasks.

Low-resolution imagery is a major constraint for remote sensing tasks (e.g., urban land cover detection) where accurate classification of buildings, roads, vegetation, and small objects is required. Deep learning-based segmentation models are highly sensitive to image quality, resulting in degraded performance on low-resolution inputs. Super-Resolution (SR) techniques offer a promising solution by enhancing image fidelity to support downstream tasks. This work applied MAPSRNet, a Multi-Attention Pyramid SR Network to aerial images used for multi-class land cover detection. Evaluated on the ISPRS Potsdam dataset, MAPSRNet achieves state-of-the-art SR performance with PSNR of 32.92 dB and SSIM of 0.87, outperforming existing methods such as SRCNN (31.54 dB, 0.83) and DRRN (31.03 dB, 0.82) while maintaining competitive inference speed. Beyond image quality, MAPSRNet significantly improves multi-class land cover segmentation when integrated with a ConvNeXtV2-based U-Net, achieving an overall accuracy of 80.60%, mean IoU of 62.54%, and FwIoU of 68.34%, surpassing not only low-resolution inputs (Overall Accuracy: 65.28%, mIoU: 40.20%, FwIoU: 50.12%) but also high-resolution(HR) ones (Overall Accuracy: 80.50%, mIoU: 62.40%, FwIoU: 68.01%), especially in certain classes such as impervious surface and clutter. These results demonstrate that perceptual and structural fidelity, rather than pixel-level similarity, can drive superior performance in urban land cover segmentation. MAPSRNet offers a practical solution for scenarios where HR imagery is limited or unavailable, highlighting its potential for large-scale remote sensing applications.

The cryosphere responds to variations in the climate. Monitoring glaciers requires research into their dynamics. The surface velocity of the Gangotri glacier was obtained in this study using the Sentinel-1 dataset. Modifying the laminar flow model improved estimates of ice thickness. Moreover, the glacier mass balance has been calculated using changes in ice thickness between 2017 and 2022. An average velocity of 0.09 m/day was observed with stretches from 0.12 to 0.23 m/day in the central trunk. A mean thickness of 189 ± 17.01 m was determined for the glacial ice. The thickest areas, with the least drag, were measured to be 587 ± 52.83 m in the middle part. Negative mass rates of -1.3 to -0.5 m.w.e./year were observed for the glacier system (with thickness changes of -3 to -0.6 m/year) due to the glacier's decreased thickness throughout time.

The Himalayan region hosts the largest reservoir of snow and ice outside the polar regions. However, ongoing climate change has resulted in widespread glacier retreat, heightening the frequency and magnitude of extreme events, including flashfloods, landslides, and Glacier Lake Outburst Floods. The Beas Basin in the northwestern Himalaya exemplifies this vulnerability, where cryospheric transformations directly threaten downstream communities, hydropower systems, and infrastructure. Despite its critical importance, long-term basin-scale records remain limited. Therefore, this study investigates the long-term cryospheric evolution of the Beas Basin and identifies emerging glacial lakes using an integrated remote-sensing and modelling-approach. Glacier mass balance from 1951 to 2024 was estimated using an Improved Accumulation-Area-Ratio method, incorporating equilibrium-line-altitudes derived from ASTER-DEM and meteorological data, alongside glacier extents from Landsat and Sentinel imagery. Current glacier ice reserves were quantified using laminar-flow and volume–area scaling methods, with surface velocities derived from sub-pixel Landsat image correlation, and slope from DEMs. Future glacial lake formation was assessed using the HIGTHIM tool, which integrates ice thickness, bed topography, and moraines. Results indicate a mean area-weighted mass balance of –0.46±0.26m.w.e.a⁻¹, corresponding to 17.75Gt cumulative ice loss (~48% of glacier-stored mass) since 1951 and a current ice reserve of 19.60±3.5 Gt. Sixty-three potential glacial lake sites were identified, with four existing lakes projected to expand, totalling 122±22 million-m³of water. These findings reveal extensive cryospheric reorganisation, with significant implications for hydrology, water security, and hazard management. The study demonstrates the value of combining satellite observations with process-based modelling for monitoring Himalayan glacier dynamics in data-sparse regions.

The intrusion of relatively warm ocean waters beneath Antarctic ice shelves is a key driver of basal melting and strongly influences ice-shelf stability. However, previous studies investigating warm-water pathways have largely relied on single-source datasets, such as ship-based Conductivity–Temperature–Depth (CTD) measurements, which are spatially sparse and limited to a few well-surveyed regions. Recent advances in multi-source remote sensing datasets provide new opportunities to address these limitations. In this study, a multi-source remote sensing–based framework is developed to identify potential pathways of relatively warm water intrusion beneath Antarctic ice shelves and to quantify the associated basal melting. The Moscow University Ice Shelf (MUIS) is used as a case study. Across the continental shelf, CTD observations, sub-ice-shelf bathymetry, and modeled ocean circulation are integrated to infer potential intrusion routes. At the ice-shelf front and base, EN4 reanalysis data are used to characterize seawater properties, while satellite-derived basal melt products are applied to analyze spatial and vertical patterns of basal melting. Results indicate that relatively warm water is mainly concentrated at depths of 300–500 m, coinciding with bathymetric depressions that facilitate its intrusion beneath MUIS. Enhanced basal melting occurs near the ice front and grounding line, primarily within the upper 0–500 m of the ice-shelf draft, with an average melt rate of ~6 m yr⁻¹. The proposed framework provides a transferable approach for investigating ocean-driven melting beneath Antarctic ice shelves.

The Antarctic Ice Sheet (AIS), the largest terrestrial ice mass on Earth, contains approximately 90% of the planet's total ice volume. This study quantifies ice discharge and associated uncertainties in AIS estimates through Input-Output method, evaluating the impact of flux gate locations on discharge magnitude and measurement uncertainty. Through analysis of key factors contributing to discharge uncertainty, we propose a gate positioning strategy that optimizes the balance between proximity to the grounding line and uncertainty minimization.

NASA’s ICESat-2, a single-photon lidar satellite launched in 2018, has for six years delivered pole-wide elevation data with <0.4 cm/yr precision. To verify and exploit these data over Antarctica, we built a “space-air-ground” calibration chain. (1) A cross-track array of corner-cube retro-reflectors (CCRs) was installed at Kunlun, Taishan and Zhongshan stations; one deployment captures both ascending and descending passes, doubling efficiency. GNSS-PPP/RTK solutions overcome the absence of fixed reference points and position CCRs to within 1 cm; comparison with ICESat-2 tracks shows sub-4 cm vertical accuracy, confirming stable on-orbit performance. (2) UAV photogrammetry during the 36th CHINARE expedition produced 5 cm-resolution DEMs of crevassed ice margins at Zhongshan/Prydz Bay. Fused with RTK ground control, these reveal ICESat-2 planimetric offsets of 2–5 m and serve as “truth” for a new Photon-Cloud algorithm that corrects slope-induced positioning errors and extends the mission’s utility in rugged terrain. (3) Whole-continent cross-over analysis of repeat tracks shows millimetre-level consistency between ascending and descending orbits; an improved cross-track model extracts robust elevation-change time series for stable ice interiors. The integrated framework provides ICESat-2 Antarctic accuracy metrics, refined processing tools and a transferable protocol for future polar photon-counting altimetry missions.

Accurate mapping of exposed rock is fundamental for cryospheric and geospatial analyses in Antarctica, yet existing products are of limited resolution and tend to underestimate true rock exposure. We present a weakly supervised deep-learning framework that refines existing rock masks by combining Sentinel-2 multispectral imagery with elevation and slope data from the Reference Elevation Model of Antarctica (REMA). A U-Net with eight input channels (six spectral bands, elevation, slope) is trained using imperfect Landsat- and GeoMap based labels. Trained on data from the Antarctic Peninsula, the model produces a 10~m rock mask that delineates small and shaded outcrops more effectively than existing datasets. While quantitative evaluation is constrained by imperfect reference data, qualitative inspection indicates improved rock–snow separation. The workflow is fully automated, requires no manual annotation, and scales efficiently to all rock-hosting regions of the continent reachable by Sentinel-2 multispectral coverage. Beyond rock mapping, the framework is transferable to other scenarios with incomplete or uncertain reference data, such as vegetation, snow, or water mapping. The resulting rock mask for complete Antarctica, together with the trained model and preprocessing scripts, will be released to support reproducible large-scale mapping and future cryospheric research.

This paper presents an efficient approach to the accessibility assessment of tram transport based on a simulation within a digital twin environment. We propose a novel framework that integrates several advanced data acquisition and processing steps: mobile mapping of the tram routes, detection of rail tracks and tram stops, and the final assessment of tram accessibility by simulating the MAL deployment in the digital twin. Our experimental evaluation demonstrates that the digital twin provides a practical and reliable tool for assessing tram accessibility.

As-built Building Information Models (BIMs) are crucial for building digitalisation, structural analysis, and life cycle management. Despite recent advances, automated reconstruction of structural elements from point clouds remains a challenging task, particularly in ensuring geometric accuracy and topological consistency within a storey and across consecutive storeys. This paper proposes an automated method for refining topological inconsistency between columns, beams, and slabs, ensuring consistent as-built BIMs. The method places Constructive Solid Geometry (CSG) at the core of the refinement process, driven by fundamental structural principles. The method starts by creating solid rectangular prisms from labelled point clouds. Beams are then aligned both vertically and horizontally within each storey. Columns are vertically aligned across consecutive storeys. Topology relationships between the elements are retrieved and encoded in graphs. These graphs, together with a set of Boolean operations, are used to resolve gaps and trim overlaps between the connected elements. The refined elements are represented in accordance with the IFC standards. The proposed method was validated on two multi-storey case studies representing frame and flat-slab building structures. Both qualitative and quantitative evaluations confirmed the effectiveness of the approach, achieving significant geometric accuracy and topological consistency. In addition, the method exhibits efficient runtime performance, indicating its promise for scalable Scan-to-BIM automation.

Bridge infrastructure plays a critical role in transportation networks, requiring reliable and efficient methods to detect missing bolts to ensure structural integrity and prevent failures. This study proposed a novel methodology integrating point cloud-based Digital Twins (DTs) with Topological Data Analysis (TDA), specifically using Persistent Homology (PH), for robust and accurate missing bolt detection. The framework combines 3D photogrammetric reconstruction to generate point cloud-based DTs, Convolutional Neural Networks (CNNs) for precise bolt localization, and PH to identify and quantify missing bolts. Through parameter evaluations and a real-world bridge case study, the proposed approach demonstrated high detection accuracy, effectively identifying missing bolts with a false positive rate below 10%. These findings confirm the reliability and effectiveness of integrating DTs with TDA as an advanced data-driven approach for automated structural inspection and bridge health monitoring.

Semantic segmentation of indoor point clouds is a fundamental task in 3D scene understanding, supporting applications such as virtual reality, indoor navigation, and building management. Point-based transformer models achieve high accuracy but require substantial computational resources, while superpoint-based methods are more efficient yet often less precise. To address this trade-off, we propose LGFormer, a lightweight framework that integrates Graph Convolutional Networks (GCN) and transformers to jointly capture local and global contextual features. The method constructs a superpoint-based topology graph, where local features are extracted using GCN and global dependencies are modeled through transformer layers. Experiments on the S3DIS and ScanNet++ datasets demonstrate that LGFormer achieves 90.7% and 88.5% segmentation accuracy, respectively, while reducing inference time by more than 99% compared with point-based transformers. By effectively leveraging superpoints and local-global feature fusion, LGFormer dlivers competitive accuracy with significantly lower computational cost, making it suitable for large-scale indoor scene analysis.

Corroding reinforcement leads to cross section loss and reduced structural capacity of concrete bridges. Detecting exposed rebars

(ER) is crucial during bridge inspection to plan countermeasures early and prevent further corrosion. With advancements in deep

learning, several public datasets derived from inspection imagery have been released to identify ER and other concrete damage

automatically. At the same time, Uncrewed Aerial Systems (UAS) have become more capable of navigating even underneath the

bridge deck. This combination holds promise to improve efficiency of bridge inspection methods, but obtained imagery differs

from available datasets, featuring very small damages and complex backgrounds. To address this mismatch, this work reviews

publicly available ER datasets, presents a UAS-based bridge inspection dataset for evaluating ER damage (UBID-ER-val), and

quantifies similarities and differences between them. We train several YOLOv8 models on conventional inspection documentation

images and benchmark the reviewed datasets, scoring F2 = 0.229 at S2DS, F2 = 0.430 at CODEBRIM, F2 = 0.584 at Dacl10k,

compared to F2 = 0.505 at UBID-ER-val. We analyse factors influencing performance and find that tiled inference raises Recall

(+0.166) but drastically reduces Precision (−0.309), while matching training and validation image resolution underperforms across

all datasets (−0.061 to −0.129). The differences in best-performing combinations underscore the underlying domain shift that

complicates practical deployment. As a practical outcome of this work, UBID-ER-val is made publicly available to enable objective

benchmarking of ER detection models and to assess their reliability under field conditions.

Detecting visible electrical utilities is a prerequisite for developing advanced reasoning strategies to reconstruct hidden in-wall networks. This paper investigates the detection of visible power-related utilities using a domain-adaptive deep learning-based vision pipeline based on the YOLOv11-L, object detection model. Four publicly available datasets containing power sockets, power strips, and light switches were curated, relabeled, and merged into a unified training dataset of 3,459 images. The resulting model achieved a mean average precision (mAP) of 0.74 for power sockets and strips and 0.98 for light switches, demonstrating strong detection performance. Real-time evaluation on a low-cost smartphone via the Ultralytics HUB App indicates reliable detection in small-scale real-world environments and detected utilities could be integrated automatically into semantic indoor models using a marker-less referencing approach. The work further highlights broader applications, including Augmented Reality-based visualization to reduce cognitive load for project managers and inspectors or construction workers and electricians, and its potential use as input for existing and future reasoning methods for hidden-utility reconstruction. The prepared dataset, trained model and source code is available at: https://github.com/hcu-cml/indoor-electrical-facility-detection

Accurate large-scale forest canopy height mapping is critical for biomass estimation and carbon monitoring, yet remains constrained by the limitations of individual remote sensing systems. This study presents a multisensor machine learning framework that integrates GEDI LiDAR with Sentinel-2, Sentinel-1, ALOS-2 PALSAR-2, and 3DEP terrain data to generate a 25 m resolution canopy height model (CHM) for the Northeastern United States in 2022. A key contribution is an adaptive GEDI relative height (RHad) strategy that selects optimal RH metrics based on canopy density, improving generalization across heterogeneous forest conditions compared to any single fixed RH metric. Independent validation against airborne LiDAR and USDA FIA plot data confirms that RHad achieves the highest accuracy and lowest bias of all configurations tested. The resulting regional canopy height map provides a reliable baseline for large-scale forest monitoring and future multitemporal analyses.

Timely and accurate detection of deforestation is essential for managing tropical forests, yet individual Earth observation sensors have inherent limitations. Multispectral imagery offers detailed spectral information on vegetation properties but is frequently hindered by cloud cover, while Synthetic Aperture Radar (SAR) imagery provides insights on vegetation structure independent of weather conditions but is sensitive to moisture variability and residual vegetation post-clearing. The complementary nature of these data has motivated multi-source fusion approaches, though most existing methods rely on offline processing or decision-level integration, limiting their real-time applicability.

This study generalizes a Bayesian Online Changepoint Detection (BOCD) framework based on the recursive estimation of the number of acquisitions since the last change to asynchronous, irregularly sampled Sentinel-1 SAR and Sentinel-2 multispectral time series. A dynamically weighted fusion mechanism is implemented, in which each sensor’s relevance reduces with increasing time since its last observation, according to a physical decay model. The resulting method, named ms-BOCD, enables interpretable, and Near Real-Time (NRT) detection of forest loss.

The ms-BOCD method is validated using MapBiomas Alerta reference data spanning deforestation polygons ranging from 0.1 to 50 hectares in the Brazilian Amazon.

Compared to $VH$-BOCD (BOCD using Sentinel-1 cross-polarization only) and the operational RADD and TropiSCO systems, ms-BOCD achieves a 25% improvement in detection performance and maintains 13% fewer false alarms than Global Forest Watch (GFW), a platform that aggregates multiple independent deforestation alert products. Overall, these results demonstrate the strong potential of multi-source Bayesian fusion for operational tropical forest monitoring.

This study assesses long-term forest change in Liberia’s Community Forest Management Areas for Conservation (CFMACs) and Protected Areas (PAs) from 2002 to 2024 using an integrated Landsat–Google Earth Engine (GEE) and an ArcGIS Pro workflow. Annual dry-season composites for three time periods were classified using a Random Forest model with 81.7% accuracy (Kappa = 0.781). Results show contrasting governance outcomes: CFMACs experienced modest forest gains from 2002–2014 and localized losses thereafter, while PAs exhibited larger overall gains but also greater cumulative forest loss, particularly along concession boundaries. Stability analysis revealed that PAs retained a higher proportion of Mature Forest over the 20-year period, whereas CFMACs showed more dynamic turnover and localized regrowth. The combined GEE/ArcGIS approach provides a scalable, transparent monitoring framework and demonstrates how governance type influences forest persistence, degradation, and recovery across Liberia’s tropical landscapes.

Accurate assessment of tree cover change is essential for monitoring deforestation, carbon emissions, and restoration progress. However, validation of global forest change products remains limited by the scarcity of consistent reference data. We present a benchmark dataset for tree canopy cover change evaluation across North America, derived from multitemporal airborne LiDAR data from the National Ecological Observatory Network (NEON). Using canopy cover maps from 2016–2022, we identified tree cover loss as a decrease of at least 20% in canopy cover persisting across multiple time steps. Thirty NEON sites spanning diverse biomes were included, forming a spatially and temporally robust reference for change detection.

We demonstrate the benchmark applicability by evaluating two global products: Forest Carbon Diligence (FCD) from Planet Labs, and the Global Forest Change (GFC) from University of Maryland. Across all sites, both products showed strong agreement with the LiDAR benchmark (r = 0.90 for FCD; r = 0.88 for GFC), though both underestimated change extent. Categorical metrics revealed higher precision than recall, indicating conservative detection thresholds relative to the benchmark.

This study establishes the NEON LiDAR-based benchmark as a valuable open resource for assessing and improving large-scale canopy cover change datasets. The approach highlights the importance of high-resolution, temporally consistent reference data for evaluating the accuracy of global monitoring products and guiding improvements in forest carbon accounting and conservation applications.

Under climate and human pressures, vegetation in Inner Mongolia exhibits complex fragmentation and degradation. Scientifically inverting its spatiotemporal dynamics is crucial for regional ecological restoration. To address the challenges faced by traditional cellular automata (CA) models in large-scale complex ecological transition zones—such as computing power bottlenecks and subjective transition rules—this study proposes a cloud-based vegetation degradation simulation and inversion framework (CA-VDS) via Google Earth Engine. By coupling Random Forest (RF) and an Improved Genetic Algorithm (IGA) with CA, the framework extracts nonlinear driving potentials and automates the optimization of bidirectional transition thresholds. Validation against the 2020 baseline shows CA-VDS effectively resolves manual parameter tuning limitations. Furthermore, it smooths the spectral fluctuations caused by short-term sporadic disturbances through the underlying spatial neighborhood mechanism, demonstrating its value in simulating potential ecological degradation risks and developmental trajectories. This work not only verifies the reliability of CA-VDS in analyzing complex nonlinear ecological processes, but also establishes a reliable parameter baseline and model paradigm for subsequent integration with CMIP6 and other multi-scenario data to conduct long-term future ecological predictions.

This study explores the application of Particle Swarm Optimization (PSO) to enhance vegetation indices (VIs) for the assessment of woody vegetation in a semi-arid savannah ecosystem. By optimizing VIs, the research aims to improve the discrimination between vegetated and non-vegetated areas, facilitating a more accurate random forest classification for habitat quality assessment. The optimization process preserves minimum VI values across different sensors to maintain lower bounds of reflectance, ensuring ecologically valid signals are represented, particularly in low-vegetated areas. Results indicate that maximum VI values increase post-optimization, enhancing sensitivity to canopy vigor, stress, health, and presence. The study highlights the effectiveness of UAV-derived indices, such as NDVI, NDRE, and SAVI, in capturing the dynamics of vegetation health and dryness, thereby contributing valuable insights into remote sensing methodologies for ecological monitoring.

The paper proposes the STF-Net (Spatial-Textural-Frequency Network) framework, designed to achieve a paradigm shift from traditional "change detection" to "suspected area identification," precisely identifying suspected abandonment areas and effectively suppressing pseudo-changes. The core of this framework lies in its fine-grained four-level annotation system and a three-stream parallel feature extraction architecture. The four-level annotation system includes "confirmed abandonment," "suspected abandonment," "non-abandonment change," and "no change," providing a robust data foundation for the model to learn the "suspected" concept, thereby compensating for the lack of "user-oriented" definitions in existing research. The three-stream parallel feature extraction architecture captures changes in geometric information (location, shape) via the spatial stream; quantifies the transition of surface texture from ordered to disordered, capturing structural degradation due to abandonment, through the textural stream; and analyzes periodic structural information in images, identifying the disappearance of periodic structures caused by cessation of cultivation, using the frequency stream. These three types of features are deeply fused, comprehensively utilizing information from different modalities, significantly enhancing the model's adaptability and identification accuracy in complex scenarios.

Methane (CH4) is a major greenhouse gas; however, large-scale monitoring remains challenging due to the high costs and spatial limitations of ground-based and airborne observations. In contrast, Sentinel-2 shortwave infrared (SWIR)–based plume detection is hindered by its coarse spectral resolution, surface artifacts, and limited real-world annotations. This study proposes a self-supervised learning (SSL) framework based on the Simple Framework for Contrastive Learning of Visual Representations (SimCLR) to learn transferable CH4 plume representations from unlabeled Sentinel-2 data. A real-world dataset of 456 Sentinel-2 image tiles was manually annotated using the multi-band–multi-pass (MBMP) approach and utilized to evaluate six encoder backbones. Across five labeled-data portions ranging from 20% to 100%, SimCLR pretraining improved plume segmentation compared to ImageNet-only initialization. In the full-data scenario, MobileNet achieved an F1-score of 0.90 with an Intersection over Union (IoU) of 0.80, while Shifted Window Transformer (SwinT) reached an F1-score of 0.85 with an IoU of 0.75. The benefit of self-supervised pretraining was most evident with limited labeled data, where ImageNet-only models degraded substantially, while SimCLR-pretrained encoders achieved higher accuracy. Moreover, the Integrated Mass Enhancement (IME) method was employed for quantifying the emission flux rate. MobileNet provided the strongest agreement with reference emission estimates, achieving an RMSE of 1690 kg/h. Finally, the results demonstrate that SimCLR-based SSL substantially enhances CH4 plume detection from Sentinel-2 imagery and supports more reliable emission quantification for large-scale CH4 monitoring.

Column-averaged methane (XCH4) data spanning 2018-2023 from the European Space Agency (ESA) Tropospheric Monitoring Instrument (TROPOMI) on the Copernicus Sentinel-5 Precursor satellite are assessed for evidence of methane (CH4) emissions from permafrost. We generated bi-monthly anomaly maps of XCH4 from TROPOMI and soil temperature (Tsoil) from reanalysis data for all land north of 50°N. Considering the XCH4 anomalies in the contexts of soil carbon content and wind variability led to a focus on Canada’s Hudson Bay Lowlands (HBL), Earth’s second largest peatland complex (~325,000 km2), which is underlain by continuous to isolated permafrost. This sub-Arctic region is vulnerable to rapid climatic warming and exhibits wind conditions favorable for emission detection from space. HBL XCH4 anomalies strongly correlate with soil temperature anomalies (R = 0.626 to 0.866), consistent with wetlands as the primary CH4 emission source; however, the strong increase in CH4 emissions over 2018-2023 may also suggest a contribution from permafrost thaw and expansion of thermokarst fens.

This study leverages TROPOMI satellite observations and atmospheric inversion modelling to quantify methane emissions from urban wetlands across six major North American cities, including Toronto, Montreal, New York, Los Angeles, Houston, and Mexico City. By coupling high-resolution column-averaged methane measurements with the GEOS-Chem chemical transport model via the Integrated Methane Inversion (IMI) platform, the research distinguishes emissions from both natural wetland and anthropogenic urban sectors. Results indicate that prior inventories substantially underestimate urban wetland methane emissions in most cities. Posterior wetland emissions are resolved alongside dominant anthropogenic sources such as landfills, energy systems, and wastewater, revealing spatially distinct patterns and highlighting seasonal wetland flux variability. The findings demonstrate that urban wetlands, although representing a relatively smaller source compared to anthropogenic emissions, display considerable underrepresented contributions to local methane budgets, underscoring the need for robust, integrated monitoring in urban environments. This methodology provides a scalable framework for routine urban wetland methane flux quantification and supports evidence-based climate mitigation and land management strategies.

Methane plume detection from medium-resolution multispectral satellites such as Sentinel-2 remains challenging due to weak methane signals and strong background variability across land cover, illumination conditions, and atmospheric states. To advance automated detection capabilities, we develop a large-scale benchmark dataset that combines simulated methane plume enhancements with real Sentinel-2 imagery, covering a wide range of emission magnitudes and diverse environmental scenarios. The dataset includes over 64,000 samples and incorporates methane-sensitive inputs derived from the MBMP retrieval workflow, providing a comprehensive foundation for robust model training and evaluation. Building on this dataset, a hybrid transformer–U-Net architecture is proposed, integrating global self-attention with Grouped Attention Gates to enhance feature fusion and improve segmentation of methane structures. The model achieves high accuracy on the benchmark dataset and demonstrates strong generalization to real emission events in complex environments. The combined contributions of the benchmark dataset and hybrid model offer a promising path toward reliable, scalable methane plume monitoring using widely available multispectral satellite observations.

Methane (CH₄) is a potent short-lived climate pollutant, making the detection of major point sources (“super-emitters”) crucial for mitigation. The Sentinel-5 Precursor (S5P) mission, with the TROPOMI instrument, captures global methane concentrations at ~7 × 5.5 km resolution with near-daily coverage. While this resolution is too coarse to identify emissions from individual facilities, its revisit frequency allows effective regional monitoring. Conversely, high-resolution (HR) imaging spectrometers like Carbon Mapper’s Tanager (~30 m) and NASA’s EMIT (~60 m) provide detailed plume mapping but have limited spatial and temporal coverage.

Carbon Mapper releases open-access, high-resolution plume products including georeferenced rasters and metadata. In this study, these HR detections serve as reference events to assess their visibility in coarser Sentinel-5P observations. The workflow includes curating HR events, summarizing their emission context, and inspecting nearby Sentinel-5P data for consistent methane enhancements. The method is exploratory and avoids presupposing Sentinel-5P’s success or failure in detecting plumes at this scale.

This analysis bridges the gap between frequent global monitoring and targeted HR observations. It establishes a path for future cross-sensor integration, combining HR spatial precision with Sentinel-5P’s temporal continuity. With additional labeled data, this approach could inform machine-learning tools for methane anomaly detection and plume segmentation, improving operational methane monitoring across scales.

This study proposes a deep learning–based enhancement of feature tracking to improve Sea Ice Drift (SID) estimation using Sentinel-1 Synthetic Aperture Radar (SAR) imagery. Traditional computer vision methods, such as Oriented FAST and Rotated BRIEF (ORB), are commonly used for generating initial drift vectors within the Nansen Environmental and Remote Sensing Center (NERSC) workflow; however, their performance declines under rotational variations, low-texture surfaces, and the fluid-like, short-term dynamics of sea ice. To address these limitations, this study evaluates two deep learning–based methods—SuperGlue and the Local Feature Transformer (LoFTR)—to enhance the robustness and accuracy of feature matching between consecutive SAR scenes. Furthermore, to effectively utilize multi-polarization information, a multi-polarization strategy was applied across both the feature tracking and pattern matching stages. Performance was evaluated using in-situ drift observations from Ice-Tethered Profiler (ITP) buoys, with feature matching assessed by the number of matched keypoints and estimated SID vectors, and drift accuracy evaluated using RMSE and the coefficient of determination (R²). Experimental results demonstrate that polarization integration significantly improves performance, reducing RMSE and increasing R². Among the methods, LoFTR achieved the best performance, followed by SuperGlue and ORB, with notable reductions in speed and directional errors. Overall, the findings demonstrate that deep learning–based methods substantially improve the stability and accuracy of SAR-derived SID estimation. These methods enable more stable and reliable performance in the Arctic environment, which is characterized by sea ice reduction, strong seasonal variability, and highly dynamic drift patterns.

global sea ice distributions on a daily basis. Ice concentration (IC) is one of the most important sea ice parameters derived from brightness temperatures measured by the microwave radiometers. However, even at microwave frequencies, the brightness

temperature data over open ocean areas are affected by the presence of adverse weather conditions, including elevated atmospheric water vapor, cloud liquid water, and abnormal surface roughness conditions. The net result is the retrieval of moderate sea ice concentration values in the open ocean where sea ice is not expected. The current sea ice algorithms make use of what is called a “weather filter” to correct such false retrieval of sea ice, but significant areas in the ice-free water that have the false ice cover remain in some areas. In this study, an improved weather filter, namely the Advanced Weather Filter (AWF), that minimizes, if not eliminates, this problem, developed by Cho et al. (2023), was implemented to produce JAXA/AMSR2 sea ice concentration products

of the Arctic for verification. The AWF was validated and shown to be very effective in selected study regions in the Arctic during the summer time from 30 June to 3 July 2014 and the winter time from 15 December to 18 December 2014, thereby supporting the

integration of the AWF into the standard AMSR2 sea ice concentration product. The AWF should be broadly applicable and can be implemented in other satellite passive microwave ice concentration datasets.

Seasonal soil freeze-thaw (FT) transitions govern critical hydrological and biogeochemical processes across northern landscapes. The physical state of freezing soil exists on a thermodynamic continuum influenced by the zero-curtain effect, a period where latent heat exchange stabilizes temperatures near 0°C. Despite this, operational passive microwave algorithms, such as FT-SMAP and FT-ESDR, enforce discrete binary classifications that mask this biogeochemically active partially frozen period. To address this limitation, this study establishes a probabilistic, non-binary FT detection framework using a parsimonious L1-regularized logistic regression model driven by multi-frequency passive microwave observations. To isolate dynamic phase changes from static landscape noise, the model integrates two locally standardized indices: the Normalized Polarization Ratio (NPR) from SMAP L-band to track soil liquid water permittivity, and the Normalized Difference V-Pol (NDV) from AMSR2 Ka/Ku-bands to capture volume scattering within canopies and snowpack. The model was trained using topsoil temperatures from North American networks, employing a probabilistic Soil Freezing Characteristic Curve to isolate high-confidence training end-members and a density-based spatial clustering approach to prevent spatial data leakage. The logistic framework demonstrated robust geographic generalizability, achieving an F1-score of 0.957 in Tundra environments. Crucially, it significantly mitigated false alarms in complex forested canopies, suppressing false positive rates in Mixed Forests to 12.6%, compared to 44.3% for FT-ESDR and 33.5% for FT-SMAP. By mathematically isolating the zero-curtain transition, this scalable approach provides the continuous baseline data necessary for advancing seasonal carbon respiration modeling in rapidly warming northern environments.

This work presents instrument development and calibration of a terrestrial L-band radiometer designed to support satellite retrieval validation and radiation transfer model parameter refinement in the Arctic. As satellite-based retrievals of key geophysical variables such as snow density and ground temperature continue to improve, their accuracy remains limited by scarce ground-truth data. Our refined radiometer addresses this gap by providing targeted, high-resolution terrestrial measurements capable of characterizing surface heterogeneity across Arctic land and water environments.

The instrument was redesigned from an existing model, and was improved based on lessons from earlier field campaigns, focusing on robustness, simplified operation, and enhanced radio-frequency isolation. Calibration procedure focused on measuring the night sky over several nights in cold temperatures to accurately characterize the operation in very cold conditions.

Initial calibration experiments show stable performance and improved consistency compared to earlier instrument versions. While some challenges remain, the system is expected to be field ready and able to capture brightness temperatures accurately over long time periods and varying conditions.

Future campaigns will extend these measurements to lake and sea ice, supported by ground-penetrating radar enabled surface roughness characterization. These efforts will ultimately contribute to improved radiative transfer modeling and more accurate satellite retrievals of key Arctic geophysical variables.

Accurate mapping of retrogressive thaw slumps (RTSs) in permafrost regions remains challenging due to their irregular morphology, blurred boundaries, and strong spatial correlation. This paper proposes a lightweight multi-level self-modulation (MLSM) module embedded into the UNet++ backbone to enhance non-local feature modeling for high-resolution image segmentation. The overall framework is built upon a UNet++ backbone with dense skip connections, where the proposed MLSM module adaptively fuses multi-scale contextual information to enhance feature coherence across spatially correlated regions. By incorporating low-rank regularization through a soft nuclear norm, MLSM dynamically modulates feature responses according to structural variations, allowing attention to adapt to spatially complex RTS regions. The integration of depth-wise convolution and channel recalibration further refines feature aggregation efficiency. Experimental evaluations on Maxar dataset demonstrate that the proposed method achieves superior segmentation accuracy and smoother boundary delineation compared with existing models. The proposed framework provides a robust and computationally efficient approach for RTS mapping, contributing to improved understanding of local geomorphic patterns.

This study investigates long-term snow persistence dynamics across the North-Western Himalaya (NWH) spanning 2000–2024 using MODIS Terra and Aqua daily snow products. Snow persistence—defined as the number of days a location remains snow-covered—is a crucial indicator of climatic variability and hydrological behaviour in high-mountain environments. Annual snow persistence was derived from daily CGF_NDSI_Snow_Cover layers after mosaicking, clipping to the study region, reclassifying snow pixels, and summing snow days at 500 m resolution. Pixel-wise trend analysis was conducted using the Mann–Kendall test, supported by Kendall’s Tau, p-values, and variability metrics.

The results show clear spatial contrasts: high-elevation zones (>4000 m) maintain persistent snow cover (>300 days/year), while mid-altitude regions (1500–3000 m) exhibit moderate persistence but significant negative trends. Low-elevation areas display minimal snow longevity and rapid decline over the 25-year period. The region recorded maximum snow-covered area in 2019 and a notably reduced extent in 2016. Approximately 29% of the NWH shows statistically significant trends, predominantly negative, with an overall mean decline of −3.2 snow days per year. Variability is highest in mid-elevation transition zones, which appear particularly sensitive to warming.These findings highlight ongoing reductions in seasonal snow cover in the NWH and their implications for glacier mass balance, water resource availability, and hydrological timing. The study underscores the value of long-term satellite-based monitoring to understand cryospheric response under changing climate conditions.

This study takes into account the heterogeneity of regional development stages and the local development context, systematically explores the relationship between localization and sustainable development, and constructs a quantifiable localized SDGs assessment model for China. An empirical analysis of the multi-level SDGs evaluation system was conducted. To address the challenges posed by heterogeneous multi-source data in the assessment process, a composite Key Performance Indicator (KPI) screening model based on Random Forest and Hyperlink-Induced Topic Search (HITS) was proposed, enhancing the scientific rigor and efficiency of localized SDGs monitoring and evaluation.

This paper is mainly based on the experience of Jiaxing City, which has done a good job in the investigation and monitoring work in China, to inspire the investigation and monitoring work in Beijing, and to provide technical support for supporting the investigation and monitoring work in Beijing to achieve the goal of "one inspection, multi-purpose, integration and sharing". Through research, the four databases of new basic surveying and mapping, land change survey, urban land space monitoring, and land space planning are integrated, and the integration of content indicators, survey methods, collection and storage, management and sharing is realized.

Accurate extraction of water bodies from remote sensing imagery is essential for environmental monitoring, water resource management, and hydrological applications. However, the performance of deep learning models for water segmentation depends on the availability of representative datasets that capture diverse environmental and spectral conditions, particularly in tropical and semi-arid regions that remain underrepresented in existing datasets. This study presents the Pernambuco Waterbody Dataset (PWD), a multi-source dataset comprising aerial and satellite remote sensing imagery for water-body segmentation. The dataset covers the state of Pernambuco, Brazil, including tropical and semi-arid environments associated with the Atlantic Forest and Caatinga biomes. The dataset includes high-resolution aerial imagery (0.5 m) from the Pernambuco Tridimensional Program (PE3D) and Sentinel-2A imagery (10 m), with manually annotated water bodies generated by cartographic specialists. The dataset was constructed through data acquisition, preprocessing, manual annotation, mask generation, patch extraction (512 × 512 pixels), and division into training, validation, and test subsets. The first version includes 51,743 aerial patches and 15,321 Sentinel-2A patches. To validate the dataset, U-Net, U-Net++, and DeepLabV3+ architectures with ResNet and EfficientNet backbones were evaluated using Recall, Precision, F1-score, and IoU metrics. The best performance was achieved by U-Net++ (ResNet34) for aerial imagery (IoU 0.946) and U-Net (ResNet34) for Sentinel-2A imagery (IoU 0.871). Overall, the proposed dataset provides a robust benchmark for advancing deep learning-based water body extraction using multi-source remote sensing data.

Multispectral satellite imagery provides an essential source of information for monitoring environmental transformations, yet robust unsupervised change detection remains challenging due to radiometric variability and seasonal dynamics. At the same time, supervised approaches based on Deep Learning are often constrained by the need for computationally expensive accelerated hardware and the limited availability of high-quality annotated datasets. This work introduces a framework based on the Bitemporal Spatial Autocorrelation (BSAC) matrix, that rather than relying on pixel-wise spectral differencing or data-intensive Deep Learning models, it is designed to quantify structural changes by evaluating the symmetry properties of the spatial autocorrelation across multiple spatial lags. Three complementary metrics are derived from the BSAC representation: a binary change/no-change trigger that identifies structural discontinuities, an asymmetry magnitude that measures the intensity of change, and a normalized Symmetry Index obtained via singular value decomposition to characterize the geometric coherence of the correlation structure.

The methodology is applied to Sentinel-2 imagery of Lake Fanaco (Sicily, Italy), which experienced severe desiccation during the 2024 drought. Experiments conducted using NDWI and NDVI confirm the index-agnostic nature of the framework, capturing both

hydrological contraction and vegetation stress. Comparison with an unsupervised K-means segmentation baseline shows strong spatial agreement in identifying the affected areas. Thanks to its unsupervised formulation and near-linear computational complexity, the BSAC framework represents a scalable and interpretable approach for operational change monitoring in Earth observation.

Accurate and rapid burned-area mapping is essential for assessing the ecological impacts of forest fires and supporting post-fire recovery efforts. Traditional pixel-based methods often suffer from limited accuracy due to spectral confusion, topographic effects, and reliance on empirical thresholds. Although deep learning models such as U-Net, DeepLab, and SegFormer improve spatial precision, their operational scalability is constrained by the need for extensive labeled data and regional retraining.

This study introduces a zero-shot burned area mapping approach using the Segment Anything Model (SAM) with Sentinel-2 imagery. SAM, trained on over a billion masks, enables prompt-based segmentation without task-specific training. Composite inputs derived from NBR, NBR2, and NDVI indices were generated and fed into SAM, followed by testing multiple pre-processing, post-processing, and hyperparameter configurations.

Results show that multi-scale settings (crop_n_layers = 2) significantly enhance boundary continuity and geometric accuracy. The method achieved IoU values of 0.89 (Bursa) and 0.87 (Çanakkale), with corresponding F1 scores of 0.94 and 0.92 performances comparable to, and in some cases exceeding, supervised models. Integrating spectral index composites further reduced boundary fragmentation and improved discrimination between burned and unburned surfaces.

Overall, the proposed framework eliminates dependence on manual labeling, offering a fast, scalable, and cost-effective solution adaptable to diverse ecosystems and sensor conditions. The study demonstrates one of the first systematic applications of SAM for burned-area detection, highlighting its strong potential for zero-shot environmental monitoring and rapid post-fire assessment.

In many regions of the world, especially those affected by armed conflicts, urbanization, or intensive environmental transformations, a high dynamic of land cover and land use changes is observed. Reliable monitoring of these processes requires the application of classification methods that ensure both high thematic accuracy and temporal consistency. This paper presents a multitemporal classification methodology based on Sentinel-2 optical data and machine learning models.

The research was conducted for the city of Sievierodonetsk (Luhansk Oblast, Ukraine) – an area that suffered significant destruction in 2022 as a result of military operations. The aim of the analysis was to identify land use changes in the years 2021-2025 using three classifiers: k-Nearest Neighbors (kNN), Random Forest (RF), and Gradient Boosting Classifier (GBC), combined into an ensemble system based on dynamic confidence weighting.

Quality assessment using the recall metric showed that the fusion method outperformed individual classifiers, achieving average values of 0.87-0.96, while classical models obtained 0.81-0.89. The largest changes (39%) occurred in the years 2022-2023, coinciding with the period of greatest military activity. The proposed method achieved the highest classification quality indices (F1 = 0.93, Acc = 0.98 for 2021), surpassing global products and models based on AlphaEarth. In subsequent years, high stability was maintained (F1 ≥ 0.88), confirming the effectiveness and robustness of the approach under various environmental conditions

This study examines the landscape dynamics in the region surrounding Comandante Ferraz Antarctic Station, Keller Peninsula, King George Island, focusing on the quantification of land cover changes over 23 years. Emphasis is placed on the integration of a multitemporal Landsat time series (2001–2024) within a standardized spatio-temporal data cube framework, coupled with a Random Forest (RF) classification approach. This methodology enables consistent pixel-wise trajectory analysis across seven distinct epochs. The RF models achieved robust performance, with F1-scores for dominant classes like water and soil typically exceeding 0.90, although seasonal snow and ice showed greater spectral ambiguity in transitional months. Quantitative results from the transition matrices reveal a significant landscape reconfiguration: while ice (85.3%) and soil (81.2%) showed high persistence, a prominent trend of deglaciation was identified, characterized by the transition of ice and snow into exposed soil and the emergence of pioneer vegetation communities detected from 2014 onwards. The study demonstrates that the integration of machine learning and data cubes provides a powerful tool for monitoring environmental shifts in high-latitude maritime Antarctica, supporting long-term ecological assessments and climate impact modeling.

This study introduces a Spatial constraint One-step Approach (SOA) and Temporal constraint One-step Approach (TOA) to improve the estimation of Terrestrial Water Storage Anomalies (TWSA) from GRACE and GRACE-FO satellite data. Traditional three-step or two-step post-processing methods sequentially apply spectral filtering and leakage correction, often causing signal attenuation, spatial leakage, and reliance on external models.

In contrast, the proposed one-step framework simultaneously estimates all signal components—including trends, seasonal cycles, and non-seasonal signals (NSS)—directly from unfiltered TWSAs within a region of interest. It incorporates full error covariance and models NSS using spatiotemporal constraints: TOA employs a Multi-Order Gauss-Markov process for temporal correlation, while SOA uses spatial covariance functions and a buffer zone to reduce boundary effects. Tikhonov regularization ensures solution stability.

Validation across major river basins and regions like Southeastern China shows that SOA/TOA outperforms conventional filters (e.g., DDK, IPF), reducing errors and improving agreement with mascon products and climate indices. The method also better identifies hydrological extremes (e.g., droughts, floods) and links them to climate drivers like ENSO, enhancing the monitoring and understanding of global water storage dynamics.

Groundwater dependent ecosystems (GDEs) are sustained by direct or indirect access to groundwater, relying on its flow or chemistry for their water needs. These ecosystems span aquatic, terrestrial, and subterranean realms, providing critical ecological functions, maintaining water quality, and supporting biodiversity and Indigenous land use. In Alberta’s boreal region, GDEs are abundant yet remain poorly mapped, limiting understanding of their extent and sensitivity to industrial development and hydrological change. Developing consistent, spatially explicit mapping tools is therefore essential for effective monitoring and management. This research develops and evaluates a remote sensing and machine learning (ML) framework for predicting GDE habitats across boreal Alberta, Canada, as part of a broader provincial effort toward consistent, high-resolution GDE mapping. Multi-sensor Earth observation and geospatial datasets were integrated using ensemble ML modelling to identify groundwater-dependent habitats. Specifically, the study aimed to (1) evaluate the performance of multiple ML algorithms and ensemble approaches for GDE prediction, (2) assess whether aquatic and terrestrial GDEs can be effectively modelled within a unified framework, and (3) identify the most influential environmental and remote sensing variables driving GDE occurrence. The resulting model ensemble achieved high predictive accuracy (AUC = 0.90), with wetland and hydrological variables emerging as dominant predictors. The approach provides a scalable, transferable methodology for regional GDE mapping to support groundwater management, ecosystem monitoring, and cumulative effects assessment across northern Alberta.

This study presents a hydrology-informed deep learning framework for supraglacial lake segmentation on the Greenland Ice Sheet using Sentinel-2 imagery. Traditional approaches to lake mapping rely primarily on spectral cues, which often struggle in regions with weak contrast, shadowing, or surface melt variability. To address these challenges, we incorporate physically meaningful hydrological features—flow accumulation, distance-to-drainage, and surface depressions—derived from high-resolution DEMs to guide the segmentation process. The proposed FiLM-based two-stream U-Net consists of an RGB stream for spectral–textural representation and a hydrology stream encoding surface meltwater routing patterns. Feature-wise linear modulation is applied at multiple levels of the RGB encoder–decoder to dynamically condition spectral features on hydrological context and improve spatial coherence.

Experiments on the SIGSPATIAL 2023 GISCUP dataset demonstrate that this architecture improves segmentation accuracy over a Sentinel-2-only baseline and a simple channel-concatenation model, particularly for small, fragmented, or spectrally ambiguous lakes. The combined use of hydrological cues and deep feature modulation reduces false positives in regions where meltwater is unlikely to accumulate and strengthens delineations along complex lake boundaries. These improvements highlight the value of integrating physically informed geospatial descriptors with modern segmentation networks for robust supraglacial lake detection.

Beyond methodological gains, the results support downstream applications including meltwater routing analysis, supraglacial drainage characterization, and improved understanding of seasonal lake evolution. Ultimately, this framework contributes to more reliable ice-sheet mass balance assessments and sea-level rise projections by enhancing the consistency and physical realism of supraglacial lake mapping at scale.

The rapid retreat and thinning of glaciers in the North-western Himalayas due to climate change have led to a significant increase in the number and size of glacial lakes. These high-altitude lakes, often dammed by unstable moraines, pose a growing threat of Glacial Lake Outburst Floods (GLOFs), which can cause catastrophic flash floods and endanger downstream communities. Accurate estimation of glacial lake bathymetry is crucial for GLOF risk assessment, but direct measurement is challenging due to inaccessibility and harsh conditions. This study presents a methodology for evaluating glacial lake bathymetry using remote sensing data, focusing on the Panikhar glacier lake in Ladakh, India. Time series analysis was conducted to map the lake's water spread from 2015 to 2024 using optical and synthetic aperture radar data. Three approaches were employed to estimate bathymetry: a radiative transfer model (RTM) based on multispectral reflectance, a topographical model using high-resolution digital elevation models, and empirical equations relating lake area to depth. The RTM approach relies on the optical properties of water, while the topographical model leverages the surrounding terrain to infer underwater topography. Empirical equations were drawn from established literature. Results were validated against physical bathymetry survey observations. Among the methods, topographical modeling demonstrated the highest potential for accurate depth estimation, as it directly incorporates the lake's topographic features. This study highlights the importance of integrating remote sensing techniques for effective GLOF hazard assessment in remote, high-altitude regions, offering a scalable solution for monitoring and mitigating risks associated with glacial lakes in the Himalayas.

Wildfires are an increasingly dominant disturbance in boreal and Arctic Canada, a trend projected to continue under a changing climate. The ecological and hydrological impacts of wildfires cascade into the abundant inland lakes in these interconnected northern landscapes, leading to post-fire changes in lake quality and colour. Previous in-situ studies on post-fire lake water quality in boreal regions have yielded inconsistent results, preventing a regional-scale understanding of the prevalence, magnitude, and duration of fire impacts on boreal lakes.

Here, we use harmonized Landsat time series to quantify fire-driven lake colour change and its controls across western boreal Canada. We studied 83 fires that burned 13,968 lakes during 2005 - 2015 and quantified lake colour dynamics through surface reflectance in the red wavelength, a proxy for suspended sediments and turbidity. Using a Difference-in-Difference approach, we found pervasive and long-lasting increases in lake colour driven by fire disturbance, beginning in the first post-fire summer and persisting for at least ten years, indicating sustained elevated suspended sediment concentrations and turbidity regardless of physiographic variations. The magnitude and temporal patterns of these changes varied, with burn severity and physiography as important controls. Severe burns in the Taiga and Shield zones underlain by extensive permafrost led to greater and more prolonged changes in lake colour.

These findings underscore the critical and growing role of wildfires in boreal lake quality change, with important implications for aquatic habitats and water resources in a fire-prone future.

Natural disasters demand rapid damage assessment to guide humanitarian response. Here, we investigate whether medium-resolution Earth observation images from the Copernicus program can support building damage assessment, complementing very-high resolution imagery with often limited availability. We introduce xBD-S12, a dataset of 10,315 pre- and post-disaster image pairs from both Sentinel-1 and Sentinel-2, spatially and temporally aligned with the established xBD benchmark. In a series of experiments, we demonstrate that building damage can be detected and mapped rather well in many disaster scenarios, despite the moderate 10m ground sampling distance. We also find that, for damage mapping at that resolution, architectural sophistication does not seem to bring much advantage: more complex model architectures tend to struggle with generalization to unseen disasters, and geospatial foundation models bring little practical benefit. Our results suggest that Copernicus images are a viable data source for rapid, wide-area damage assessment and could play an important role alongside VHR imagery. We release the xBD-S12 dataset, code, and trained models to support further research.

In recent years, technological advancements, particularly in artificial intelligence (AI), are changing various fields and spurring new research. This study focuses on the use of AI in cartography and historical studies. It is part of the PRIN project "Crafted in Stone / Recorded on Paper," which aims to document the heritage of small Italian municipalities by creating an open-access database. The research discovered significant documents in Gandino, Italy, including a large-scale map and a 139-page textual register from the mid-eighteenth century. These documents come from land surveyors who measured municipal boundaries and properties using physical landscape markers. The original surveying method, although lost, shares similarities with modern land descriptions.

The study seeks to generate new maps from these textual registers using AI capabilities, aiming to replicate a historical mapping effort from the 1700s. Initial tests with an AI model involved reading the register, computing measurements, and creating coordinate tables. The results showed promise despite some inaccuracies. The goal is to develop an interdisciplinary method that graphically reconstructs information from written documents, enhancing access for historical and territorial analysis. The research will also explore further AI models and larger case studies to achieve this aim.

The analysis of buildings from aerial imagery is a fundamental task for urban planning and disaster response, yet it traditionally requires a suite of specialized models for tasks like segmentation, detection, and semantic querying. The advent of generalist Vision-Language Models (VLMs) offers a new paradigm, but their adaptation to the specific, high-resolution remote sensing domain remains a significant challenge. This paper proposes and investigates a novel methodology for adapting a general-purpose VLM,

Google’s PALIGEMMA2, to function as a unified geospatial building analyzer. The core of this contribution is a data-centric pipeline that converts single-modality annotations (building polygons) into a rich, multi-task instruction-tuning dataset (16,500 samples) spanning segmentation, detection, Visual Question Answering (VQA), and captioning. A rigorous study is conducted to answer three critical questions: (1) Can a single instruction-tuned VLM outperform specialized models in a multi-task setting? (2) What are the synergistic benefits of multi-task learning? (3) How data-efficient is this adaptation process? The results demonstrate that the unified model significantly outperforms the zero-shot PaliGemma2 baseline and strong single-task fine-tuned variants on three out of four tasks, while remaining competitive on the fourth. A strong synergistic effect is found: multi-task training on both visual localization and semantic tasks improves performance on individual localization tasks. Furthermore, the analysis shows that high performance can be achieved with a surprisingly small instruction dataset. This work provides a complete methodology for efficiently adapting VLMs to multi-task geospatial analysis, suggesting a new path towards generalist models in remote sensing.

Foundation models have achieved remarkable success across various domains due to their ability to learn generalizable representations from large-scale, unlabeled datasets. In the geospatial domain, several foundation models have been developed to leverage the abundance of unlabeled remote sensing data and support Earth observation tasks across diverse regions and sensor types. However, the geolocation-dependent characteristics of remote sensing data introduce unique challenges in adapting these models to region-focused applications. By conducting a comprehensive empirical analysis across diverse geographical regions and tasks, we explore whether incorporating regional information during pretraining or fine-tuning improves performance on region-specific downstream tasks. We show that regional representation learning, as well as regional adaptation of features extracted from a globally trained foundation model, is beneficial when the region-specific performance of the downstream tasks is of interest. To this end, we also propose a regional adaptation to the globally trained foundation models to balance global diversity with regional representation learning for improved performance.

Label noise in the sense of incorrect labels is present in many real-world data sets and is known to severely limit the generalizability of deep learning models. In the field of remote sensing, however, automated treatment of label noise in data sets has received little attention to date. In particular, there is a lack of systematic analysis of the performance of data-centric methods that not only cope with label noise but also explicitly identify and isolate noisy labels. In this paper, we examine three such methods and evaluate their behavior under different label noise assumptions. To do this, we inject different types of label noise with noise levels ranging from 10 to 70% into two benchmark data sets, followed by an analysis of how well the selected methods filter the label noise and how this affects task performances. With our analyses, we clearly prove the value of data-centric methods for both parts – label noise identification and task performance improvements. Our analyses provide insights into which method is the best choice depending on the setting and objective. Finally, we show in which areas there is still a need for research in the transfer of data-centric label noise methods to remote sensing data. As such, our work is a step forward in bridging the methodological establishment of data-centric label noise methods and their usage in practical settings in the remote sensing domain.

Extracting road networks from high-resolution imagery remains a significant challenge in geomatics, particularly in fragmented rural landscapes. The big difficulty is the spectral similarities between unpaved tracks and agricultural backgrounds that can lead to classification errors. This study proposes an automated geospatial pipeline based on the YOLOv11 architecture. Specifically, the approach is made on the optimization of the multi-class road detection in the rural areas of Kosina and Markowa, two villages in Poland. To reduce the computational effort, due to large-scale 9000x9000 px orthophotos and to improve the detection of small-scale features, Slicing Aided Hyper Inference (SAHI) strategy was integrated. High-resolution imagery has been decomposed into optimized tiles, ensuring feature continuity across boundaries and preventing GPU memory overhead. The instance segmentation model was trained on a custom-annotated dataset, with seven labels (categories) such as internal paved roads, rural tracks, and railway infrastructures. Therefore, a high level of robustness has been achieved reaching a mean Average Precision value (mAP@0.5) of 0.90. A confusion matrix reveals quantitatively that the pipeline effectively distinguishes between complex classes and low omission rates. As a result, the generated outputs are converted into interoperable GeoJSON format ensuring their integration into GIS environments. In conclusion, the experimental result demonstrates that the framework is valuable for emergency response logistics and urban planning. It offers a scalable and near real-time solution for updating national topographic databases.