Conference Agenda

The development of high-performance, affordable UAVs has transformed vegetation monitoring, enabling observation of forest canopies at an unprecedented level of detail. UAV-derived datasets now provide high-fidelity structural and physiological information at the individual tree level across entire forest stands, offering novel insights into forest dynamics. In the context of increasing tree mortality, such data are becoming essential for understanding forest resilience and adaptation. However, exploiting this data requires effective individual tree crown segmentation algorithms (ITCS) at the forest scale, capable of tackling large-scale data and variability introduced by the environment. In this paper, we developed a new workflow designed to process UAV hyperspectral imagery at the forest scale, enabling automated ITCS and analysis. Our pipeline integrates hyperspectral-to-RGB conversion, ITCS, and centroid-based mask fusion. To assess the performance of our pipeline, we evaluated the model on two replicated white spruce common gardens in Canada, each comprising approximately 6,000 trees of similar age and structure. The experiments rely on a large multi-temporal dataset of hyperspectral imagery acquired during 60 UAV missions between 2022 and 2024, allowing us to evaluate the robustness of the proposed pipeline across a wide range of seasonal and acquisition conditions. Results show that the proposed pipeline achieves a mean segmentation performance of 0.536 mAP (0.885 mAP50) on the annotated dataset. At the forest scale, the system demonstrates strong detection capability with F1-scores of 0.948 at the Pintendre site and 0.863 at the Pickering site, successfully detecting most trees while maintaining stable performance across varying environmental conditions.

Individual tree detection and crown delineation (ITDCD) in dehesa landscapes is complicated by geometric distortions from steep terrain, varying tree densities, and the partly multi-crown 'broccoli-like' structure of holm and cork oaks. This study evaluates the usability of a modified StarDist deep learning model, which has recently shown effectiveness for ITDCD in Canadian forests. Moreover, this study develops a workflow transforming the original StarDist, designed for microscopy images, into an ITDCD solution, taking the georeferencing of geospatial data into account. The tile-wise organized ground truth dataset is created with the pretrained Tree Segmentation model available in the ArcGIS Living Atlas, combined with manual revision. Several augmentation methods are applied, resulting in 960 images, which are split into 85 % for training and 15 % for validation. Following the approach of the Canadian forest study, the StarDist implementation is modified by introducing a constraint to the probability loss function. Rather than computing loss across all pixels, the modified loss function considers only pixels explicitly annotated as objects, while background pixels are excluded. An additional dataset of 1,200 trees serves as ground truth for testing the prediction across the entire study area. Using an Intersection over Union of 0.5, this test demonstrates good performance (Accuracy: 87.50 %; F1-score: 0.85). The accuracy varies with tree density: in areas with sparse tree cover, nearly all tree crowns are detected; in moderately dense areas, a number of tree crowns are missed; whereas in very dense tree layers, the frequency of missed detections increases.

Individual tree crowns detection and delineation from airborne LiDAR data is essential for forest inventory, carbon stock estimation, and ecosystem monitoring. In mixed-wood forests, however, this task remains difficult due to high stand density, multi-layered canopy structure, and the wide variation in crown size and shape across coniferous and deciduous species.

This study addresses two core limitations of existing deep learning methods for individual tree crown delineation. Standard instance segmentation models rely on blind anchor-based proposals that frequently miss small understorey trees in dense canopies, and their pixel-based mask representations struggle to accurately capture crown boundaries for small or irregular crowns.

We propose a multi-task learning framework that jointly trains a structure-aware treetop detection head and a crown segmentation head on a shared backbone network. The treetop detection head generates spatially precise crown seeds guided by canopy height and allometric relationships, replacing blind anchor proposals with data-driven initialisation. Two segmentation strategies are evaluated within this framework: a Mask R-CNN pixel-based approach and a StarDist contour-based approach.

Experiments are conducted on a high-density airborne LiDAR dataset acquired over a mixed-wood forest in Ontario, Canada, comprising 4,417 manually delineated reference crowns. Results demonstrate improved detection completeness for small crowns and more accurate boundary delineation for overlapping larger crowns compared to single-task baselines.

This study examines the use of multi-temporal UAV hyperspectral and LiDAR data to identify tree species in a mixed deciduous forest in southern Ontario, Canada. Weekly UAV flights were conducted from summer through spring to capture structural and spectral changes associated with leaf development, senescence, and leaf drop. Field measurements were collected to provide species labels and biometric information for individual trees.

LiDAR data are processed to delineate individual tree crowns and to derive structural metrics such as crown height, width, density, and vertical canopy profile. Hyperspectral imagery, consisting of more than 300 bands, is co-registered with the LiDAR-derived crowns to extract spectral signatures and compute vegetation indices. These data support the development of a spectral library for the main species in the study area.

The multi-temporal dataset allows evaluation of how phenological changes influence separability among species. Early leaf loss in autumn and differences in budburst timing in spring are expected to produce temporary structural and spectral contrasts that aid classification. Machine learning models, including random forest and neural networks, are applied to assess the contribution of structural, spectral, and seasonal features to species discrimination.

Accurate 3D reconstruction and instance segmentation of soybean seedlings are crucial for early phenotyping and precision agriculture. This study presents a UAV-based sparse-view 3D reconstruction and plant-level segmentation framework that integrates 3D Gaussian Splatting (3DGS) with Mobile-SAM, enabling efficient and high-fidelity modeling under routine field conditions. Traditional LiDAR and MVS approaches, while detailed, are constrained by cost, acquisition density, and computational complexity. By contrast, 3DGS offers explicit Gaussian primitives for fast rendering and direct geometric access but often fails under sparse-view UAV imagery due to weak multi-view constraints and repetitive canopy structures.

To overcome these limitations, the proposed method introduces a mask–geometry co-optimization mechanism: YOLO-generated bounding-box prompts guide Mobile-SAM to produce accurate single-view plant masks, which serve as semantic priors to associate 2D observations with 3D Gaussian primitives. Iterative refinement aligns rendered and observed masks, ensuring spatial consistency and coherent 3D plant boundaries.

Field experiments on a soybean plot demonstrated the method’s effectiveness, achieving high reconstruction quality and visually precise seedling segmentation. The resulting 3D models capture fine structural details and distinct plant instances even under sparse-view UAV data.

This work highlights the potential of combining explicit geometric modeling and lightweight semantic segmentation to achieve robust, scalable, and field-deployable 3D crop reconstruction, offering a promising pathway for high-throughput plant phenotyping and yield estimation in real-world agricultural applications.

In this study, we propose an upscaling approach based on 8-band PlanetScope SuperDove imagery (Coastal Blue, Blue, Green I, Green, Yellow, Red, Red Edge, NIR) combined with UAV data. We employed an evidential Dirichlet neural network to estimate the fractional cover of 13 herbaceous and shrub species typical of Mediterranean coastal dunes, previously mapped at 3 cm using a traditional Random Forest classifier trained on UAV multispectral samples. The overall goal is to enable large-scale mapping of coastal vegetation using high-resolution satellite imagery.

This work addresses the emerging challenge of achieving proactive spatial cognition for embodied and spatial AI systems operating in dynamic real-world environments. Conventional mapping and reasoning approaches are largely passive and task-dependent, limiting their ability to build persistent understanding beyond immediate goals. We introduce the Proactive Cognitive Map (PCM), a unified framework that enables agents to autonomously construct, verify, and refine their spatial knowledge through continual perception, self-questioning, and mental simulation. PCM integrates a grid-based perceptual map with a semantic, object-centric memory, forming an explicit and interpretable representation of the environment. A self-questioning module identifies uncertain or ambiguous regions and generates targeted queries, while a simulation module emulates human imagination to perform counterfactual reasoning and lightweight geometric self-verification across time and viewpoints.

We evaluate PCM across episodic-memory embodied QA tasks and the long-horizon, multi-task benchmarks, GOAT-Bench, covering episodic reasoning, continual understanding, and cross-task generalization. Results show that PCM’s self-driven graph construction and proactive refinement outperform goal-specific exploration methods.

By transforming mapping from static perception into a continual cognitive process of questioning, imagining, and verifying, this study provides a step toward lifelong, interpretable, and self-improving spatial intelligence.

As a spatial digital foundation for digital twins and smart cities, the timeliness and accuracy of realistic 3D models are of critical importance. Intelligent and automated data acquisition and update workflows form the core infrastructure that sustains this digital foundation. Current modeling techniques relying on a single data source face inherent limitations: UAV(Unmanned aerial vehicle)-based oblique photogrammetry struggles to capture lower facade details, often leading to geometric distortions and blurred textures, while conventional terrestrial surveying methods suffer from low efficiency and limited automation as well as intelligence. Moreover, the substantial viewpoint differences between aerial and ground data hinder effective fusion. However, recent technological advances in 3D Gaussian Splatting (3DGS), large vision model, multi-sensor SLAM and robotic systems, open up new opportunities to significantly improve the fidelity, efficiency, completeness and automation of 3D reconstruction through the cooperation of UGVs and UAVs.To address the current challenges from 3D reconstruction, this study proposes a novel framework which seamlessly integrates autonomous unmanned systems, state-of-the-art large visual models, multi-sensor SLAM (simultaneous localization and mapping) and cutting-edge 3D Gaussian rendering technology. The framework realizes an integrated workflow for automatic updating building facade and high-fidelity 3D GS rendering using air to ground fusion algorithms with autonomous systems. The primary focus is to advance the automation and intelligence of building 3D reconstruction, thereby enabling efficient updates of urban 3D models.

High-precision digital terrain models (DTMs) are important for Mars explorations and research. However, traditional terrain reconstruction methods suffer from limitations in coverage and resolution. To enhance the model's ability to recover fine-grained topography, we present a diffusion-based monocular terrain reconstruction method, which progressively recovers Martian terrains from single-view high-resolution optical images. We employed a multi-scale U-Net denoising network with attention mechanisms and introduced an additional end-to-end depth constraint. To improve terrain reconstruction efficiency, we implemented a diffusion model in the latent space and adopted a skipping sampling mechanism. We employed the proposed method to reconstruct terrain in different regions. Experimental results demonstrate that the reconstructed terrain achieves an accuracy of 2 m. Furthermore, compared to photogrammetric terrain, the shaded relief generated by our method exhibits greater similarity to the input imagery.

GESM is a Gaussian-mixture sonar mapping pipeline that converts 2D imaging sonar into a continuous 3D probabilistic map for navigation. We estimate posterior occupancy with Gamma-CFAR, cluster occupied and free space along beams, encode them with weighted EM/MPPCA and moment-matched Gaussians, and incrementally merge local mixtures into a globally consistent map. Loop closure is handled by in-place edits of mixture parameters. On simulation and pool/harbour data, GESM yields dense, navigation-ready structure and free water while reducing map memory by ~99% compared with a comparable voxel grid.

This paper investigates how the provenance and resolution of geospatial data used to construct mesh maps affect the accuracy and robustness of mesh-based visual localisation. Mesh-based approaches offer significant advantages over traditional pipelines reliant on Structure from Motion (SfM) models, including the ability to scale to city-sized scenes---by leveraging large-scale data sources such as national mapping databases--- and on-demand generation of arbitrary synthetic views. While prior work has focused on algorithmic improvements to mesh-based localisation, none has systematically analysed how different input data affect localisation outcomes. In this work, we evaluate three meshes---derived from aerial oblique imagery, combined aerial and ground mobile mapping data, and close-range ground imagery---across the egenioussBench Extended and House of Science query sets and four image matchers. We show that mesh quality is the dominant factor governing localisation performance. In the House of Science experiments, aerial meshes lack the resolution required to resolve façade detail, causing near-total localisation failure regardless of matcher. In the egenioussBench Extended experiments, augmenting an aerial mesh with ground data yields consistent but less dramatic improvements. We further introduce the Perceptual Detail Score (PDS), a viewing-condition-aware metric that proves to be a strong predictor of downstream pose accuracy across all experimental configurations.

The accurate recognition of segment joints serves as a critical step for capturing joint anomaly information, evaluating segment assembly quality, diagnosing structural health status, and determining the loosening of connecting bolts. It holds significant importance for the operation and maintenance of shield tunnels. However, existing studies on joint recognition based on Rail-borne Mobile Laser Scanning (RMLS) suffers from insufficient comprehensiveness in feature representation, leading to notably poor accuracy and robustness under complex scenarios such as noise interference, data loss due to object occlusion, and uneven point cloud density. To address this issue, this study proposes a shield tunnel segment joint recognition method based on the Joint Composite

Feature Index (JCFI). The proposed method first employs a cross-sectional ellipse fitting approach to filter out obvious non-lining points. Subsequently, a composite index JCFI, which integrates curvature, left-right density ratio, and relative depth, is designed to

quantitatively characterize the feature differences of segment joints. Finally, based on the constructed JCFI indicator, the recognition of circumferential and longitudinal joints is sequentially achieved. Validation tests using RMLS point cloud data from the Guangzhou Metro Line 8 tunnel demonstrate that the proposed method, by constructing the JCFI that comprehensively characterizes joint features, effectively handles complex scenarios including noise interference, joint missing, and uneven point cloud density. The

joint recognition achieves a recall rate of 90.14%, a precision rate of 99.04%, and an IoU of 89.36%, providing a reliable technical solution for the accurate identification of shield tunnel segment joints.

Severe convective rainfall, triggered by multi-scale atmospheric interactions, poses a critical forecasting challenge in coastal cities like Shanghai, where monsoon, topography, and sea-land breeze amplify extremes. Conventional methods, constrained by scale separation and model biases, struggle to predict convection. This study develops the Synergistic Framework for Convective Rainfall Forecasting (SSF-CRF) by integrating three modules: (1) Adaptive S/X-band radar remote sensing, dynamically capturing mesoscale convective structures; (2) Gated Vertical Information Propagation (GVIP) network, machine learning on vertical energy propagation to capture convection; (3) Precipitation Ordinal Distribution Autoencoder (PODA), correcting numerical weather prediction (NWP) biases with ordinal precipitation classification. Verification against Radar data and European Centre for Medium-Range Weather Forecasts (ECMWF) model indicates that SSF-CRF improves heavy rainfall (≥50 mm/h) Critical Success Index (CSI) by 33% versus operational forecasts. It offers a potential solution for convective forecasting in climate-vulnerable coastal regions, advancing remote sensing-driven atmospheric applications.

Monitoring atmospheric water vapour is essential for weather forecasting and climate studies. GNSS networks can retrieve Precipitable Water Vapour (PWV) continuously at each station location, but the accuracy depends on the quality of the satellite orbit and clock corrections used in the processing. This study evaluates PWV retrieval from 478 stations of the French Centipede low-cost GNSS network using four levels of correction products with decreasing latency: GFZ Final ($\sim$2 weeks), Rapid ($\sim$1 day), Ultra-rapid (3--9 hours), and broadcast ephemerides (real-time). Validation against ERA5 reanalysis shows that the Final and Rapid products achieve similar performance (RMSE $\approx$ 2~mm, $r^2$ = 0.84), confirming that near-real-time processing introduces no significant accuracy loss. Ultra-rapid products remain usable (RMSE = 3.4~mm), while broadcast ephemerides show larger errors (RMSE = 5.8~mm) but still capture the spatial moisture pattern. In addition, a real-time experiment using the freely available Galileo High Accuracy Service (HAS) demonstrates that stable tropospheric estimates (ZTD $\pm$ 1.4~mm, PWV $\pm$ 0.2~mm) can be obtained in real time, even before the positioning solution has fully converged. These results suggest that combining the spatial density of low-cost networks with real-time HAS corrections could enable high-resolution PWV monitoring that is not achievable with existing systems.

Fengyun-3G, launched in 2023, carries Ku- Ka dual-frequency precipitation measurement radar (PMR) providing new opportunities for monitoring the fine three-dimensional structure of typhoon precipitation over the ocean. This study first validate the FY-3GPMR data by using the ground-based data, then utilizes PMR to analyze the precipitation during the rapid intensification phase of Super Typhoon Yagi in the year of 2024. The analysis reveals the horizontal and vertical distribution characteristics of precipitation during Yagi's RI phase based on the FY-3G PMR data, and discusses the associated dynamical-microphysical coupling mechanism. Overall, FY-3G PMR offers critical insights for understanding cloud and precipitation process involved in the RI.

Atmospheric water vapor plays a fundamental role in regional climate regulation and precipitation formation, yet its vertical structure and spatiotemporal evolution over mainland China remain insufficiently understood due to complex terrain and diverse climatic conditions. Using Fengyun-4A layered precipitable water (LPW) products from 2020 to 2023, this study provides a comprehensive assessment of the vertical distribution, spatiotemporal variability, and key environmental drivers of water vapor across China. Results show pronounced spatial gradients and seasonal contrasts: total precipitable water (TPW) exhibits a slight overall decline, primarily driven by reductions in low layer; spatially, TPW is highest in the southeast and lowest in the northwest; seasonally, water vapor peaks in summer and reaches its minimum in winter, with spring and autumn representing monsoon-transition phases. Vertically, approximately 75% of atmospheric water vapor is concentrated within the lowest 4 km, with the middle layer contributing most to regional differences, while high layer remains relatively uniform and minimally influenced by terrain. Environmental correlations indicate that TPW is positively associated with 2m temperature, relative humidity, surface pressure, total cloud cover, and precipitation, but negatively associated with DEM and evaporation. Layer-dependent responses indicate that the lower layer is strongly influenced by surface processes, the middle layer by both surface moisture transport and large-scale circulation, and the high layer primarily by thermodynamic structure and synoptic background. These findings, derived from high-resolution satellite observations, enhance understanding of atmospheric water vapor stratification and its controlling mechanisms, providing essential support for water vapor transport diagnosis, precipitation evolution, and operational forecasting improvement.

In recent decades, global climate change has triggered a rise in extreme environmental phenomena, including prolonged droughts, intensified precipitation events, and shifts in tidal patterns. This study focuses on the application of the observations from Global Navigation Satellite System (GNSS) signals for monitoring and classifying climatic conditions, with particular emphasis on drought.

Using daily vertical displacement data from a GNSS station in California (2005–2023), we developed a robust analysis framework. It includes data cleaning (removing outliers, filling gaps, detecting offsets, and modeling noise), trend and seasonal pattern extraction through Singular Spectrum Analysis (SSA), feature generation (like amplitude, energy, and dominant frequency), labeling

based on the Standardized Precipitation-Evapotranspiration Index (SPEI), and classification using a hybrid CNN-Transformer model. The results demonstrate the model’s capability to accurately detect drought periods (SPEI > -1) characterized by diminished amplitudes in seasonal components and heightened noisy fluctuations, as well as wet periods (SPEI < 1) marked by elevated energy in semi-annual signals. The model was evaluated with an overall accuracy of 83.3 percent, an F1-score of 0.90 for the drought class, and successful application to future data (2024–2029). This approach, independent of traditional meteorological data, underscores the potential of GNSS as a geodetic tool for environmental monitoring, albeit with limitations such as reliance on single stations and the need for supplementary datasets. The methodology holds promise for enhancing early warning systems and climate models.

Carbon dioxide (CO₂) and methane emissions (CH₄) are primary greenhouse gases whose rising atmospheric levels intensify global climate change. Wetlands, despite covering only 5–8% of Earth’s land area, contribute nearly 30% of global methane emission while storing up to 30% of global soil organic carbon. This makes wetlands both sinks and sources of greenhouse gases, though their seasonal CO₂ and CH₄ dynamics in the Guangdong–Hong Kong–Macao Greater Bay Area (GBA) remain poorly understood.

Ground-based instruments offer high accuracy but limited spatial coverage, whereas satellite missions, such as Sentinel-5P/TROPOMI for XCH₄ and OCO-2 for XCO₂, enable wide-area monitoring. This study investigates the seasonal dynamics of CH₄ and CO₂ across different wetland ecosystems in the GBA using satellite observations and ERA5-Land climate variables. Seasonal means were computed in Google Earth Engine for Winter, Spring, Summer, and Autumn from 2019 to 2025.

Results show a consistent rise in atmospheric CH₄ from 1856 ppb (2019) to 1939 ppb (2025), with the highest levels in Autumn and Winter. CO₂ increased from 404 ppm to 424 ppm, peaking in Winter and Spring. Non-wetland regions and mangroves emerged as the primary contributors to greenhouse gas accumulation, while salt marshes and other wetlands showed lower values.

Pearson correlation analysis indicated strong influence of temperature, dew point, and precipitation on CO₂, while CH₄ showed variable sensitivity to rainfall and wind. Findings emphasize the impact of land-cover type and climate in shaping seasonal greenhouse gas dynamics, supporting SDG 13 and SDG 15, and necessitating hyperspectral data integration for climate policies.

Urban air quality remains a critical concern, as NO₂ emissions from transport and industrial activities frequently exceed healthy limits in major cities. Urban vegetation can help reduce pollution by enhancing natural filtration and cooling, while higher land surface temperatures (LST) tend to intensify pollutant accumulation. Using satellite-based remote sensing, this study investigates how vegetation health (NDVI) and surface temperature influence NO₂ levels in two distinct urban environments: Blackburn/Arlington Road in England and District No. 3 in Tehran, Iran, across pre-, during-, and post-COVID-19 lockdown periods. Both cities experienced notable environmental improvements in 2020: NDVI increased from approximately 0.45–0.48 to around 0.54–0.61, while NO₂ dropped significantly from about 0.46–0.50 to roughly 0.13–0.35. LST also declined from pre-lockdown values near 0.46–0.48 to as low as 0.12–0.38. During the lockdown, vegetation levels showed a clear negative relationship with NO₂ concentrations, and pollution trends displayed a strong positive association with higher temperatures, highlighting the linked benefits of greener and cooler environments. However, as human activities resumed after 2021, these relationships became inconsistent or weakened, with occasional shifts in direction depending on seasonal conditions and external drivers such as traffic recovery and industrial intensity. Overall, the results reinforce that increasing vegetation coverage and mitigating urban heating can meaningfully reduce NO₂ levels. By revealing how urban form, vegetation dynamics, and thermal conditions collectively shape pollution patterns, this research provides insights for city planners, environmental managers, and public health authorities working to design more sustainable and healthier urban environments.