Conference Agenda

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.