Reconstructing Multi-Decadal Forest Disturbances: A Spatio-Temporal Transformer Approach
It addresses the need for accurate, spatially coherent forest disturbance monitoring for carbon dynamics and land management, though improvements are incremental over existing methods.
The paper presents a spatio-temporal transformer model for mapping 38 years of forest disturbances across the contiguous US, achieving high precision (up to 98.2%) but with trade-offs in F1-score (up to 75.8%) compared to pixel-wise baselines.
Accurate monitoring of forest disturbances is essential for understanding carbon dynamics and land management, yet traditional approaches typically rely on pixel-wise analysis of satellite time-series, ignoring spatial context. We present a deep learning framework that maps 38 years (1984-2022) of forest disturbance across the contiguous United States by modeling temporal trajectories and spatial neighborhoods simultaneously. By leveraging a vision transformer architecture, our approach effectively filters noise from weak supervision signals to produce spatially coherent disturbance maps. We perform exhaustive evaluations across multiple satellites (Landsat, Sentinel-1, Sentinel-2) and temporal windows (38 years and the more recent 6 years), validating performance against a novel, manually annotated validation dataset (n=300) and independent fire perimeter dataset (n=706). The results highlight the complexity of the task: while our spatio-temporal model demonstrates high precision (up to 98.2% for +-1 year detection on MTBS and up to 71.3% on the CONUS validation datasets, with F1-scores up to 75.8% and 47.3%, respectively) and effectively reduces spatial artifacts, it exhibits performance trade-offs across different disturbance regimes compared to pixel-wise baselines. Our method offers a promising foundation for consistent forest monitoring.