Deep Learning-Based Snow Depth Retrieval Using Sentinel-1 Repeat-Pass InSAR
For hydrologists and remote sensing scientists, this work provides a more accurate and transferable method for high-resolution snow depth estimation, though it is domain-specific and tested on limited sites.
The paper develops a deep learning model that directly learns snow depth from Sentinel-1 repeat-pass InSAR observables, achieving a Pearson correlation of 0.81 with lidar snow depth, significantly outperforming physics-based methods (0.47) in temporal transfer experiments.
Snow depth plays a central role in seasonal snowpack characterization and the terrestrial water cycle, yet remains challenging to estimate at high spatial resolution. Recent studies have shown that repeat-pass interferometric synthetic aperture radar (InSAR) measurements combined with physics-based models can enable effective snow water equivalent (SWE) retrieval. However, the performance of these methods depends strongly on measurement accuracy and modeling assumptions. Building on the success of InSAR-based approaches, we develop a robust learning-based model that directly learns the relationship between measured InSAR observables and snow depth. The model is trained on a single SnowEx Idaho site and evaluated across independent years and geographically distinct regions. Results demonstrate strong temporal and spatial transferability. In temporal transfer experiments, the proposed approach achieves a Pearson correlation of 0.81 with lidar snow depth, compared to a correlation of approximately 0.47 reported for physics-based Sentinel-1 SWE retrievals over the same site.