Learning Regional Snow Water Equivalent and Snow Height Variations from Sentinel-1 InSAR Acquisitions

2026-09-28

AI Summary

This study addresses the challenge of reliably monitoring snow water equivalent (SWE) and snow depth (HS) at scale in mountainous regions. Leveraging Sentinel-1 InSAR data combined with machine learning methods—including XGBoost, U-Net, and SegFormer—the project jointly estimates SWE and HS variations across the Italian Alps. By comparing multiple model architectures and analyzing feature sensitivity, the research demonstrates that spatial metrics are more effective than mean error metrics in distinguishing model performance, while errors primarily stem from systematic biases. Results indicate that SegFormer achieves optimal performance, yielding an HS MAE of 10.39 cm and an SWE MAE of 27.11 mm, alongside minimal initialization variability. Overall, this work provides an efficient and reliable deep learning framework for snow parameter retrieval using InSAR remote sensing.

Abstract

Managing water resources in mountainous regions depends heavily on reliable Snow Water Equivalent (SWE) and Snow Height (HS) data, yet these variables remain difficult to track at scale. This study evaluates three machine learning architectures (XGBoost, U-Net and SegFormer) for the joint estimation of SWE and HS variations from Sentinel-1 InSAR data over the Italian Alps, using the IT-SNOW reanalysis as reference. SegFormer achieves the best results on both targets, with an MAE of 10.391 cm for HS and 27.113 mm w.e. for SWE and the lowest variability across initializations. A feature sensitivity analysis shows that including all available features does not guarantee the lowest error, with model- and task-specific sensitivities. Spatial metrics (R2, Pearson's r) separate the three architectures far more clearly than mean error (MAE, RMSE) does, and decomposing the error per window attributes most of it to a systematic offset in the estimated mean variation rather than to the spatial pattern.

Problem

• Snow Water Equivalent
• Snow Height
• Sentinel-1 InSAR
• Mountainous regions

Innovation

• Snow Water Equivalent
• InSAR
• SegFormer
• Machine Learning
• Feature Sensitivity