Deep Learning-Based Snow Depth Retrieval Using Sentinel-1 Repeat-Pass InSAR

2026-04-18

AI Summary

This study addresses the challenge of snow depth estimation at high spatial resolution, which is typically hindered by measurement errors and simplifying assumptions inherent in physical models. For the first time, deep learning is introduced into InSAR-based snow depth inversion, leveraging repeat-pass Sentinel-1 interferometric data to directly model the nonlinear mapping between InSAR observables and snow depth. By integrating multi-source remote sensing data and employing a transfer learning strategy, the proposed approach achieves robust generalization across years and regions. Experimental results demonstrate that, under temporal transfer scenarios, the model attains a correlation coefficient of 0.81 with LiDAR-derived snow depth measurements—substantially outperforming conventional physical models, which yield correlations of approximately 0.47—thereby validating the method’s effectiveness and superiority.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Deep Learning Theory
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Models for Web evolution

Abstract

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.

Problem

• snow depth
• high spatial resolution
• InSAR
• snow water equivalent
• remote sensing

Innovation

• Deep Learning
• Snow Depth Retrieval
• Repeat-Pass InSAR
• Sentinel-1
• Transferability