Pré-Publication, Document De Travail Année : 2025

Weakly supervised learning for snow cover segmentation in mountainous areas from Sentinel-1 SAR images using interpolated NDSI time series

Résumé

Snow cover plays a fundamental role in climate regulation and hydrological processes. Existing snow products are based on optical imagery. Yet, snow monitoring remains challenging in mountainous regions due to frequent cloud cover. Synthetic Aperture Radar (SAR) imagery, unaffected by clouds, enables regular wet snow observations. However dry snow remains mostly transparent to SAR. In this study, we propose a fully automated framework to transfer the snow detection capabilities of optical images, that does not differentiate dry and wet snow, to SAR images. A convolutional neural network is trained to predict a binary snow cover map from a Sentinel-1 Single Look Complex (SLC) dual-pol amplitude image and a snow-free reference image. We threshold the MODIS Normalized Difference Snow Index (NDSI) product to generate binary training labels. Our model is trained in a weakly supervised manner by filling the cloudinduced gaps via temporal interpolation. We first evaluate the influence of the input SAR channels configuration and show that concatenating the acquisition of the day with the reference image is preferable to more complex preprocessing. Then, we compare the Closest Neighbours Interpolation and the Kalman smoother to fill the cloud-induced gaps in the MODIS NDSI time series. We show that increasing the level of supervision improves the model performance.

By removing all the gaps and the noise in the NDSI time series, the Kalman smoother yields the best model perfomance. However the regularization strength of the Kalman smoother is shown to be critical. To validate our method, we compare it to existing snow products. By comparing with the THEIA L2B Snow product, we show that our method gives comparable results to Sentinel-2 based snow cover maps. The comparison with the Copernicus Wet/Dry Snow product shows that our model can detect both wet and dry snow solely from Sentinel-1.

Fichier principal
Vignette du fichier
draft_preprint.pdf (11.01 Mo) Télécharger le fichier
draft_preprint (1).pdf (11.01 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05186268 , version 1 (25-07-2025)

Licence

Identifiants

  • HAL Id : hal-05186268 , version 1

Citer

Swann Briand, Flora Weissgerber, Sylvain Lobry, Jérôme Idier. Weakly supervised learning for snow cover segmentation in mountainous areas from Sentinel-1 SAR images using interpolated NDSI time series. 2025. ⟨hal-05186268⟩
2347 Consultations
292 Téléchargements

Partager

  • More