SRSDNet: Super-Resolution Snow Depth Retrieval and Mapping Over the Qinghai-Tibet Plateau

作者：Linglong Zhu, Zhou Zhou, Yonghong Zhang, Renliang Xu, Xu Liu, Xiaojun Niu, Xi Kan, Jiangeng Wang · 发表于：IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 年份：2025 · DOI：10.1109/jstars.2025.3648297 · 研究领域：Cryospheric studies and observations、Arctic and Antarctic ice dynamics、Soil Moisture and Remote Sensing

Conventional passive microwave (PMW) snow depth (SD) retrieval faces dual limitations over the Qinghai-Tibetan Plateau (QTP): coarse spatial resolution (typically >25 km) obscures topographic heterogeneity, while station-based labels introduce representativity errors by treating sparse points as pixel-scale “truth.” To overcome these challenges, we propose SRSDNet (Super-Resolution Snow Depth Network)—a deep learning framework integrating FengYun-3 PMW data with auxiliary variables (topography, fractional snow cover). Crucially, SRSDNet pioneers the use of 500-m resolution Sentinel-1 SD products as area-constrained labels, eliminating point-to-pixel mismatches. Its architecture incorporates three novel modules, the bidirectional feature extract block (BFEB) extracts anisotropic features via bidirectional convolutions to resolve mountain snow textures; the optimized coordination attention (OCA) dynamically weighted multi-source channels, especially low-frequency microwaves in deep snow; and the reconstructive output block (ROB) reconstructs 6.25-km outputs with local detail and global consistency. The results of this study were systematically validated at 95 meteorological stations in QTP during the 2017-2018 snow season, SRSDNet achieves best-in-class accuracy (RMSE = 12.075 cm, MAE = 7.724 cm, R2 = 0.781). Notably, it sets a new benchmark for deep snow retrieval with an RMSE of 9.939 cm for SD >50 cm and a relative error of less than 20%. This work establishes a paradigm for...