Machine‐Learning Estimation of Snow Depth in 2021 Texas Statewide Winter Storm Using SAR Imagery

Abstract

Abstract The frequency of extreme climate events has escalated since 1980. In February 2021, an unprecedented winter storm dumped the snow record in Texas. It claimed hundreds of lives and evolved into a national major disaster. However, we still lack a systematic approach to quantify large‐scale snow depth. Here, we use the differential coherence from Sentinel‐1 synthetic aperture radar (SAR) imagery to characterize the surface disturbance due to this winter storm. We further rely on machine‐learning algorithms to quantify Texas statewide snow depth using surface disturbance map, SAR amplitude, precipitation, temperature, surface topography, land cover, and population. Our approach can provide an independent snow depth estimation. Approximately 89% of Texas accumulated over 30‐mm snow depth. The SAR and machine‐learning integrated methods can also be applied to quantify other forms of surface disturbance and to ultimately help natural hazard mitigation.