Abstract. The majority of the water supply for many western US states is derived from seasonal snowmelt in mountainous regions. This study aims to generate basin-scale snow depth estimates using a multistep, Gaussian-based machine learning model that combines snow probe depth measurements with static lidar terrain features from a single snow-free date, enabling rapid, high-resolution estimation at low institutional cost. We focus on reducing personnel danger by modifying the algorithm to minimize the exposure of field sample collectors to avalanche-prone terrain. Using snow observations taken solely within a subbasin (∼ 9 km2) of a larger basin (∼ 70 km2), a basin-scale snow depth estimate is modeled for a given date throughout the snow season. Results show that a small number of observations (i.e., 10) within a subbasin can realize snow depth across the greater basin with high accuracy, with a root mean squared error (RMSE) of 0.37 m and Kling–Gupta efficiency (KGE) of 0.59 when compared to lidar snow depth distribution. We test the universality of the algorithm by modeling multiple subbasins of differing spatial characteristics and find similar results. The algorithm shows consistent performance across subbasins with varying spatial characteristics and maintains accuracy even when high-risk avalanche areas are excluded from the training data. This method exhibits a potential for citizen-scientist data to safely provide gridded modeled snow depth across different spatial ranges in snow-covered basins.
Liljestrand et al. (Mon,) studied this question.