Integrating meteorological forcings and satellite-derived observations to emulate snow water equivalent in the Colorado Rocky Mountains using a spatiotemporal deep learning model
Accurate estimates of snow water equivalent (SWE) are critical for hydrologic forecasting and water resource management in snow-dominated regions. While in situ observations, such as those from the United States Department of Agriculture snow telemetry (SNOTEL) network, provide direct measurements, their sparse spatial coverage limits their broader applicability. Numerical models such as Noah Multi-Parameterization (Noah-MP) provide spatially continuous SWE estimates but are computationally demanding. This study develops a deep learning–based emulator to reproduce SWE simulated by Noah-MP using a Convolutional Long Short-Term Memory (ConvLSTM) network trained on meteorological forcings from the Weather Research and Forecasting model and augmented with static physiographic variables and remotely sensed snow cover and leaf area index data. Incorporating spatial coupling substantially improves performance relative to a pixel-wise Long Short-Term Memory baseline, increasing the fraction of grid cells with non-negative Nash–Sutcliffe Efficiency (NSE) by 15–27% during the test period. The emulator reproduces large-scale SWE patterns consistent with both Noah-MP and Snow Data Assimilation System (SNODAS) and maintains competitive NSE and root mean square error performance relative to SNOTEL observations. Seasonal sensitivity experiments yield high R 2 values up to 0.96 during accumulation and 0.97 during melt. Once trained, the emulator generates SWE predictions faster than the parent physics-based simulation, enabling rapid, high-resolution estimates that support real-time monitoring and ensemble forecasting.