SWEML

The current iteration of the SWEML produces 11,000 1 km SWE inferences for select locations throughout the Western U.S. plus the Upper Colorado River Basin. There is a heavy focus on SWE inferences in the Sierra Nevada mountains, Colorado Rockies, and Wind River Range in Wyoming. The NSM pipeline assimilates nearly 700 snow telemetry (SNOTEL) and California Data Exchange Center (CDEC) sites and combines them with processed lidar-derived terrain features for the prediction of a 1 km x 1 km SWE inference in critical snowsheds. The ML pipeline retrieves all SWE observations from SNOTEL and CDEC snow monitoring locations for the date of interest and processes the SWE observations into a model-friendly data frame alongside lidar-derived terrain features, seasonality metrics, previous SWE estimates, and location. SWEML predicts SWE using a uniquely trained multilayered perceptron network model for each region and supports an interactive visualization of the SWE estimates across the western U.S.