Accurately estimating snow water equivalent (SWE) is crucial for understanding the impacts of climate change, urbanization, and population growth on water resources. High operational costs of lidar observations limit the frequency and coverage of SWE estimates at high spatial resolutions, leading to significant data gaps. We address this challenge with a transfer learning framework that leverages abundant SWE data from California to enhance predictions in Colorado, where data are scarce. From 2016 to 2019, the disparity in SWE data collection between these states was stark: 94 snowpack maps were recorded in California’s Sierra Nevada versus only 12 in Colorado’s Rocky Mountains. We hypothesized that geographic predictors (e.g., elevation and snowfall) would exhibit similar effects on SWE across these landscapes. By conducting an explanatory factor analysis, we validated this hypothesis and refined our transfer learning model, which incorporated data from California to predict SWE in Colorado. When compared with using data from Colorado alone, transfer learning improved the mean R2 value from 0.43 to 0.56, indicating a significant enhancement of over 30% in predictive accuracy. Such advancements underscore the potential of our framework to mitigate lidar data limitations, offering a valuable tool for water resource management amidst changing environmental conditions.