A Machine Learning Model for Estimating Snow Density and Snow Water Equivalent from Snow Depth and Seasonal Snow Climate Classes

Download here

Abstract: Direct snow water equivalent (SWE) measurements are time-consuming, labor intensive,and often impractical over large areas. However, if the snowpack bulk density is known, SWE can be estimated from snow depth. Snow depth is a more accessible proxy for estimating SWE, as it can be quickly and easily measured with high precision. We propose a machine learning (ML) model that estimates snowpack bulk density from snow depth and other variables that only require the location and date of snow depth acquisitions. The estimated density can then be used to calculate SWE from depth. Our model was trained on approximately 2 million data points and tested on 544,513 testing samples from 864 SNOTEL sites in the western United States. We compared the proposed ML model to state-of-the-art statistical models, and it outperformed them all, reducing SWE estimation RMSE by up to 40% compared to the best-performing statistical model. To evaluate the ML model’s transferability, we tested it using data from the Maine Snow Survey - a different snow climate in the northeastern United States. The model provided promising SWE estimates without retraining and showed improved performance after retraining with a small portion of local data. Our ML model offers a practical and broadly applicable tool for estimating SWE in regions with limited snowpack monitoring.

Bibtex:
@article{alabi_climate,
  year = 2026,
  publisher = {},
  volume = {},
  number = {},
  pages = {},
  author = {Ibrahim Olalekan Alabi, Hans-Peter Marshall, Jodi Mead, Ernesto Trujillo},
  title = {A Machine Learning Model for Estimating Snow Density and Snow Water Equivalent from Snow Depth and Seasonal Snow Climate Classes},
  journal = {Artificial Intelligence for the Earth Systems}
}