New insights into the role of snow and machine learning tools in water supply prediction

For large populations across the western U.S., water supply prediction relies centrally on knowledge of spring snow conditions, where snowpack can provide critical early warning of anomalous water supplies. As drought conditions emerge or future temperatures rise, snowpack is likely to decline, causing the relationship between snow and streamflow to shift. Recent research found that in the future, snowpack will be less predictive of drought in snowmelt-dominated systems in the western U.S.

In this webinar, WWA Director Ben Livneh and NOAA MAPP-supported PhD students Madeline Pernat and Parthkumar Modi began with an overview explaining why snow has been so important for water supply forecasting. Then, they followed by sharing their findings about alternative ways to use snow information to improve the performance of existing forecast techniques. Finally, they contrasted the utility of Machine Learning tools versus the inclusion of additional, non-snow based observational predictions, in improving water supply predictions.

The research is supported by the NOAA MAPP and NOAA CAP programs. For more information, contact Ben Livneh at ben.livneh@colorado.edu.