CSU machine learning model helps forecasters improve confidence in storm prediction

Over the last several years, Russ Schumacher, professor in the Department of Atmospheric Science and Colorado State Climatologist, has led a team developing a sophisticated machine learning model for advancing skillful prediction of hazardous weather across the continental United States. First trained on historical records of excessive rainfall, the model is now smart enough to make accurate predictions of events like tornadoes and hail four to eight days in advance – the crucial sweet spot for forecasters to get information out to the public so they can prepare. The model is called CSU-MLP, or Colorado State University-Machine Learning Probabilities. 

UFS Weather Model Image of moving Nests

Implementation and testing of stochastic perturbations within a stand-alone regional (SAR) FV3 ensemble using the Common Community Physics Package (CCPP).

The Weather Program Office is working with the Cooperative Institute for Research in the Atmosphere (CIRA) at Colorado State University (CSU) and the National Center for Atmospheric Research (NCAR) to advance the forecast capabilities of the Rapid Refresh Forecast System (RRFS) through the testing and implementation of stochastic physics configurations. Researchers are testing various configurations…