Enhancing Storm-Scale 1-h Probabilistic Low-Level Rotation Forecasts through Machine Learning

One focus of the NOAA Warn-on-Forecast (WoF) project is to provide probabilistic guidance for short-term (e.g., 0-1 h) tornado forecasts. Tornadoes are unresolvable with current operational models, but convection-allowing ensembles (CAEs) such as the 3-km NSSL Experimental WoF System for Ensembles (NEWS-e) provide forecasts of low-level rotation that can potentially discriminate between tornadic and non-tornadic storms. However, CAE forecasts of storms often contain large errors in storm intensity, timing, and location. Machine learning methods can produce calibrated probabilistic forecasts from the raw ensemble model output that can correct for systematic forecast biases, incorporate ensemble uncertainty, and include additional model variables.

This study will utilize real-time NEWS-e forecasts generated during the 2016 and 2017 NOAA Hazardous Weather Testbed Spring Forecasting Experiments and azimuthal shear analyses from NSSL Multi-Radar/Multi-Sensor (MRMS) as input data for training various machine learning algorithms to produce calibrated 1-h probabilistic forecasts of low-level rotation. Given that strong low-level rotation occurs infrequently, we are oversampling cases available cases to produce a more balanced dataset, which has been shown to improve machine-learning performance. The reliability and discrimination of the forecasts will be compared through verification statistics and multiple case studies.