Severe Hail Prediction within a Spatiotemporal Relational Data Mining Framework

Abstract

Severe hail, or spherical ice precipitation over 1 inch in diameter, has caused billions of dollars in damage to crops, buildings, automobiles, and aircraft. Accurate predictions of severe hail with enough lead time can allow people to mitigate some hail damage by sheltering themselves and their vehicles and by rerouting their aircraft. Current pinpoint forecasts of severe hail rely on detection of hail in existing storms with radar-based methods. Predictions beyond an hour are limited to probabilistic predictions over larger areas based on expected environmental conditions. This paper describes a technique that could increase the accuracy of severe hail forecasts by incorporating output from an ensemble of storm scale numerical weather prediction models into a spatiotemporal relational data mining model that would produce probabilistic predictions of severe hail. The spatiotemporal relational framework represents the ensemble output as a network of storm objects connected by spatial relationships. Composites of the ensemble data show spatial biases in the placement of severe and non severe hail storms. The spatiotemporal relational model performs significantly better at discriminating between severe and non-severe hail compared to a traditional data mining model of the same type. Variable importance rankings show results physically consistent with previous studies and highlight the importance of the relational data.