Applying a Genetic Algorithm to Optimize Hail Prediction Using the Weather Research and Forecasting Model

Hailstorms are highly localized severe weather events that can cause extensive damage to agriculture, infrastructure, and property, necessitating accurate forecasting for effective risk mitigation. The Weather Research and Forecasting (WRF) model, a numerical model which is able to simulate features from a wide range of scales, offers a range of physics parameterizations to simulate sub-grid scale processes which are essential for hail storm forecast. However, the vast number of possible configurations complicates the identification of an optimal setup for hail simulation. This study leverages a genetic algorithm (GA) to systematically optimize WRF physics parameterizations for hail prediction over Central Europe, focusing on the severe hail events of June 2022.

The GA framework encodes WRF physical parameterizations configurationsas individuals within a population, evolving through selection, crossover, and mutation across multiple generations. Fitness is evaluated using the F2 score, prioritizing recall to address the imbalance between observed hail and non-hail events. By exploring over 2.4 million potential configurations, the GA provides the best combinations of physical parametrizations to capture the spatial and temporal characteristics of hailstorms. The results show that this methodology enables the exploration of a wide range of possible configurations, demonstrating its potential to optimize parameterizations for high-impact weather events effectively. This novel methodology represents a substantial step toward advancing hail forecasting capabilities using high-resolution NWP models.