Modelling hail probability over Italy with a machine learning approach

CMCC Webinar June 29, 2021 – h. 12:30 pm CEST Speakers: Verónica Torralba, CMCC Foundation – CSP Division Riccardo Henin, CMCC Foundation – CSP Division Moderator: Jaroslav Mysiak, CMCC Foundation – Director RAAS Division Hail is a meteorological phenomenon with adverse impacts that affects multiple socio economic sectors such as agriculture, renewable energy and insurance. Consequently, the mitigation of the hail-related risk in particularly sensitive regions such as Italy has fostered the hail research, including a deeper understanding of the favourable environmental conditions for hail formation and the improvement of hail forecasting skill. Nevertheless, one of the major limitations for the study of long-term hail variability is the scarce temporal and spatial coverage of hail observations. To overcome this issue, several large-scale meteorological variables and convective indices (from ERA5 reanalysis) are considered to describe hail probability, following the statistical method described in Prein and Holland (2018). The best set of variables to be used as predictors in the hail model has been selected with a machine learning approach, based on a genetic algorithm. The model output is an estimation of the hail probability over Italy in the 1979-2020 period, on a 30×30 km grid which has been used to characterize the seasonality and long-term variability of the hail events and to investigate the potential large-scale drivers of hail storms over Italy.

الفئة