Thunderstorms pose a major hazard to society and economy, which calls for reliable thunderstorm forecasts. In this work, we introduce a Signature-based Approach of identifying Lightning Activity using MAchine learning (SALAMA), a feedforward neural network model for identifying thunderstorm occurrence in numerical weather prediction (NWP) data. The model is trained on convection-resolving ensemble forecasts over Central Europe and lightning observations. Given only a set of pixel-wise input parameters that are extracted from NWP data and related to thunderstorm development, SALAMA infers the probability of thunderstorm occurrence in a reliably calibrated manner. For lead times up to eleven hours, we find a forecast skill superior to classification based only on NWP reflectivity. Varying the spatiotemporal criteria by which we associate lightning observations with NWP data, we show that the time scale for skillful thunderstorm predictions increases linearly with the spatial scale of the forecast.
@article{arxiv.2303.08736,
title = {A machine-learning approach to thunderstorm forecasting through post-processing of simulation data},
author = {Kianusch Vahid Yousefnia and Tobias Bölle and Isabella Zöbisch and Thomas Gerz},
journal= {arXiv preprint arXiv:2303.08736},
year = {2024}
}
Comments
19 pages, 11 figures, 3 tables. Submitted to Quarterly Journal of the Royal Meteorological Society; v3: More thorough explanation of our use of ensemble data, improved performance of SALAMA in reliability diagrams; v2: Consideration of additional skill scores and more competitive baseline model, and novel visualization of reliability and resolution as a function of model probability