A Deep Learning Model of Lightning Stroke Density

Abstract Lightning plays a crucial role in the Earth's climate system; however, existing parameterizations for use in forecasting and earth system models show room for improvement in capturing spatial and temporal variations in its frequency. This study develops deep learning‐based parameterizations of lightning stroke density using meteorological variables from the ERA and IMERG data sets. Convolutional neural networks (CNNs) with U‐Net architectures are trained using World Wide Lightning Location Network (WWLLN) data from 2010 to 2021 and evaluated on WWLLN lightning observations from 2022 to 2023. Compared to the multiplicative product of CAPE and precipitation, the CNNs reduce the average domain mean bias by an order of magnitude and produce significantly higher Fractions Skill Score (FSS) values across all lightning regimes. The CNNs show skill relative to previously published parameterizations over the oceans especially, with r 2 values as high as 0.92 achieved between the best‐performing CNN‐produced climatology in this study and observed lightning stroke density climatology. The CNNs are also able to accurately capture the 12‐hourly evolution of lightning spatial patterns on an event‐by‐event basis with high skill. These results show the potential for deep learning to improve lightning parameterizations in weather and earth system models.