The Development and Initial Capabilities of ThunderCast, a Deep-Learning Model for Thunderstorm Nowcasting in the United States

Abstract

Abstract This paper presents the Thunderstorm Nowcasting Tool (ThunderCast), a 24-hour, year round model for predicting the location of convection that is likely to initiate or remain a thunderstorm in the next 0-60 minutes in the continental United States, adapted from existing deep learning convection applications. ThunderCast utilizes a U-Net convolutional neural network for semantic segmentation trained on 320 km by 320 km data patches with four inputs and one target dataset. The inputs are satellite bands from the Geostationary Operational Environmental Satellite (GOES-16) Advanced Baseline Imager (ABI) in the visible, shortwave infrared, and longwave infrared spectrum, and the target is Multi-Radar Multi-Sensor (MRMS) radar reflectivity at the - 10°C isothermin the atmosphere. On a pixel-by-pixel basis, ThunderCast has high accuracy, recall, and specificity but is subject to false positive predictions resulting in low precision. However, the number of false positives decreases when buffering the target values with a 15×15 km centered window indicating ThunderCast’s predictions are useful within a buffered area. To demonstrate the initial prediction capabilities of ThunderCast, three case studies are presented: a mesoscale convective vortex, sea breeze convection, and monsoonal convection in the southwestern United States. The case studies illustrate that the ThunderCast model effectively nowcasts the location of newly initiated and ongoing active convection, within the next 60 minutes, under a variety of geographic and meteorological conditions.