A postdoctoral researcher at the US National Center for Atmospheric Research (NCAR) developed a simple convolutional neural network model to predict hailstorms. The researcher trained the model on 82,000 storm profiles and tested it on 32,000 storms. It was accurate 88 percent of the time. While this neural net is currently a proof of concept, its accuracy shows promise, piquing the interest of other meteorologists.
Photo Found Here: https://pixabay.com/en/hailstone-storm-highveld-1614239/