Facial Recognition Technique Could Improve Hail Forecasts

The same artificial intelligence method used in facial recognition systems could help improve the prediction of hailstorms and their severity, according to researchers at the National Center for Atmospheric Research. National Center for Atmospheric Research (NCAR) researchers have found that the same artificial intelligence method used in facial recognition systems could help improve the prediction of hailstorms and their severity. The researchers used machine learning to train a convolutional neural network to recognize features of individual storms that affect the formation of hail. The model was trained on images of simulated storms, along with information about temperature, pressure, wind speed, and direction. Once trained, the model was able to determine which features of the storm correlate with whether or not it will hail, and how big the hailstones are likely to be.