Using artificial intelligence to predict Mississippi lightning
In order to improve lightning threat assessment for Mississippi, a support vector machine lightning detection algorithm is under development. The algorithm uses several common thunderstorm forecast parameters (i.e. surface dewpoint, CAPE, CIN, surface divergence, etc.) from Weather and Research Forecasting model simulations of 30 different fall thunderstorm and non-thunderstorm days in Mississippi. This output, combined with data from the National Lightning Detection Network, is used to train a support vector machine classification algorithm. Individual probabilities of cloud-to-ground lightning strikes within a kilometer of each grid point for all of Mississippi are computed, resulting in a spatial probability of cloud-to-ground lightning strikes.
Initial results are promising, as the algorithm generally portrays lightning threats in areas of heavy daily lightning activity up to 12 hours prior to the event. More cases and integration of additional data sources will be conducted in future work.