P4.1
Using artificial intelligence to predict Mississippi lightning

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner
Tuesday, 12 October 2010
Using artificial intelligence to predict Mississippi lightning
Grand Mesa Ballroom ABC (Hyatt Regency Tech Center)
Andrew Edward Mercer, Mississippi State University, Mississippi State, MS; and M. E. Brown and C. Babineaux

Thunderstorms are a common occurrence in Mississippi in the late summer and fall months, but the lightning strikes associated with these storms are difficult to predict. According to the National Weather Service, cloud to ground lightning strikes are the second most deadly weather phenomenon nation-wide, killing up to 58 people per year. However, current lightning threat forecasts are limited to output from numerical weather prediction simulations. This method of lightning threat assessment is not useful when determining ground lightning threat, since the model is incapable of resolving lightning strikes and instead predicts the threat for thunderstorm activity.

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.