A Rough Set Theory Based Rule Generation Method for Local Lightning Prediction using Now Casting and Other Local Measurements

To predict the probability of local lightning strike is always a challenging task. Several factors affect the performance of the existing tools including proper learning of the local weather model. The present work proposes a Rough Set Theory (RST) based rule generation method based on local weather data and now casting. The proposed model is able to learn the local weather model and to update its rule set to improve its prediction performance. The results show promising trend in the local lightning probability prediction and hence the present method may be considered for further exploration to improve the accuracy.