Improved Prediction Analysis with Hybrid Models for Thunderstorm Classification over the Ranchi Region

Thunderstorms are natural disasters that impact people, animals, and the economy. Thunderstorms’ detrimental repercussions can be avoided by identifying their occurrence in advance. The current work, in this respect, uses soft computing techniques such as K-Nearest Neighbour (KNN), Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM) with various kernel functions to categorize the occurrence of thunderstorms over Ranchi, India. These techniques were trained and tested using two data sets: daily average and hourly meteorological datasets. The primary purpose of this study is to find which dataset-classifier combination is optimal for categorizing thunderstorm occurrence in Ranchi. No classifier was found to adequately classify either the Day Average Dataset or the Modified Day Average Dataset. On the other hand, the Hourly Dataset was found to be more balanced in terms of the number of thunderstorms that occurred than the Day Average and Modified Average datasets. The F-Score value of the incidence of thunderstorm incidents after using different classifiers was used to compare the outcomes of these datasets. The results reveal that using SVM with radial basis function. The Hourly Dataset is the best for thunderstorm day classification. For the overall and only incidence of thunderstorms classes, SVM-RBF gets 0.81 and 0.74 F-Scores, respectively. Other approaches, like grid search and Bagging, have been used to increase SVM-RBF performance. Grid search and Bagging are used on SVM-RBF to produce a hybrid Grid-Bag-SVM-RBF classifier with 82.04% accuracy and F-scores of 0.83 and 0.78 for overall and just thunderstorm occurrence, respectively.