Lightning prediction using an ensemble learning approach for northeast of Iran.

This paper examines some data mining techniques for lightning prediction. If we indicate by one the lightning event occurrence and by zero the non-occurrence of the event, then we will have a binary classification problem. In some cases, the dataset of lightning event is class imbalance. Thus, in the current research, the method of undersampling will be employed to generate several balanced datasets. Two binary classification algorithms, including neural networks and decision tree, were examined for lightning prediction. Furthermore, their performance was evaluated and compared. The proposed method was applied for some selected regions in Iran. Based on the evaluation results, decision tree outperforms feed-forward neural networks with one hidden layer for all datasets. • Lightning prediction considered as a binary classification problem. • Lightning dataset in this study is an imbalance dataset. • Under-bagging algorithm was applied for classification. [ABSTRACT FROM AUTHOR]