Extreme Learning Machine for the Classification of Rainfall and Thunderstorm

Forecasting rainfall and thunderstorm is one of the important requirements for planning and management of many applications, including, agriculture, flood and traffic. Considering the relevance and importance of the study, this research study aims at classification of rainfall and thunderstorm. There are various classifiers available but not limited to, Support Vector Machine (SVM), Artificial Neural Network (ANN), K-Nearest Neighbourhood classier (KNN), Adaboost, etc. Recently Dr. G.B. Huang suggested and proposed an efficient classifier based on single layer feedforward Neural Network called as Extreme Learning Machine (ELM) which is extremely powerful to be an Universal classifier. Hence, this study focuses on the classification of rainfall and thunderstorm. The results of the classification using ELM show a classification accuracy of 87.69% which is much better when compared to the results of other classifiers, namely, SVM and ANN. Hence, ELM can be considered as a good classifier for the classification of rainfall and thunderstorm.