Rainfall prediction around Sathanur dam by Naive Bayes classifier, logistic regression models and various classification and regression machine learning techniques

Abstract

Agriculture is the major backbone of Indian economy. India depends mainly on natural rainfall for agriculture. Hence, predicting rainfall becomes very important which could help farmers to take right decision related to agricultural activities. However, at the same time, it is a challenging problem for the meteorological department to accurately predict the rainfall. The present work uses machine learning approach to investigate the prediction of rainfall around Sathanur Dam in Tamil Nadu, India. The rainfall prediction around the Sathanur Dam is carried out using the dam data for the year 2012. The current work considers the four important features namely, Water Level, In-Flow, Out-flow and storage of the dam and their effects in predicting the rainfall. This is accomplished by applying various machine learning classifiers including CART, LDA, CART, KNN, SVM, Naive Bayes, Logistic Regression and Random Forest method. Out of all the classifiers, the CART model gives the highest prediction accuracy which is 86.11%.