Rainfall Prediction to Aid Agriculture by Analysing Rainfall Data Using Ensemble Learning

G. Kalpana, R. Gnanavel, P. Yuvashree, P. Sowndarya and H. Pavithra

Rainfall, owing to its erratic nature at most times, is considered one of the most destructive natural disasters, making it highly complex to model. Hence, extensive research has been conducted on the advancement of rainfall prediction models, focusing mainly on risk reduction, policy reformation suggestions, minimization of the loss of human life, and reduction of the property damage associated with rainfall. The objective of the paper is to aid rainfall prediction for solving the various aforementioned problems by investigating the rainfall dataset of India using ensemble learning method-based techniques. The dataset is first pre-processed to deal with missing values, eliminate duplicate values and such, and then it is subject to various machine learning algorithms to predict the occurrence of rainfall. Finally, the results are analysed by the voting classifier algorithm. Accuracy calculation using the confusion matrix is performed, and a evaluation classification report is generated, to graphically represent the predicted information to the users, on a GUI based application, thus relaying the prediction effectively to the intended audience.

Volume 12 | 04-Special Issue

Pages: 279-283

DOI: 10.5373/JARDCS/V12SP4/20201490