Performance Comparison of Various Machine Learning Models for Rainfall Prediction Using Wind Information

Abstract

Forecasting rainfall, crucial for agriculture, water management, and disaster preparedness, presents significant challenges due to intricate relationships often missed by conventional statistical methods. Hence, machine learning (ML) models offer promising alternatives, enhancing the precision and dependability of rainfall predictions. This paper presents a comprehensive comparison of various ML models with diverse model structures and regularization strategies for rainfall prediction in urban metropolitan cities. The results show that the random forest model, and gradient boosting model outperform the other models such as logistic regression, support vector machine (SVM), decision tree, K-nearest neighbor (KNN), Naive Bayes, linear SVM, and neural network in terms of accuracy. Validation accuracies of 75%, 77%, 68%, 78%, 76%, 78%, 74%, 75% and 76% were achieved for logistic regression, SVM, decision tree, random forest model, KNN, gradient boosting model, Naive Bayes, linear SVM, and neural network, respectively. The choice of ML models for rainfall prediction should consider the characteristics of the data, e.g. a lag feature for 20 days was employed that uses previous time steps to predict the next time step. The paper concludes that ML models, especially the random forest and gradient boosting models are powerful and robust tools for rainfall prediction in urban metropolitan cities. Key Words: rainfall prediction, wind information, machine learning, gradient boosting, random forest