Analyzing and predicting rainfall patterns: A comparative analysis of machine learning models

Abstract

Accurate rainfall prediction is vital for agriculture, water resource management, and disaster preparedness. This study investigates the application of machine learning (ML) models to analyze and predict rainfall patterns in Sokoto, Nigeria. We evaluated four ML techniques - Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) - using historical weather data. The results reveal that SVM outperforms other models, achieving an accuracy of 0.98 and a Kappa statistic of 0.95. Our findings demonstrate the potential of ML models to greatly increase the accuracy of rainfall forecasts, enabling better decision-making and resource management.