Predicting Rainfall Using AI: A Comparative Study of Machine Learning Models
Keywords:
Rainfall Prediction, Machine Learning, Artificial Intelligence, Decision Trees, Support , Vector MachineAbstract
Accurate rainfall prediction is essential for agriculture, disaster management, and water resource planning. Traditional meteorological models often struggle to capture the complex, nonlinear patterns of rainfall, leading to unreliable forecasts. This study explores the potential of Artificial Intelligence (AI) in enhancing rainfall prediction through a comparative analysis of various machine learning models, including XGBoost, Random Forest and Support Vector Machines. Using historical weather datasets, we assess the performance of these models based on key metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and prediction consistency. Our results show that AIbased methods can predict rainfall more accurately than traditional approaches. Among them, deep learning models perform the best, as they can better understand complex weather patterns. This study helps highlight which AI techniques work well for rainfall prediction, contributing to more reliable and data-driven weather forecasting.
DOI: https://doi.org/10.24321/2455.3190.202505
References
Zhang H, Liu Y, Zhang C, Li N. Machine learning methods for weather forecasting: A survey. Atmosphere. 2025 Jan 14;16(1):82. Liu Y, Duffy K, Dy JG, Ganguly AR. Explainable deep learning for insights in El Niño and river flows. Nature Communications. 2023 Jan 20;14(1):339.
Yeshwanth M, Kumar PR, Mathivanan G. Comparative study of machine learning algorithms for rainfall prediction. IJTSRD. 2019;3(3):677-81.
