Analysis of Machine Learning Algorithms for Prediction of Short-Term Rainfall Amounts Using Uganda’s Lake Victoria Basin Weather Dataset

This study presents a Lake Victoria Basin weather dataset and conducts rigorous analysis of machine learning algorithms for short-term rainfall prediction. The research validates the dataset using various regression models including Random Forest, Support Vector, Neural Network, LASSO, Gradient boosting, and Extreme Gradient boosting regression. Performance evaluation using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) shows that Extreme Gradient Boost regression achieves the lowest MAE values of 0.006, 0.018, 0.005 for Uganda, Kenya, and Tanzania respectively. The work addresses limitations of existing numerical weather prediction models in precipitation forecasting.