Application of Machine Learning and Remote Sensing Techniques for Forecasting of Rainfall in Nigeria: From the Perspective of Improved Accuracy

The accuracy of rainfall prediction in Nigeria is significantly enhanced through the application of machine learning models. This study employs a comprehensive approach that integrates historical meteorological data with satellite imagery data, utilizing a variety of machine learning models, including Linear Regression, LSTM, Random Forest, XGBoost, SVR, Lasso Regression, and ElasticNet Regression. It evaluates the performance of each model using key metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2). The findings highlight the effectiveness of ensemble techniques, particularly Random Forest and XGBoost, highlighting their superior accuracy in capturing the complex patterns inherent in rainfall data. Additionally, the temporal data-capturing capabilities of LSTM networks further contribute to the overall accuracy of the prediction models.