Optimizing Solar Radiation Prediction in Arid Climates Using Ensemble Machine Learning Technique

This project focuses on the prediction of solar radiation using machine learning techniques. The goal is to predict Diffuse Horizontal Irradiance (DHI) from meteorological data, including temperature, humidity, wind speed, and pressure. The model uses algorithms such as XGBoost, Random Forest, and Stacking Classifier to improve prediction accuracy. The data consists of historical solar radiation values, which are processed, cleaned, and used for training the model. The project aims to provide accurate predictions for solar radiation, which are important for energy forecasting and climate modeling. The performance of the models is evaluated using key metrics such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R² score. The proposed system provides a user-friendly interface for easy interaction, where users can upload input data, view predictions, and analyze historical trends.

Keywords: Solar radiation, Diffuse Horizontal Irradiance, XGBoost, Random Forest, Stacking Classifier, temperature, humidity, wind speed, energy forecasting, climate modeling.