Rainfall prediction is a crucial task in weather forecasting, with significant applications in agriculture, disaster management, and environmental planning. This work focuses on classifying rainfall occurrence using a structured meteorological dataset containing parameters such as temperature, humidity, atmospheric pressure, wind speed, and cloud cover. A variety of machine learning and deep learning models were explored, including Random Forest (RF), XGBoost, Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). To enhance predictive performance, ensemble strategies like stacking and voting classifiers were employed. Transfer learning techniques were integrated to improve model generalization and training efficiency. Explainable AI methods such as SHAP and LIME were used to provide transparency into model decision-making. The final ensemble model demonstrated high accuracy and interpretability, making it well-suited for real-world rainfall prediction applications.

Keywords: Rainfall Prediction, Ensemble Learning, Transfer Learning, Voting Classifier, Stacking Classifier, CNN, LSTM, GRU, Random Forest, XGBoost, SHAP, LIME, Explainable AI, Meteorological Data, Deep Learning.