ClimateXAI: An Explainable Hybrid Deep Learning Framework For Climate Trend Analysis And Extreme Weather Prediction

Climate change has significantly increased the occurrence of extreme weather events such as floods, cyclones, droughts, heatwaves, and heavy rainfall, creating a strong need for accurate and reliable forecasting systems. Traditional climate prediction methods often fail to effectively capture the complex spatial and temporal relationships present in large-scale climate data and generally lack interpretability. This project proposes an Explainable Hybrid Deep Learning Framework for Climate Trend Analysis and Extreme Weather Prediction that integrates Convolutional Neural Networks (CNN) for spatial feature extraction, Long Short-Term Memory (LSTM) networks for temporal sequence learning, and an Attention Mechanism for identifying important climatic features. To enhance transparency and trustworthiness, Explainable Artificial Intelligence (XAI) techniques such as SHAP and Grad-CAM are incorporated into the framework. The system utilizes climate parameters including temperature, humidity, rainfall, wind speed, atmospheric pressure, cloud cover, and satellite imagery collected from multiple sources. Data preprocessing techniques such as normalization, missing value handling, and feature engineering are applied to improve data quality and model performance. The hybrid CNN-LSTM architecture effectively learns spatiotemporal climate patterns, enabling accurate climate trend analysis and extreme weather forecasting. Experimental results demonstrate improved prediction accuracy, reduced false alarm rates, and better interpretability compared to traditional forecasting approaches. The proposed framework supports real-time climate monitoring and provides reliable, transparent, and efficient forecasting solutions for disaster management, agriculture, environmental monitoring, and public safety applications.