Earth warming forecasting through artificial intelligence techniques

Earth warming is increasingly taking place due to the population and buildings expansion which increased the total pollution. This study investigates the classification of weather status using the Climate Change. Dataset manifested by Earth Surface Temperature Data from Kaggle, which encompasses over 150 years of global surface temperature records. The primary aim is to develop predictive models that can accurately forecast weather conditions. This forecasting is based on historical temperature patterns, thereby aiding climate management efforts. Four algorithms were deployed in regard of classifying the dataset namely Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting (XGBoost). Utilizing a 10-fold cross-validation approach, we evaluated each model\'s performance based on accuracy, precision, recall, F1-score, and ROC-AUC. Our findings reveal that XGBoost significantly outperformed the other. XGBoost algorithms, achieving an impressive accuracy of 88%, with good precision score. After applying the aforementioned algorithms, results are calculated and prepared for stating the conclusion. Results demonstrate the potential of advanced machine learning techniques in effectively classifying weather statuses and highlight the importance of data-driven approaches in addressing the challenges posed by climate change. This study underscores the relevance of historical climate data in enhancing predictive capabilities, ultimately contributing to improved climate resilience and decision- making.