Improved Temperature Trend Forecasting in Major Pakistani Cities Using XGBoost and other Ensemble Machine Learning Models

This study employs advanced machine learning algorithms Random Forest, Gradient Boosting Machines (GBM), and XGBoost to predict normalized temperatures in major Pakistani cities, focusing on Lahore. Using a comprehensive dataset divided into training and testing subsets, model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). Results show that XGBoost excelled with the lowest RMSE (0.0281), MAE (0.0219), and highest R² (0.9879), demonstrating superior predictive accuracy. Gradient Boosting and Random Forest also performed well, confirming the efficacy of ensemble methods for temperature forecasting. This study highlights the potential of machine learning in environmental analysis, offering a scalable framework for climate predictions and informed urban planning.