Comparative Analysis of Machine Learning Models for Weather Forecasting: A Heathrow Case Study

Abstract

Accurate weather forecasting, especially temperature prediction, is fundamental for various segments within the UK, including agriculture, energy, and policy planning, as the nation adapts to the effects of climate change. This study addresses the limitations of conventional linear models in capturing the complex, non-linear relationships within meteorological data by comparing the effectiveness of different Machine Learning (ML) strategies. This study evaluates the performance of baseline ML models, such as Linear Regression (LR), Support Vector Regression (SVR), and K-Nearest Neighbors (KNN). It also examines advanced ensemble and boosting models such as Decision Tree (DT), Random Forest (RF), XGBoost (XGB), LightGBM (LGBM), and CatBoost, using a comprehensive dataset from Heathrow Airport. Detailed preprocessing, model training, and optimization through cross-validation were conducted, with performance assessed using Mean Squared Error (MSE) and Coefficient of Determination (R²) metrics. The results demonstrate that ensemble methods, particularly XGB and LGBM, offer superior predictive accuracy for weather forecasting tasks, highlighting their potential to enhance predictive models in meteorological applications.