Leveraging Machine Learning Models for Climate Data Interpretation and Forecasting

Climate change poses significant challenges for ecosystems, agriculture, and societal resilience, driven by rising global temperatures and shifting climate patterns. This work leverages historical climate data from the Berkeley Earth Surface Temperature repository to analyze and predict global warming trends using machine learning techniques. Key features such as temporal components (Year, Month) and spatial coordinates (Latitude, Longitude) are processed to train four machine learning algorithms: Linear Regression, Random Forest, Support Vector Regression (SVR), and K-Nearest Neighbor (KNN). Among these, the Random Forest Regressor demonstrated the highest predictive accuracy with an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> score of 0.9857, followed closely by KNN at 0.9706. These results underscore the capability of machine learning to uncover meaningful trends in climate data and enhance our understanding of global warming, enabling more informed analyses of its impacts.