Implementation of Hyperparameter Tuning of CATBoost Regressor Model for Climate Change Detection

Climate change will impact everyone. From more extreme weather to rising food prices, recreation, and reduced opportunities to appreciate nature, people everywhere will feel the impact. This study aims to develop and compare climate change prediction models with the CATBoost Regressor model. The dataset used includes historical climate data such as air temperature, greenhouse gas concentrations, and other atmospheric parameters. The research methods include data understanding, preprocessing, dataset sharing, modeling, model evaluation, and result analysis. The results show that the accuracy of the CATBoost Regressor is better than the XGBoost Regressor and Random Forest Regressor and provides the best performance with a Root Mean Squared Error (RMSE) of 0.0559.