Environmental Sustainability through AI: A Case Study on CO2 Emission Prediction

In this study, the Biogeography-Based Optimization (BBO) algorithm was effectively utilized to predict carbon dioxide (CO2) emissions. In the context of combating global warming and climate change, making accurate and reliable CO2 emission predictions is critically important for developing environmental policies and strategies. Accordingly, the motivation for our study is to contribute to environmental decision-making processes by improving the accuracy of CO2 emission predictions. BBO is a nature-inspired optimization method used to analyze complex relationships and identify significant features within a dataset. The focus of the study is to accurately predict the “share_global_coal_co2” parameter, and for this purpose, the BBO algorithm was employed to identify the 20 most influential features. The analyses revealed that the Gradient Boosting algorithm provided the lowest Mean Squared Error (MSE) value of 0.347408, indicating that the model can make predictions closer to the actual data. Additionally, the use of interpretable artificial intelligence models such as SHAP and LIME made the model’s predictions more understandable and clearly demonstrated the impact of specific features on the predictions. The results obtained provide significant guidance for environmental policymakers and energy experts. The effectiveness of the BBO algorithm in predicting CO2 emissions can contribute to more informed and data-driven decisions in environmental analysis and policy-making processes. This study emphasizes the importance of artificial intelligence and optimization techniques in achieving sustainability goals and helps develop more effective strategies in environmental management.