A White-Box AI Framework for Interpretable Global Warming Potential Prediction

Accurate yet interpretable prediction of Global Warming Potential (GWP) is essential for the sustainable design of chemical products and processes. However, existing studies that utilize molecular structure and physicochemical properties for GWP prediction often suffer from low interpretability, relying on black-box models that obscure the underlying relationships between molecular descriptors and environmental impact. To address this limitation, this study employs a Kolmogorov�Arnold Network (KAN) to derive symbolic equations that establish explicit relationships between molecular properties and GWP. By extracting interpretable mathematical expressions, our approach provides a transparent foundation for decision-making in chemical processes and reaction development. Our comparative analysis of machine learning models�including Random Forest, XGBoost, Deep Neural Networks (DNN), and KAN�reveals that Mordred descriptors outperform MACCS keys in GWP prediction, emphasizing the importance of physicochemical properties. The proposed KAN model achieves predictive accuracy comparable to conventional deep learning methods while maintaining interpretability, facilitating data-driven and transparent sustainability assessments in the chemical industry.