A KAN-based interpretable framework for prediction of global warming potential across chemical space

Abstract

Accurate yet interpretable prediction of Global Warming Potential (GWP) is essential for the sustainable design of novel molecules, chemical processes and materials. This capability is valuable in the early-stage screening of compounds with potential relevance to carbon management and emerging CCUS applications. However, conventional models often face a trade-off between predictive accuracy and interpretability. In this study, we propose an AI-based GWP prediction framework that integrates both molecular and process-level features to improve accuracy while employing white-box modeling techniques to enhance interpretability. First, by incorporating molecular descriptors (MACCS keys, Mordred descriptors) and process-level information (process title, description, location), the Deep Neural Network (DNN) model achieved an R² of 86 % on the test data, representing a 25 % improvement over the most comparable benchmark reported in prior studies. XAI analysis further highlights the crucial role of process-related features, particularly process title embeddings, in enhancing model predictions. Second, to address the need for model transparency, we employed a Kolmogorov–Arnold Network (KAN) model to develop a symbolic, white-box GWP prediction model. While achieving a lower R² of 64 %, this model provides explicit mathematical representations of GWP relationships, enabling interpretable decision-making in sustainable chemical and process design. Our findings demonstrate that integrating molecular and process-level features improves both predictive accuracy and interpretability in GWP modelling. The resulting framework can support early-stage environmental assessment of novel compounds, offering a useful tool to inform the sustainable design of chemicals, including those with potential applications in CCUS.