PUFFIN: A Path-Unifying Feed-Forward Interfaced Network for Vapor Pressure Prediction
This work addresses the need for accurate vapor pressure predictions in industrial and environmental applications, offering a partially interpretable solution that can be integrated into process design software, though it is incremental as it builds on existing machine learning techniques with domain-specific adaptations.
The authors tackled the problem of predicting vapor pressure for chemical compounds, which is resource-intensive to measure experimentally, by proposing PUFFIN, a machine learning framework that incorporates domain knowledge and transfer learning to improve prediction accuracy, outperforming alternative methods.
Accurately predicting vapor pressure is vital for various industrial and environmental applications. However, obtaining accurate measurements for all compounds of interest is not possible due to the resource and labor intensity of experiments. The demand for resources and labor further multiplies when a temperature-dependent relationship for predicting vapor pressure is desired. In this paper, we propose PUFFIN (Path-Unifying Feed-Forward Interfaced Network), a machine learning framework that combines transfer learning with a new inductive bias node inspired by domain knowledge (the Antoine equation) to improve vapor pressure prediction. By leveraging inductive bias and transfer learning using graph embeddings, PUFFIN outperforms alternative strategies that do not use inductive bias or that use generic descriptors of compounds. The framework's incorporation of domain-specific knowledge to overcome the limitation of poor data availability shows its potential for broader applications in chemical compound analysis, including the prediction of other physicochemical properties. Importantly, our proposed machine learning framework is partially interpretable, because the inductive Antoine node yields network-derived Antoine equation coefficients. It would then be possible to directly incorporate the obtained analytical expression in process design software for better prediction and control of processes occurring in industry and the environment.