Predicting Diffusion Coefficients of Binary and Ternary Supercritical Water Mixtures via Machine and Transfer Learning with Deep Neural Network

Prediction for diffusion coefficients of multi-component supercritical water (SCW) mixtures is crucial for the system design and industrial application of SCW-related technologies, such as SCW gasification and oxidation. In this work, machine learning (ML) and transfer learning (TL) techniques with deep neural network (DNN) are explored to predict diffusion coefficients of binary and ternary SCW mixtures. Initially, diffusion coefficients are calculated through molecular dynamics (MD) simulations. Then, the structure of DNN is found and examined with a cross-validation method so that an accurate predictive ML model is trained with our database for diffusion coefficients of binary SCW mixtures. Finally, TL is used to train a DNN model for diffusion coefficients of ternary mixtures where the knowledge learned from the pretrained DNN model for binary mixtures is transferred to improve the model performance with minimal training data. Compared to the model trained from scratch (non-TL), the TL model reduces the mean squared error by 89% and proves its possibility for industrial and engineering applications. It indicates the advantage of ML and TL methods over empirical equations when the priority is to predict diffusion coefficients of multicomponent mixtures without complex and tedious MD simulations.

Automated summary

In this study, machine learning and transfer learning techniques with deep neural networks were explored to predict diffusion coefficients of multi-component supercritical water mixtures. Diffusion coefficients were initially calculated using molecular dynamics simulations, and a cross-validation method was used to find an accurate predictive model. Transfer learning was then applied to improve the model performance for ternary mixtures, based on the knowledge learned from the pretrained model for binary mixtures.