Gibbs-Duhem-Informed Neural Networks for Binary Activity Coefficient Prediction

TL;DR

This paper introduces Gibbs-Duhem-informed neural networks that incorporate thermodynamic consistency directly into training, improving the accuracy and generalization of binary activity coefficient predictions without relying on specific thermodynamic models.

Contribution

It presents a novel method that embeds the Gibbs-Duhem equation into neural network training as a regularizer, enhancing thermodynamic consistency and flexibility over existing hybrid approaches.

Findings

Improved thermodynamic consistency in activity coefficient predictions.

Enhanced generalization capabilities of Gibbs-Duhem-informed models.

Model architecture, especially activation functions, significantly affects prediction quality.

Abstract

We propose Gibbs-Duhem-informed neural networks for the prediction of binary activity coefficients at varying compositions. That is, we include the Gibbs-Duhem equation explicitly in the loss function for training neural networks, which is straightforward in standard machine learning (ML) frameworks enabling automatic differentiation. In contrast to recent hybrid ML approaches, our approach does not rely on embedding a specific thermodynamic model inside the neural network and corresponding prediction limitations. Rather, Gibbs-Duhem consistency serves as regularization, with the flexibility of ML models being preserved. Our results show increased thermodynamic consistency and generalization capabilities for activity coefficient predictions by Gibbs-Duhem-informed graph neural networks and matrix completion methods. We also find that the model architecture, particularly the activation function, can have a strong influence on the prediction quality. The approach can be easily extended to account for other thermodynamic consistency conditions.