Machine Learning of consistent thermodynamic models using automatic differentiation

TL;DR

This paper introduces a neural network-based method that uses automatic differentiation to learn thermodynamic equations of state directly from data, ensuring consistency and accuracy in modeling complex systems.

Contribution

It presents a novel approach combining neural networks and automatic differentiation to model free energy and derive thermodynamic properties, preserving Maxwell relations.

Findings

Outperforms direct property learning in accuracy

Ensures thermodynamic consistency via Maxwell relations

Implicitly computes free energy without explicit integration

Abstract

We propose a data-driven method to describe consistent equations of state (EOS) for arbitrary systems. Complex EOS are traditionally obtained by fitting suitable analytical expressions to thermophysical data. A key aspect of EOS are that the relationships between state variables are given by derivatives of the system free energy. In this work, we model the free energy with an artificial neural network, and utilize automatic differentiation to directly learn the derivatives of the free energy. We demonstrate this approach on two different systems, the analytic van der Waals EOS, and published data for the Lennard-Jones fluid, and show that it is advantageous over direct learning of thermodynamic properties (i.e. not as derivatives of the free energy, but as independent properties), in terms of both accuracy and the exact preservation of the Maxwell relations. Furthermore, the method implicitly provides the free energy of a system without explicit integration.