Differentiable Thermodynamic Phase-Equilibria for Machine Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hicham, Karim K. Ben, Ascani, Moreno, Rittig, Jan G., Mitsos, Alexander
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917346789031936
author Hicham, Karim K. Ben
Ascani, Moreno
Rittig, Jan G.
Mitsos, Alexander
author_facet Hicham, Karim K. Ben
Ascani, Moreno
Rittig, Jan G.
Mitsos, Alexander
contents Accurate prediction of phase equilibria remains a central challenge in chemical engineering. Physics-consistent machine learning methods that incorporate thermodynamic structure into neural networks have recently shown strong performance for activity-coefficient modeling. However, extending such approaches to equilibrium data arising from an extremum principle, such as liquid-liquid equilibria, remains difficult. Here we present DISCOMAX, a differentiable algorithm for phase-equilibrium calculation that guarantees thermodynamic consistency at both training and inference, only subject to a user-specified discretization. The method is rooted in statistical thermodynamics, and works via a discrete enumeration with subsequent masked softmax aggregation of feasible states, and together with a straight-through gradient estimator to enable physics-consistent end-to-end learning of neural $g^{E}$-models. We evaluate the approach on binary liquid-liquid equilibrium data and demonstrate that it outperforms existing surrogate-based methods, while offering a general framework for learning from different kinds of equilibrium data.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11249
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differentiable Thermodynamic Phase-Equilibria for Machine Learning
Hicham, Karim K. Ben
Ascani, Moreno
Rittig, Jan G.
Mitsos, Alexander
Machine Learning
Accurate prediction of phase equilibria remains a central challenge in chemical engineering. Physics-consistent machine learning methods that incorporate thermodynamic structure into neural networks have recently shown strong performance for activity-coefficient modeling. However, extending such approaches to equilibrium data arising from an extremum principle, such as liquid-liquid equilibria, remains difficult. Here we present DISCOMAX, a differentiable algorithm for phase-equilibrium calculation that guarantees thermodynamic consistency at both training and inference, only subject to a user-specified discretization. The method is rooted in statistical thermodynamics, and works via a discrete enumeration with subsequent masked softmax aggregation of feasible states, and together with a straight-through gradient estimator to enable physics-consistent end-to-end learning of neural $g^{E}$-models. We evaluate the approach on binary liquid-liquid equilibrium data and demonstrate that it outperforms existing surrogate-based methods, while offering a general framework for learning from different kinds of equilibrium data.
title Differentiable Thermodynamic Phase-Equilibria for Machine Learning
topic Machine Learning
url https://arxiv.org/abs/2603.11249