Thermodynamically consistent machine learning model for excess Gibbs energy

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hoffmann, Marco, Specht, Thomas, Göttl, Quirin, Burger, Jakob, Mandt, Stephan, Hasse, Hans, Jirasek, Fabian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911627403591680
author Hoffmann, Marco
Specht, Thomas
Göttl, Quirin
Burger, Jakob
Mandt, Stephan
Hasse, Hans
Jirasek, Fabian
author_facet Hoffmann, Marco
Specht, Thomas
Göttl, Quirin
Burger, Jakob
Mandt, Stephan
Hasse, Hans
Jirasek, Fabian
contents The excess Gibbs energy plays a central role in chemical engineering and chemistry, providing a basis for modeling thermodynamic properties of liquid mixtures. Predicting the excess Gibbs energy of multi-component mixtures solely from molecular structures is a long-standing challenge. We address this challenge with HANNA, a flexible machine learning model for excess Gibbs energy that integrates physical laws as hard constraints, guaranteeing thermodynamically consistent predictions. HANNA is trained on experimental data for vapor-liquid equilibria, liquid-liquid equilibria, activity coefficients at infinite dilution and excess enthalpies in binary mixtures. The end-to-end training on liquid-liquid equilibrium data is facilitated by a surrogate solver. A geometric projection method enables robust extrapolations to multi-component mixtures. We demonstrate that HANNA delivers accurate predictions, while providing a substantially broader domain of applicability than state-of-the-art benchmark methods. The trained model and corresponding code are openly available, and an interactive interface is provided on our website, MLPROP.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06484
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Thermodynamically consistent machine learning model for excess Gibbs energy
Hoffmann, Marco
Specht, Thomas
Göttl, Quirin
Burger, Jakob
Mandt, Stephan
Hasse, Hans
Jirasek, Fabian
Machine Learning
Computational Engineering, Finance, and Science
The excess Gibbs energy plays a central role in chemical engineering and chemistry, providing a basis for modeling thermodynamic properties of liquid mixtures. Predicting the excess Gibbs energy of multi-component mixtures solely from molecular structures is a long-standing challenge. We address this challenge with HANNA, a flexible machine learning model for excess Gibbs energy that integrates physical laws as hard constraints, guaranteeing thermodynamically consistent predictions. HANNA is trained on experimental data for vapor-liquid equilibria, liquid-liquid equilibria, activity coefficients at infinite dilution and excess enthalpies in binary mixtures. The end-to-end training on liquid-liquid equilibrium data is facilitated by a surrogate solver. A geometric projection method enables robust extrapolations to multi-component mixtures. We demonstrate that HANNA delivers accurate predictions, while providing a substantially broader domain of applicability than state-of-the-art benchmark methods. The trained model and corresponding code are openly available, and an interactive interface is provided on our website, MLPROP.
title Thermodynamically consistent machine learning model for excess Gibbs energy
topic Machine Learning
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2509.06484