# Graph Neural Networks embedded into Margules model for vapor-liquid equilibria prediction

arXiv: https://arxiv.org/abs/2502.18998 · HTML: https://mlsanity.com/paper/2502.18998/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 26 Feb 2025.

## Builds on (most cited first, 7 of 7)

- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Gibbs-Duhem-Informed Neural Networks for Binary Activity Coefficient Prediction](https://mlsanity.com/paper/2306.07937/) (2023)
- [HANNA: Hard-constraint Neural Network for Consistent Activity Coefficient Prediction](https://mlsanity.com/paper/2407.18011/) (2024)
- [Gibbs-Helmholtz Graph Neural Network: capturing the temperature dependency of activity coefficients at infinite dilution](https://mlsanity.com/paper/2212.01199/) (2022)
- [Thermodynamics-Consistent Graph Neural Networks](https://mlsanity.com/paper/2407.18372/) (2024)
- [SPT-NRTL: A physics-guided machine learning model to predict thermodynamically consistent activity coefficients](https://mlsanity.com/paper/2209.04135/) (2022)
- [Advancing Thermodynamic Group-Contribution Methods by Machine Learning: UNIFAC 2.0](https://mlsanity.com/paper/2408.05220/) (2024)

## Built on by (most cited first, 2 of 2)

- [DeepEOSNet: Capturing the dependency on thermodynamic state in property prediction tasks](https://mlsanity.com/paper/2509.17018/) (2025)
- [Clapeyron Neural Networks for Single-Species Vapor-Liquid Equilibria](https://mlsanity.com/paper/2602.18313/) (2026)

## Abstract (arXiv)

Predictive thermodynamic models are crucial for the early stages of product and process design. In this paper the performance of Graph Neural Networks (GNNs) embedded into a relatively simple excess Gibbs energy model, the extended Margules model, for predicting vapor-liquid equilibrium is analyzed. By comparing its performance against the established UNIFAC-Dortmund model it has been shown that GNNs embedded in Margules achieves an overall lower accuracy. However, higher accuracy is observed in the case of various types of binary mixtures. Moreover, since group contribution methods, like UNIFAC, are limited due to feasibility of molecular fragmentation or availability of parameters, the GNN in Margules model offers an alternative for VLE estimation. The findings establish a baseline for the predictive accuracy that simple excess Gibbs energy models combined with GNNs trained solely on infinite dilution data can achieve.