DeepEOSNet: Capturing the dependency on thermodynamic state in property prediction tasks

2025-09-21

AI Summary

Thermodynamic properties exhibit strong dependence on state variables (e.g., temperature, pressure, composition), yet existing models lack sufficient expressive power to capture these dependencies accurately. To address this, we propose a dual-channel neural network architecture: a graph neural network (GNN) independently encodes molecular structure, while a multilayer perceptron (MLP) explicitly models state variables; their interaction is realized via dot-product fusion—yielding interpretable, physics-informed integration—and inspired by DeepONet, the model learns state-response functions for end-to-end equation-of-state prediction. This design decouples structural and thermodynamic information, enhancing generalizability. Experiments demonstrate that our method achieves significant improvements over state-of-the-art approaches in vapor pressure prediction, matches performance in mixture molar volume prediction, and exhibits superior extrapolation capability under sparse state-space sampling.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

We propose a machine learning (ML) architecture to better capture the dependency of thermodynamic properties on the independent states. When predicting state-dependent thermodynamic properties, ML models need to account for both molecular structure and the thermodynamic state, described by independent variables, typically temperature, pressure, and composition. Modern molecular ML models typically include state information by adding it to molecular fingerprint vectors or by embedding explicit (semi-empirical) thermodynamic relations. Here, we propose to rather split the information processing on the molecular structure and the dependency on states into two separate network channels: a graph neural network and a multilayer perceptron, whose output is combined by a dot product. We refer to our approach as DeepEOSNet, as this idea is based on the DeepONet architecture [Lu et al. (2021), Nat. Mach. Intell.]: instead of operators, we learn state dependencies, with the possibility to predict equation of states (EOS). We investigate the predictive performance of DeepEOSNet by means of three case studies, which include the prediction of vapor pressure as a function of temperature, and mixture molar volume as a function of composition, temperature, and pressure. Our results show superior performance of DeepEOSNet for predicting vapor pressure and comparable performance for predicting mixture molar volume compared to state-of-research graph-based thermodynamic prediction models from our earlier works. In fact, we see large potential of DeepEOSNet in cases where data is sparse in the state domain and the output function is structurally similar across different molecules. The concept of DeepEOSNet can easily be transferred to other ML architectures in molecular context, and thus provides a viable option for property prediction.

Problem

• Predicting thermodynamic properties dependent on state variables
• Improving machine learning models for molecular property prediction
• Capturing state dependencies using separate neural network channels

Innovation

• Separate network channels for molecular and state data
• Combines graph neural network with multilayer perceptron
• Uses dot product to merge molecular and state information