Assessing the Limits of Graph Neural Networks for Vapor-Liquid Equilibrium Prediction: A Cryogenic Mixture Case Study
This work addresses the need for fast thermophysical models in cryogenic mixture design and optimization, but it is incremental as it highlights limitations of current GNN approaches rather than achieving a breakthrough.
This study investigated whether a graph neural network (GNN) could serve as a practical surrogate for vapor-liquid equilibrium (VLE) predictions in cryogenic mixtures, but found that the GNN failed to produce acceptable equilibria and offered no runtime advantage, with single-phase interpolation taking tens of milliseconds compared to sub-millisecond for existing methods.
Accurate and fast thermophysical models are needed to embed vapor-liquid equilibrium (VLE) calculations in design, optimization, and control loops for cryogenic mixtures. This study asks whether a structure-aware graph neural network (GNN; DimeNet++) trained on GERG-2008/CoolProp data can act as a practical surrogate for an equation of state (EoS). We generate a ternary dataset over 90-200 K and pressures to 100 bar, curate it with a 15% density filter (reducing 5,200 states to 1,516), and pair each state with a lightweight molecular-dynamics snapshot to supply structural features. The model is trained in two stages; pretraining on residual Helmholtz energy followed by pressure fine-tuning with a stability penalty; and evaluated via single-phase interpolation tests, solver-free derivative-quality diagnostics, an audited VLE driver, and a latency benchmark. Within its regime, the GNN interpolates single-phase properties reasonably well; however, the VLE driver accepts no GNN equilibria on tested binaries (all plotted VLE points are CoolProp fallback or the solver fails), and diagnostic probes reveal jagged P(V|T) paths and thermal-stability flags concentrated in dense/cold regions, indicating insufficient derivative smoothness/consistency for robust equilibrium solving. An end-to-end timing comparison shows no single-phase speed advantage relative to CoolProp (tens of milliseconds vs sub-millisecond). We conclude that, as configured, the surrogate in this study is not solver-ready for VLE and offers no runtime benefit; its value is methodological, delineating failure modes and pointing to remedies such as physics-informed training signals and targeted coverage near phase boundaries.