Neural Density Functional Theory of Liquid-Gas Phase Coexistence
Open Access
- 24 January 2025
- journal article
- Published by American Physical Society (APS) in Physical Review X
- Vol. 15 (1)
Abstract
We use supervised machine learning together with the concepts of classical density functional theory to investigate the effects of interparticle attraction on the pair structure, thermodynamics, bulk liquid-gas coexistence, and associated interfacial phenomena in many-body systems. Local learning of the one-body direct correlation functional is based on Monte Carlo simulations of inhomogeneous systems with randomized thermodynamic conditions, randomized planar shapes of the external potential, and randomized box sizes. Focusing on the prototypical Lennard-Jones system, we test predictions of the resulting neural attractive density functional across a broad spectrum of physical behavior associated with liquid-gas phase coexistence in bulk and at interfaces. We analyze the bulk radial distribution function g ( r ) obtained from automatic differentiation and the Ornstein-Zernike route and determine (i) the Fisher-Widom line, i.e., the crossover of the asymptotic (large distance) decay of g ( r ) from monotonic to oscillatory, (ii) the (Widom) line of maximal correlation length, (iii) the line of maximal isothermal compressibility, and (iv) the spinodal by calculating the poles of the structure factor in the complex plane. The bulk binodal and the density profile of the free liquid-gas interface are obtained from density functional minimization and the corresponding surface tension from functional line integration. We also show that the neural functional describes accurately the phenomena of drying at a hard wall and of capillary evaporation for a liquid confined in a slit pore. Our neural framework yields results that improve significantly upon standard mean-field treatments of interparticle attraction. Comparison with independent simulation results demonstrates a consistent picture of phase separation even when restricting the training to supercritical states only. We argue that phase coexistence and its associated signatures can be discovered as emerging phenomena via functional mappings and educated extrapolation.Keywords
All Related Versions
Funding Information
- Leverhulme Trust (EM-2020-029/4)
- Deutsche Forschungsgemeinschaft (551294732, 422127126)
This publication has 84 references indexed in Scilit:
- Classical density functional theory in three dimensions with GPU-accelerated automatic differentiation: Computational performance analysis using the example of adsorption in covalent-organic frameworksChemical Engineering Science, 2024
- Machine Learning of a Density Functional for Anisotropic Patchy ParticlesJournal of Chemical Theory and Computation, 2024
- Perfecting Liquid-State Theories with Machine IntelligenceThe Journal of Physical Chemistry Letters, 2023
- Physics Informed Neural Networks applied to liquid state theoryJournal of Molecular Liquids, 2022
- Toward the Exact Exchange–Correlation Potential: A Three-Dimensional Convolutional Neural Network ConstructThe Journal of Physical Chemistry Letters, 2019
- Machine Learning the Physical Nonlocal Exchange–Correlation Functional of Density-Functional TheoryThe Journal of Physical Chemistry Letters, 2019
- Modeling Molecular Interactions in Water: From Pairwise to Many-Body Potential Energy FunctionsChemical Reviews, 2016
- Molecular simulation of phase coexistence: Finite-size effects and determination of critical parameters for two- and three-dimensional Lennard-Jones fluidsInternational Journal of Thermophysics, 1994
- Equilibrium state of a classical fluid of hard rods in an external fieldJournal of Statistical Physics, 1976
- A uniqueness theorem for fluid pair correlation functionsPhysics Letters A, 1974