Learning the bulk and interfacial physics of liquid-liquid phase separation with neural density functionals.

We use simulation-based supervised machine learning and classical density functional theory to investigate bulk and interfacial phenomena associated with phase coexistence in binary mixtures. For a prototypical symmetrical Lennard-Jones mixture, our trained neural density functional yields accurate liquid-liquid and liquid-vapor binodals together with predictions for the variation of the associated interfacial tensions across the entire fluid phase diagram. From the latter, we determine the contact angles at fluid-fluid interfaces along the line of triple-phase coexistence and confirm that there can be no wetting transition in this symmetrical mixture.

• Publication year

  2025

• Venue

  Journal of Chemical Physics

• Publication date

  2025-07-11

• Fields of study

  Medicine, Physics, Chemistry, Computer Science

• Identifiers
  DOI 10.1063/5.0290261arXiv 2507.08395PMID 41123133
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Neural density functional theory in higher dimensions with convolutional layers.

  2025cited by this paper
• Constraints on the location of the liquid–liquid critical point in water

  2025cited by this paper
• The orientational structure of a model patchy particle fluid: Simulations, integral equations, density functional theory, and machine learning.

  2025cited by this paper
• Determining the Chemical Potential via Universal Density Functional Learning.

  2025cited by this paper
• Neural operators for forward and inverse potential-density mappings in classical density functional theory.

  2025cited by this paper
• Static Contact Angles of Mixtures: Classical Density Functional Theory and Experimental Investigation

  2025cited by this paper
• A first-principles approach to electromechanics in liquids

  2025cited by this paper
• Dielectrocapillarity for exquisite control of fluids.

  2025cited by this paper
• Machine Learning Predicts Liquid–Gas Transition

  2025cited by this paper
• Critical surface adsorption of confined binary liquids with locally conserved mass and composition

  2024cited by this paper
• Early Predictor for the Onset of Critical Transitions in Networked Dynamical Systems

  2024cited by this paper
• Neural force functional for non-equilibrium many-body colloidal systems

  2024cited by this paper
• Neural density functionals: Local learning and pair-correlation matching.

  2024cited by this paper
• Bridging electronic and classical density-functional theory using universal machine-learned functional approximations.

  2024cited by this paper
• Experimental and theoretical bulk phase diagram and interfacial tension of ouzo.

  2024cited by this paper
• Learning Neural Free-Energy Functionals with Pair-Correlation Matching.

  2024cited by this paper
• A classical density functional theory for solvation across length scales.

  2024cited by this paper
• Hyperdensity Functional Theory of Soft Matter.

  2024cited by this paper
• Coexisting multiphase and interfacial behavior of ouzo

  2024cited by this paper
• Wetting, Algebraic Curves, and Conformal Invariance.

  2024cited by this paper
• Metadensity Functional Theory for Classical Fluids: Extracting the Pair Potential.

  2024cited by this paper
• The orientational structure of a model patchy particle fluid: simulations, integral equations, density functional theory and machine learning

  2024cited by this paper
• High-Dimensional Operator Learning for Molecular Density Functional Theory.

  2024cited by this paper
• Why hyperdensity functionals describe any equilibrium observable

  2024cited by this paper
• Learning Classical Density Functionals for Ionic Fluids.

  2024cited by this paper
• Neural Density Functional Theory of Liquid-Gas Phase Coexistence

  2024cited by this paper
• Why neural functionals suit statistical mechanics

  2023cited by this paper
• Finite-size analysis in neural network classification of critical phenomena.

  2023cited by this paper
• Mapping Out Phase Diagrams with Generative Classifiers.

  2023cited by this paper
• Neural functional theory for inhomogeneous fluids: Fundamentals and applications

  2023cited by this paper
• Physics-informed Bayesian inference of external potentials in classical density-functional theory.

  2023cited by this paper
• Detection of Approaching Critical Transitions in Natural Systems Driven by Red Noise

  2023cited by this paper
• Tracking the Distance to Criticality in Systems with Unknown Noise

  2023cited by this paper
• Machine Learning of a Density Functional for Anisotropic Patchy Particles.

  2023cited by this paper
• Modeling Mixtures with PCP-SAFT: Insights from Large-Scale Parametrization and Group-Contribution Method for Binary Interaction Parameters

  2023cited by this paper
• Reliable emulation of complex functionals by active learning with error control.

  2022cited by this paper
• Wetting and Nonwetting near a Tricritical Point.

  2022cited by this paper
• Noether’s theorem in statistical mechanics

  2021cited by this paper
• Inverse design of soft materials via a deep learning–based evolutionary strategy

  2021cited by this paper
• From predictive modelling to machine learning and reverse engineering of colloidal self-assembly

  2021cited by this paper
• Machine-learning free-energy functionals using density profiles from simulations

  2021cited by this paper
• Machine learning for condensed matter physics

  2020cited by this paper
• Continuous Demixing Transition of Binary Liquids: Finite‐Size Scaling from the Analysis of Sub‐Systems

  2020cited by this paper
• Enhancing Gas Solubility in Nanopores: A Combined Study using Classical Density Functional Theory and Machine Learning.

  2020cited by this paper
• Physics-constrained Bayesian inference of state functions in classical density-functional theory.

  2020cited by this paper
• Analytical classical density functionals from an equation learning network

  2019cited by this paper
• A classical density functional from machine learning and a convolutional neural network

  2018cited by this paper
• Pushing the limits of Monte Carlo simulations for the three-dimensional Ising model.

  2017cited by this paper
• Structure and dynamics of binary liquid mixtures near their continuous demixing transitions.

  2016cited by this paper
• New developments in classical density functional theory

  2016cited by this paper
• Liquid-liquid interfacial properties of a symmetrical Lennard-Jones binary mixture.

  2015cited by this paper
• Neural-network approach to modeling liquid crystals in complex confinement.

  2014cited by this paper
• A Density Functional Theory for Vapor–Liquid Interfaces of Mixtures Using the Perturbed-Chain Polar Statistical Associating Fluid Theory Equation of State

  2014cited by this paper
• Liquid-liquid phase separation in biology.

  2014cited by this paper
• Matching

  2009cited by this paper
• Phase behaviour of a symmetrical binary mixture in a field

  2006cited by this paper
• Self-consistent Ornstein–Zernike approximation for a binary symmetric fluid mixture

  2003cited by this paper
• Phase diagram of symmetric binary fluid mixtures: first-order or second-order demixing.

  2002cited by this paper
• Understanding molecular simulation : from algorithms to applications. 2nd ed.

  2002cited by this paper
• Wetting of a symmetrical binary fluid mixture on a wall.

  2000cited by this paper
• A density functional study of liquid–liquid interfaces in partially miscible systems

  1999cited by this paper
• Phase behavior of a symmetrical binary fluid mixture.

  1998cited by this paper
• Critical end point behavior in a binary fluid mixture

  1997cited by this paper
• Pairwise correlations at a fluid-fluid interface The influence of a wetting film

  1985cited by this paper
• Adsorption from a binary fluid mixture

  1985cited by this paper
• Molecular Theory of Capillarity

  1983cited by this paper
• The structure and surface tension of the liquid-vapour interface near the upper critical end point of a binary mixture of Lennard-Jones fluids: II. The three phase region and the Cahn wetting transition

  1983cited by this paper
• The structure and surface tension of the liquid-vapour interface near the upper critical end point of a binary mixture of Lennard-Jones fluids

  1983cited by this paper
• Critical lines and phase equilibria in binary van der Waals mixtures

  1980cited by this paper
• The nature of the liquid-vapour interface and other topics in the statistical mechanics of non-uniform, classical fluids

  1979cited by this paper

• The roles of bulk and surface thermodynamics in the selective adsorption of a confined azeotropic mixture

  2026cites this paper
• Dielectrocapillarity for exquisite control of fluids.

  2025cites this paper
• Gauge invariance and hyperforce correlation theory for equilibrium fluid mixtures.

  2025cites this paper
• Learning Density Functionals to Bridge Particle and Continuum Scales

  2025cites this paper