Analytical classical density functionals from an equation learning network

Abstract

We explore the feasibility of using machine learning methods to obtain an analytic form of the classical free energy functional for two model fluids, hard rods and Lennard--Jones, in one dimension . The Equation Learning Network proposed in Ref. 1 is suitably modified to construct free energy densities which are functions of a set of weighted densities and which are built from a small number of basis functions with flexible combination rules. This setup considerably enlarges the functional space used in the machine learning optimization as compared to previous work 2 where the functional is limited to a simple polynomial form. As a result, we find a good approximation for the exact hard rod functional and its direct correlation function. For the Lennard--Jones fluid, we let the network learn (i) the full excess free energy functional and (ii) the excess free energy functional related to interparticle attractions. Both functionals show a good agreement with simulated density profiles for thermodynamic parameters inside and outside the training region.

Update figures and SI. Some explanations and clarifications are added

References in corpus (8)

• By-passing the Kohn-Sham equations with machine learning
• Finding Density Functionals with Machine Learning
• General non-existence theorem for phase transitions in one-dimensional systems with short range interactions, and physical examples of such transitions
• Molecular Density Functional Theory of Water
• Fast Computation of Solvation Free Energies with Molecular Density Functional Theory: Thermodynamic-Ensemble Partial Molar Volume Corrections
• Molecular Density Functional Theory of Water describing Hydrophobicity at Short and Long Length Scales
• Machine learning density functional theory for the Hubbard model
• A classical density functional from machine learning and a convolutional neural network

Cited by in corpus (26)

• Power functional theory for many-body dynamics
• Neural functional theory for inhomogeneous fluids: Fundamentals and applications
• Machine-learning free-energy functionals using density profiles from simulations
• Evolving symbolic density functionals
• Perspective: How to overcome dynamical density functional theory
• Machine learning of a density functional for anisotropic patchy particles
• Physics-constrained Bayesian inference of state functions in classical density-functional theory
• Learning classical density functionals for ionic fluids
• Reliable emulation of complex functionals by active learning with error control
• Fluctuation profiles in inhomogeneous fluids
• Perspective: New directions in dynamical density functional theory
• Why neural functionals suit statistical mechanics
• Physics-informed Bayesian inference of external potentials in classical density-functional theory
• Hyper-density functional theory of soft matter
• Hyperforce balance via thermal Noether invariance of any observable
• Neural density functional theory of liquid-gas phase coexistence
• Neural density functionals: Local learning and pair-correlation matching
• Neural force functional for non-equilibrium many-body colloidal systems
• Why hyperdensity functionals describe any equilibrium observable
• Metadensity functional theory for classical fluids: Extracting the pair potential
• Learning the bulk and interfacial physics of liquid-liquid phase separation with neural density functionals
• A density functional for the lattice gas from fundamental measure theory
• Neural Density Functional Theory in Higher Dimensions with Convolutional Layers
• Metadensity functional learning for classical fluids: Regularizing with pair correlations
• Determining the chemical potential via universal density functional learning
• The roles of bulk and surface thermodynamics in the selective adsorption of a confined azeotropic mixture