Determining the chemical potential via universal density functional learning

Abstract

We demonstrate that the machine learning of density functionals allows one to determine simultaneously the equilibrium chemical potential across simulation datasets of inhomogeneous classical fluids. Minimization of a loss function based on an Euler-Lagrange equation yields both the universal one-body direct correlation functional, which is represented locally by a neural network, as well as the system-specific unknown chemical potential values. The method can serve as an efficient alternative to conventional computational techniques of measuring the chemical potential. It also facilitates using canonical data from Brownian dynamics, molecular dynamics, or Monte Carlo simulations as a basis for constructing neural density functionals, which are fit for accurate multiscale prediction of soft matter systems in equilibrium.

9 pages, 5 figures

References in corpus (40)

• Density functional theory for hard-sphere mixtures: the White-Bear version Mark II
• Molecular Dynamics Simulations
• Machine learning and density functional theory
• Unsupervised learning for local structure detection in colloidal systems
• Colloidal Hard Spheres: Triumphs, Challenges and Mysteries
• Grand-canonical-like molecular-dynamics simulations by using an adaptive-resolution technique
• Fast Computation of Solvation Free Energies with Molecular Density Functional Theory: Thermodynamic-Ensemble Partial Molar Volume Corrections
• Chemical potential of liquids and mixtures via Adaptive Resolution Simulation
• Use the force! Reduced variance estimators for densities, radial distribution functions and local mobilities in molecular simulations
• Neural functional theory for inhomogeneous fluids: Fundamentals and applications
• Better than counting: Density profiles from force sampling
• A classical density functional from machine learning and a convolutional neural network
• Machine-learning free-energy functionals using density profiles from simulations
• Analytical classical density functionals from an equation learning network
• Machine learning many-body potentials for colloidal systems
• Molecular dynamics of open systems: construction of a mean-field particle reservoir
• Structural and Thermodynamic Properties of Hard-Sphere Fluids
• Perspective: How to overcome dynamical density functional theory
• Machine learning of a density functional for anisotropic patchy particles
• Machine-learning effective many-body potentials for anisotropic particles using orientation-dependent symmetry functions
• Chemical Potential Calculations In Dense Liquids Using Metadynamics
• 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
• Why neural functionals suit statistical mechanics
• Hyper-density functional theory of soft matter
• Physics-informed Bayesian inference of external potentials in classical density-functional theory
• Learning Neural Free-Energy Functionals with Pair-Correlation Matching
• Chemical potential of a test hard sphere of variable size in a hard-sphere fluid
• Neural density functionals: Local learning and pair-correlation matching
• Neural density functional theory of liquid-gas phase coexistence
• Bridging electronic and classical density-functional theory using universal machine-learned functional approximations
• Thermodynamic relations at the coupling boundary in adaptive resolution simulations for open systems
• Neural force functional for non-equilibrium many-body colloidal systems
• Chemical Potential Calculations in Non-Homogeneous Liquids
• Why hyperdensity functionals describe any equilibrium observable
• Metadensity functional theory for classical fluids: Extracting the pair potential
• Chemical potential of a test hard sphere of variable size in hard-sphere fluid mixtures
• Neural Density Functional Theory in Higher Dimensions with Convolutional Layers
• A first principles approach to electromechanics in liquids

Cited by in corpus (2)

• Metadensity functional learning for classical fluids: Regularizing with pair correlations
• A unified machine-learning framework for ab initio multiscale modeling of liquids