Neural Density Functional Theory in Higher Dimensions with Convolutional Layers

Abstract

Based on recent advancements in using machine learning for classical density functional theory for systems with one-dimensional, planar inhomogeneities, we propose a machine learning model for application in two dimensions (2D) akin to density functionals in weighted density forms, as e. g. in fundamental measure theory (FMT). We implement the model with fast convolutional layers only and apply it to a system of hard disks in fully 2D inhomogeneous situations. The model is trained on a combination of smooth and steplike external potentials in the fluid phase. Pair correlation functions from test particle geometry show very satisfactory agreement with simulations although these types of external potentials have not been included in the training. The method should be fully applicable to 3D problems, where the bottleneck at the moment appears to be in obtaining smooth enough 3D histograms as training data from simulations.

added bin potential integration and minor improvements

References in corpus (20)

• Two-step melting in two dimensions: First-order liquid-hexatic transition
• 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
• A classical density functional from machine learning and a convolutional neural network
• Machine-learning free-energy functionals using density profiles from simulations
• Phase diagram of two-dimensional hard rods from fundamental mixed measure density functional theory
• Analytical classical density functionals from an equation learning network
• Machine learning of a density functional for anisotropic patchy particles
• Explicitly stable Fundamental Measure Theory models for classical density functional theory
• Learning classical density functionals for ionic fluids
• Why neural functionals suit statistical mechanics
• Hyper-density functional theory of soft matter
• Learning Neural Free-Energy Functionals with Pair-Correlation Matching
• Bridging electronic and classical density-functional theory using universal machine-learned functional approximations
• Neural density functionals: Local learning and pair-correlation matching
• Neural density functional theory of liquid-gas phase coexistence
• Bulk structural informations from density functionals for patchy particles
• Why hyperdensity functionals describe any equilibrium observable
• Metadensity functional theory for classical fluids: Extracting the pair potential
• Phase diagrams and crystal-fluid surface tensions in additive and nonadditive two-dimensional hard disk mixtures

Cited by in corpus (5)

• Learning the bulk and interfacial physics of liquid-liquid phase separation with neural density functionals
• Metadensity functional learning for classical fluids: Regularizing with pair correlations
• The roles of bulk and surface thermodynamics in the selective adsorption of a confined azeotropic mixture
• Determining the chemical potential via universal density functional learning
• A unified machine-learning framework for ab initio multiscale modeling of liquids