SciPost Physics

SciPost Phys. 6, 025 (2019) · published 26 February 2019

• doi: 10.21468/SciPostPhys.6.2.025
• pdf
• BiBTeX
• RIS
• Submissions/Reports
• 

Abstract

We use machine learning methods to approximate a classical density functional. As a study case, we choose the model problem of a Lennard Jones fluid in one dimension where there is no exact solution available and training data sets must be obtained from simulations. After separating the excess free energy functional into a "repulsive" and an "attractive" part, machine learning finds a functional in weighted density form for the attractive part. The density profile at a hard wall shows good agreement for thermodynamic conditions beyond the training set conditions. This also holds for the equation of state if it is evaluated near the training temperature. We discuss the applicability to problems in higher dimensions.

• Sammüller et al., Hyperdensity Functional Theory of Soft Matter
  Phys. Rev. Lett. 133, 098201 (2024) [Crossref]
• Tao et al., Deep Neural Network Enhanced Mesoscopic Thermodynamic Model for Unlocking the Electrode/Electrolyte Interface
  Angewandte Chemie, e202418447 (2024) [Crossref]
• Tao et al., Deep Neural Network Enhanced Mesoscopic Thermodynamic Model for Unlocking the Electrode/Electrolyte Interface
  Angew Chem Int Ed, e202418447 (2024) [Crossref]
• Simon et al., Machine Learning of a Density Functional for Anisotropic Patchy Particles
  J. Chem. Theory Comput. 20, 1062 (2024) [Crossref]
• Clegg, Characterising soft matter using machine learning
  Soft Matter 17, 3991 (2021) [Crossref]
• Meyer et al., Machine Learning Approaches toward Orbital-free Density Functional Theory: Simultaneous Training on the Kinetic Energy Density Functional and Its Functional Derivative
  J. Chem. Theory Comput. 16, 5685 (2020) [Crossref]
• Cats et al., Machine-learning free-energy functionals using density profiles from simulations
  9, 031109 (2021) [Crossref]
• Eckert et al., Fluctuation Profiles in Inhomogeneous Fluids
  Phys. Rev. Lett. 125, 268004 (2020) [Crossref]
• de las Heras et al., Perspective: How to overcome dynamical density functional theory
  J. Phys.: Condens. Matter 35, 271501 (2023) [Crossref]
• Wang et al., A semilocal machine-learning correction to density functional approximations
  158, 154107 (2023) [Crossref]
• Lin et al., Analytical classical density functionals from an equation learning network
  152, 021102 (2020) [Crossref]
• Schmidt, Power functional theory for many-body dynamics
  Rev. Mod. Phys. 94, 015007 (2022) [Crossref]
• Sammüller et al., Neural functional theory for inhomogeneous fluids: Fundamentals and applications
  Proc. Natl. Acad. Sci. U.S.A. 120, e2312484120 (2023) [Crossref]
• Zimmermann et al., Neural force functional for non-equilibrium many-body colloidal systems
  Mach. Learn.: Sci. Technol. 5, 035062 (2024) [Crossref]
• te Vrugt et al., Classical dynamical density functional theory: from fundamentals to applications
  Advances in Physics 69, 121 (2020) [Crossref]
• Wu et al., Perfecting Liquid-State Theories with Machine Intelligence
  J. Phys. Chem. Lett. 14, 10545 (2023) [Crossref]
• Fang et al., Reliable emulation of complex functionals by active learning with error control
  157, 214109 (2022) [Crossref]
• Malpica-Morales et al., Physics-informed Bayesian inference of external potentials in classical density-functional theory
  159, 104109 (2023) [Crossref]
• Nagai et al.,
  36, 91 (2023) [Crossref]
• te Vrugt et al., Perspective: New directions in dynamical density functional theory
  J. Phys.: Condens. Matter 35, 041501 (2023) [Crossref]
• Sammüller et al., Neural density functionals: Local learning and pair-correlation matching
  Phys. Rev. E 110, L032601 (2024) [Crossref]
• Camps-Valls et al., Discovering causal relations and equations from data
  Physics Reports 1044, 1 (2023) [Crossref]
• Robitschko et al., Hyperforce balance via thermal Noether invariance of any observable
  Commun Phys 7, 103 (2024) [Crossref]