Machine-learning effective many-body potentials for anisotropic particles using orientation-dependent symmetry functions

Abstract

Spherically-symmetric atom-centered descriptors of atomic environments have been widely used for constructing potential or free energy surfaces of atomistic and colloidal systems and to characterize local structures using machine learning techniques. However, when particle shapes are non-spherical, as in the case of rods and ellipsoids, standard spherically-symmetric structure functions alone produce imprecise descriptions of local environments. In order to account for the effects of orientation, we introduce two- and three-body orientation-dependent particle-centered descriptors for systems composed of rod-like particles. To demonstrate the suitability of the proposed functions, we use an efficient feature selection scheme and simple linear regression to construct coarse-grained many-body interaction potentials for computationally-efficient simulations of model systems consisting of colloidal particles with anisotropic shape: mixtures of colloidal rods and nonadsorbing polymer, hard rods enclosed by an elastic microgel shell, and ligand-stabilized nanorods. We validate the machine-learning (ML) effective many-body potentials based on orientation-dependent symmetry functions by using them in direct coexistence simulations to map out the phase behavior of colloidal rods and non-adsorbing polymer. We find good agreement with results obtained from simulations of the true binary mixture, demonstrating that the effective interactions are well-described by the orientation-dependent ML potentials.

References in corpus (13)

• On representing chemical environments
• Physics-inspired structural representations for molecules and materials
• The Phase Diagram of Star Polymer Solutions
• On the colloidal stability of apolar nanoparticles: The role of particle size and ligand shell structure
• On the colloidal stability of apolar nanoparticles: The role of ligand length
• Many-body interactions and correlations in coarse-grained descriptions of polymer solutions
• Orientational Ordering of Passivating Ligands on CdS Nanorods in Solution Generates Strong Rod-Rod Interactions
• Triplet forces between star polymers
• Depletion induced isotropic-isotropic phase separation in suspensions of rod-like colloids
• Machine learning many-body potentials for colloidal systems
• Machine Learning Characterization of Structural Defects in Amorphous Packings of Dimers and Ellipses
• Modeling of many-body interactions between elastic spheres through symmetry functions
• Equation of state of hard oblate ellipsoids by replica exchange Monte Carlo

Cited by in corpus (9)

• Neural functional theory for inhomogeneous fluids: Fundamentals and applications
• Perspective: How to overcome dynamical density functional theory
• Why neural functionals suit statistical mechanics
• Hyper-density functional theory of soft matter
• Anisotropic molecular coarse-graining by force and torque matching with neural networks
• A neural network potential with self-trained atomic fingerprints: a test with the mW water potential
• Active crystallization from power functional theory
• Approximation of anisotropic pair potentials using multivariate interpolation
• Determining the chemical potential via universal density functional learning