Ex Machina Determination of Structural Correlation Functions

Abstract

Determining the structural properties of condensed-phase systems is a fundamental problem in theoretical statistical mechanics. Here we present a machine learning method that is able to predict structural correlation functions with significantly improved accuracy in comparison with traditional approaches. The usefulness of this ex machina (from the machine) approach is illustrated by predicting the radial distribution functions of two paradigmatic condensed-phase systems, a Lennard-Jones fluid and a hard-sphere fluid, and then comparing those results to the results obtained using both integral equation methods and empirically motivated analytical functions. We find that application of the developed ex machina method typically decreases the predictive error by more than an order of magnitude in comparison with traditional theoretical methods.

A review on mechanical and material characterisation through molecular dynamics using large-scale atomic/molecular massively parallel simulator (LAMMPS)

“…The MD simulations, which were developed with the unprecedented work by Wainwright et al on performing the systems involving direct simulations that depend on the hard spheres, provide an elaborate microscopic modelling of methodology, and thermodynamic data can be extracted from the simulations. Atoms and molecules are constantly moving in real life and in simulations of MD [3].…”

Advancing Physical Chemistry with Machine Learning

“…9 Both supervised and unsupervised ML has demonstrated great successes in thermodynamics and statistical mechanics. Recent examples include the deep NN study of the inverse problem of the liquid-state theory aimed at obtaining interaction potentials from distribution functions, 10 the prediction of distribution functions, 11 and the extraction of the order parameter that leads to universality of supercritical fluid properties. 12 Data analysis tools have been developed for the prediction of key thermodynamic properties, such as activation energies, 13 rate constants, 14 and activity coefficients.…”