Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods

Abstract

Modern ab initio methods have rapidly increased our understanding of solid state materials properties, chemical reactions, and the quantum interactions between atoms. However, poor scaling often renders direct ab initio calculations intractable for large or complex systems. There are two obvious avenues through which to remedy this problem: (i) develop new, less expensive methods to calculate system properties, or (ii) make existing methods faster. This paper describes an open source framework designed to pursue both of these avenues. PROPhet (short for PROPerty Prophet) utilizes machine learning techniques to find complex, non-linear mappings between sets of material or system properties. The result is a single code capable of learning analytical potentials, non-linear density functionals, and other structure-property or property-property relationships. These capabilities enable highly accurate mesoscopic simulations, facilitate computation of expensive properties, and enable the development of predictive models for systematic materials design and optimization. This work explores the coupling of machine learning to ab initio methods through means both familiar (e.g., the creation of various potentials and energy functionals) and less familiar (e.g., the creation of density functionals for arbitrary properties), serving both to demonstrate PROPhet’s ability to create exciting post-processing analysis tools and to open the door to improving ab initio methods themselves with these powerful machine learning techniques.

From DFT to machine learning: recent approaches to materials science–a review

“…Roughly two classes of properties can be predicted, or classified, using machine learning methods: bandgaps and electronic conductivity. The former being widely explored by regression techniques, capable of presenting a numerical value for the gap [206,210,253,264,[452][453][454][455][456][457][458][459][460][461][462], or classification methods, which simply provide an answer to the question 'is this compound or material a metal?' [463].…”

“…Among those, many authors point out the requirement that descriptors should be invariant with respect to translations and rotations of atomic positions, as well as reordering of atomic indices. Popular descriptors with these properties can be categorized into few cases: structural data such as Coulomb matrices [248,457,470], molecular strings or graphs [264,455,457], and polymer fingerprinting [457][458][459]; simple atomic properties of the constituent species [460,462,466], and DFT-derived data, such as PBE/LDAlevel bandgaps and hybrid-level electronic density [206,272,452,456,461,471,472]. Frequently a combination of two or more classes of descriptors [453,457,460,473] as well as experimental data as features [272,465] is found in the literature.…”

A Critical Review of Machine Learning of Energy Materials

“…Besides general purpose ML tools such as scikit‐learn, tensorflow, and Pytorch, there has been an explosion of customized open‐source ML software libraries for materials science. A nonexhaustive list includes AutoMatminer, PROPhet for general materials ML; amp, ænet, and ANI for developing neural network potentials; CGCNN, MEGNet, and SchnetPack are graph‐based deep learning model packages for accurate crystal and/or molecule property modeling.…”

Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO2 Reduction

“…The per-atom neural network potentials were similar to a standard scheme shown to be effective in recent literature 16 and implemented recently in an open-source software package, 17 one of several implementations in the literature. 18,19 However, rather than predict the electronic energy reported by the DFT code as is standard for these methods, the adsorption energy was instead chosen as a target, which had several advantages. First, the adsorption energy is a small well-normalized energy, usually ranging from -3 eV to +1 eV, so that energy normalization was not a problem.…”