Machine learning with force-field inspired descriptors for materials: fast screening and mapping energy landscape

TL;DR

This paper introduces a comprehensive set of chemo-structural descriptors for machine learning in materials science, enabling accurate property prediction and efficient screening of multicomponent systems, including 2D layered materials.

Contribution

It develops new descriptors that differentiate structural prototypes and integrates ML with genetic algorithms for structure search and validation.

Findings

Accurately predicts formation energies, bandgaps, and other properties.

Successfully discovers exfoliable 2D materials with desired properties.

Validates ML models against DFT convex hull calculations.

Abstract

We present a complete set of chemo-structural descriptors to significantly extend the applicability of machine-learning (ML) in material screening and mapping energy landscape for multicomponent systems. These new descriptors allow differentiating between structural prototypes, which is not possible using the commonly used chemical-only descriptors. Specifically, we demonstrate that the combination of pairwise radial, nearest neighbor, bond-angle, dihedral-angle and core-charge distributions plays an important role in predicting formation energies, bandgaps, static refractive indices, magnetic properties, and modulus of elasticity for three-dimensional (3D) materials as well as exfoliation energies of two-dimensional (2D) layered materials. The training data consists of 24549 bulk and 616 monolayer materials taken from JARVIS-DFT database. We obtained very accurate ML models using gradient boosting algorithm. Then we use the trained models to discover exfoliable 2D-layered materials satisfying specific property requirements. Additionally, we integrate our formation energy ML model with a genetic algorithm for structure search to verify if the ML model reproduces the DFT convex hull. This verification establishes a more stringent evaluation metric for the ML model than what commonly used in data sciences. Our learnt model is publicly available on the JARVIS-ML website (https://www.ctcms.nist.gov/jarvisml ) property predictions of generalized materials.