Rapid Discovery of Stable Materials by Coordinate-free Coarse Graining

TL;DR

This paper introduces a coordinate-free machine learning approach using Wyckoff representations to efficiently discover stable materials, bypassing the need for crystal structure identification and enabling rapid exploration of new materials.

Contribution

The authors propose a novel coordinate-free method employing Wyckoff representations for materials discovery, significantly improving the efficiency and scope of stable material prediction.

Findings

Identified 1,569 potentially stable materials from 5,675 calculations.

Achieved high precision in predicting stability without crystal structure data.

Enabled rapid exploration of the materials space by coarse-graining atomic coordinates.

Abstract

A fundamental challenge in materials science pertains to elucidating the relationship between stoichiometry, stability, structure, and property. Recent advances have shown that machine learning can be used to learn such relationships, allowing the stability and functional properties of materials to be accurately predicted. However, most of these approaches use atomic coordinates as input and are thus bottle-necked by crystal structure identification when investigating novel materials. Our approach solves this bottleneck by coarse-graining the infinite search space of atomic coordinates into a combinatorially enumerable search space. The key idea is to use Wyckoff representations -- coordinate-free sets of symmetry-related positions in a crystal -- as the input to a machine learning model. Our model demonstrates exceptionally high precision in discovering new theoretically stable materials, identifying 1,569 materials that lie below the known convex hull of previously calculated materials from just 5,675 ab-initio calculations. Our approach opens up fundamental advances in computational materials discovery.