Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials

TL;DR

This paper introduces topogivity, a machine-learned chemical rule that predicts topological materials solely from chemical formulas, enabling efficient discovery of new topological compounds beyond symmetry-based methods.

Contribution

The authors develop a novel heuristic based on topogivity, facilitating high-throughput prediction and discovery of topological materials using only chemical formulas.

Findings

Identified new topological materials not detectable by symmetry indicators.

Validated predictions with ab initio calculations.

Demonstrated high accuracy of the topogivity heuristic.

Abstract

Topological materials present unconventional electronic properties that make them attractive for both basic science and next-generation technological applications. The majority of currently known topological materials have been discovered using methods that involve symmetry-based analysis of the quantum wavefunction. Here we use machine learning to develop a simple-to-use heuristic chemical rule that diagnoses with a high accuracy whether a material is topological using only its chemical formula. This heuristic rule is based on a notion that we term topogivity, a machine-learned numerical value for each element that loosely captures its tendency to form topological materials. We next implement a high-throughput procedure for discovering topological materials based on the heuristic topogivity-rule prediction followed by ab initio validation. This way, we discover new topological materials that are not diagnosable using symmetry indicators, including several that may be promising for experimental observation.