A Physics-Informed Chemical Rule for Topological Materials Discovery

TL;DR

This paper presents a physics-informed chemical rule that combines compositional, orbital, and crystallographic data within an interpretable linear model to efficiently identify topological materials, overcoming limitations of composition-only heuristics.

Contribution

The authors develop a novel, interpretable linear framework that integrates multiple descriptors to predict topological propensity, enabling rapid high-throughput discovery of topological materials.

Findings

The model achieves superior predictive performance compared to existing methods.

It successfully identifies candidate topological materials where symmetry indicators fail.

The approach reduces complex material properties to a single, physically interpretable score.

Abstract

Topological phases of matter$\unicode{x2013}$comprising both insulators and semimetals$\unicode{x2013}$offer great potential for quantum applications, but identifying new candidates remains challenging due to expensive first-principles simulations and labor-intensive experimental workflows. Here we introduce a physics-informed chemical rule that integrates compositional, orbital and crystallographic descriptors within an interpretable linear framework. By explicitly encoding electron filling, space-group symmetry and orbital-resolved chemical environments, our method overcomes a fundamental limitation of composition-only heuristics$\unicode{x2013}$their inability to distinguish polymorphs with identical stoichiometry but different crystal structures. Using only elemental characteristics, our approach reduces a material's topological propensity to a single, physically interpretable score, enabling rapid and high-throughput assessment. The model achieves superior predictive performance while maintaining physical transparency, and identifies candidate topological materials where conventional symmetry indicators fail. Consequently, our framework enables rapid and interpretable exploration of complex materials spaces, establishing a scalable paradigm for the intelligent discovery of next-generation topological and quantum materials.