Identifying Split Vacancy Defects with Machine-Learned Foundation Models and Electrostatics

TL;DR

This paper introduces a tiered screening method combining geometric analysis, electrostatics, and foundation machine learning models to efficiently identify split vacancy defects across a vast database of solid-state compounds, revealing their widespread occurrence.

Contribution

It presents a novel, efficient approach for detecting complex split vacancy defects using a combination of computational techniques and foundation ML models, enabling large-scale defect screening.

Findings

Thousands of low-energy split vacancy configurations identified.

Split vacancies are more prevalent in inorganic solids than previously recognized.

Foundation ML models show potential but require careful application.

Abstract

Point defects are ubiquitous in solid-state compounds, dictating many functional properties such as conductivity, catalytic activity and carrier recombination. Over the past decade, the prevalence of metastable defect geometries and their importance to relevant properties has been increasingly recognised. A striking example is split vacancies, where an isolated atomic vacancy transforms to a stoichiometry-conserving complex of two vacancies and an interstitial ($V_X \rightarrow [V_X + X_i + V_X]$), which can be accompanied by a dramatic energy lowering and change in behaviour. These species are particularly challenging to identify from computation, due to the `non-local' nature of this reconstruction. Here, I present an approach for the efficient identification of these defects, through tiered screening which combines geometric analysis, electrostatic energies and foundation machine learning (ML) models. This approach allows the screening of all solid-state compounds in the Materials Project database (including all entries in the ICSD, along with several thousand predicted metastable materials), identifying thousands of low energy split vacancy configurations, hitherto unknown. This study highlights both the potential utility of (foundation) machine-learning potentials, with important caveats, the significant prevalence of split vacancy defects in inorganic solids, and the importance of global optimisation approaches for defect modelling.