Machine-learning structural reconstructions for accelerated point defect calculations

Abstract

Defects dictate the properties of many functional materials. To understand the behaviour of defects and their impact on physical properties, it is necessary to identify the most stable defect geometries. However, global structure searching is computationally challenging for high-throughput defect studies or materials with complex defect landscapes, like alloys or disordered solids. Here, we tackle this limitation by harnessing a machine-learning surrogate model to qualitatively explore the defect structural landscape. By learning defect motifs in a family of related metal chalcogenide and mixed anion crystals, the model successfully predicts favourable reconstructions for unseen defects in unseen compositions for 90% of cases, thereby reducing the number of first-principles calculations by 73%. Using CdSe${}_x$Te${}_{1-x}$ alloys as an exemplar, we train a model on the end member compositions and apply it to find the stable geometries of all inequivalent vacancies for a range of mixing concentrations, thus enabling more accurate and faster defect studies for configurational complex systems.

References in corpus (11)

• Electronic Defects in Metal Oxide Photocatalysts
• A foundation model for atomistic materials chemistry
• Distribution of Formation and migration energies of point defects in concentrated solid-solution alloys: Ni_{0.5}Co_{0.5}, Ni_{0.5}Fe_{0.5}, Ni_{0.8}Fe_{0.2} and Ni_{0.8}Cr_{0.2}
• doped: Python toolkit for robust and repeatable charged defect supercell calculations
• Imperfections are not 0 K: free energy of point defects in crystals
• Developments and Further Applications of Ephemeral Data Derived Potentials
• A substitutional quantum defect in WS${}_2$ discovered by high-throughput computational screening and fabricated by site-selective STM manipulation
• Matbench Discovery -- A framework to evaluate machine learning crystal stability predictions
• Machine learning for impurity charge-state transition levels in semiconductors from elemental properties using multi-fidelity datasets
• Learned Force Fields Are Ready For Ground State Catalyst Discovery
• Database of semiconductor point-defect properties for applications in quantum technologies

Cited by in corpus (5)

• Approximate Excited-State Potential Energy Surfaces for Defects in Solids
• Identifying Split Vacancy Defects with Machine-Learned Foundation Models and Electrostatics
• DeFecT-FF: a machine learning force field framework for high throughput defect modeling in CdTe-based solar cells
• Machine Learning Phonon Spectra for Fast and Accurate Optical Lineshapes of Defects
• Accelerating point defect simulations using data-driven and machine learning approaches