Accelerating point defect simulations using data-driven and machine learning approaches

Abstract

Point defects in solid-state materials are now routinely simulated using large supercell structures, requiring efficient quantum mechanical solutions. Data-driven and machine learning (ML) models trained on computational data can enable rapid defect property predictions and high-throughput screening. In this article, we provide an overview of prominent efforts to accelerate defect simulations using these approaches. We begin by discussing the motivations for data-driven techniques in defect modeling, and describe efforts over the past decade to use descriptor-based models for rapid screening of defect properties -- most notably in oxides. In particular, we discuss case studies where surrogate models and interatomic potentials were trained on density functional theory (DFT) data, leading to predictions with quantum-mechanical accuracies at a fraction of the cost. In addition to geometry relaxation and formation energy predictions, these interatomic potentials are capable of predicting phonon modes and vibrational free energies to yield defect energetics at finite temperatures -- representing a key frontier for computational defect research. We finish with a discussion on how to connect these approaches and their outputs with experimental data, and provide an outlook on this burgeoning sub-field.

Part of the MRS Bulletin '100 Years of Point Defects' Special Collection

References in corpus (25)

• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• First-principles theory of nonradiative carrier capture via multiphonon emission
• First-principles theory of the luminescence lineshape for the triplet transition in diamond NV centre
• The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts
• AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance
• First-Principles Calculations of Luminescence Spectrum Line Shapes for Defects in Semiconductors: The Example of GaN and ZnO
• A practical guide to machine learning interatomic potentials -- Status and future
• PyCDT: A Python toolkit for modeling point defects in semiconductors and insulators
• How to validate machine-learned interatomic potentials
• General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian
• Identifying the ground state structures of point defects in solids
• Rapid Recombination by Cadmium Vacancies in CdTe
• doped: Python toolkit for robust and repeatable charged defect supercell calculations
• Explicit Multi-element Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems
• Imperfections are not 0 K: free energy of point defects in crystals
• On the Dopability of Semiconductors and Governing Material Properties
• Impact of metastable defect structures on carrier recombination in solar cells
• Machine-learning structural reconstructions for accelerated point defect calculations
• Unveiling the complex structure-property correlation of defects in 2D materials based on high throughput datasets
• Self-compensation in phosphorus-doped CdTe
• Quantitative Modeling of Point Defects in $\beta$-Ga2O3 Combining Hybrid Functional Energetics with Semiconductor and Processes Thermodynamics
• Optical line shapes of color centers in solids from classical autocorrelation functions
• Machine Learning Prediction of Charged Defect Formation Energies from Crystal Structures
• Real space representation of the quasiparticle self-consistent $GW$ self-energy and its application to defect calculations
• Machine Learning Phonon Spectra for Fast and Accurate Optical Lineshapes of Defects