Collection 

Machine Learning of Defects in Crystals

Submission status
Open
Submission deadline

Machine learning (ML) has emerged as a powerful tool for studying the properties of condensed matter. To date, most research has focused on the bulk properties of solids, however, defects are ubiquitous in crystalline systems. Many modern functional technologies are constrained or enabled by their presence. For example, in photovoltaics, point-defects can introduce electronic states that fall within the band gap and result in voltage losses through trapping and non-radiative recombination. In contrast, point-defect qubits are an emerging platform for quantum computing and sensing that are uniquely enabled by long lived and addressable spin states on paramagnetic point defects. Defects pose a particular challenge for modern machine learning methods since they are often charged, leading to long range forces that are not well captured by existing approaches. This collection focuses on the development and application of novel machine learning approaches to study the geometric, thermodynamic, kinetic, and electronic properties of defects in the solid state.
 

Submit manuscript
Manuscript editing services
net and dots

Editors

Alex Ganose, Department of Chemistry, Imperial College London, UK
Dr. Alex Ganose is a Lecturer in the Department of Chemistry at Imperial College London. His work is focused on using computational materials chemistry, machine learning, and high-throughput calculations to design new materials for energy applications. He is a co-investigator for the Materials Project, an open database of computational materials properties, and he leads the development of several open-source software packages for high-throughput materials science calculations.


Matthew D. Witman, PhD, Sandia National Laboratories, United States
Dr Matthew D. Witman is a Senior Member of the Technical Staff, Sandia National Laboratoriesat using data science, machine learning, and computational materials science to facilitate the discovery of improved materials for hydrogen storage and generation. He obtained the PhD degree in Chemical Engineering from University of California, Berkeley. His research focuses on applying a diverse computational skill set to solve problems and make new discoveries at the intersection of material science, statistics, computer science, and machine learning.