Special Issue
Topic: Application of Machine Learning to Crystal Structure Prediction
A Special Issue of Journal of Materials Informatics
ISSN 2770-372X (Online)
Submission deadline: 31 Jul 2024
Guest Editor(s)
Prof. Qiang Zhu
Department of Mechanical Engineering and Engineering Science, University of North Carolina Charlotte, Charlotte, NC, USA.
Special Issue Introduction
In recent years, the design and discovery of complex materials has undergone a revolution with the development of crystal structure prediction (CSP) methods. These techniques enable the prediction of intricate material structures, regardless of the availability of prior knowledge. The breakthrough in structure prediction has been primarily driven by the integration of advanced global optimization techniques with accurate energy models, such as density functional theory and tight binding based on electronic structure calculations or more cost-effective classical force fields. These methodologies efficiently explore the vast landscape of structural and compositional space, leading to the identification of plausible low-energy candidate structures on the computer.
Traditionally, the computational power of CSP was limited by the high cost associated with electronic structure calculations and the lack of efficient sampling methods to handle the complexity of chemical compositions. However, in recent years, machine learning has emerged as a game-changing approach, significantly advancing the field of CSP. Various machine learning and deep learning techniques have been developed to facilitate the high-throughput prediction of complex materials in the vast chemical space. Consequently, the introduction of machine learning approaches has had a profound impact on the CSP community.
This Special Issue aims to compile the diverse applications of machine learning and deep learning approaches in the field of CSP. We encourage the submission of original contributions or topical reviews within the broad scope of machine learning in CSP. Specifically, we welcome submissions on the following topics:
● Development of machine force fields for structure prediction or high-throughput materials screening;
● Utilization of machine learning for predicting materials properties and its application in the design of functional and structural materials (e.g., superconducting materials, superhard materials, energy storage systems, batteries, organic crystals, and more);
● Combination of machine learning with other emerging techniques to achieve fast and accurate structure generation;
● Application of machine learning or deep learning techniques in global optimization of material structures.
Traditionally, the computational power of CSP was limited by the high cost associated with electronic structure calculations and the lack of efficient sampling methods to handle the complexity of chemical compositions. However, in recent years, machine learning has emerged as a game-changing approach, significantly advancing the field of CSP. Various machine learning and deep learning techniques have been developed to facilitate the high-throughput prediction of complex materials in the vast chemical space. Consequently, the introduction of machine learning approaches has had a profound impact on the CSP community.
This Special Issue aims to compile the diverse applications of machine learning and deep learning approaches in the field of CSP. We encourage the submission of original contributions or topical reviews within the broad scope of machine learning in CSP. Specifically, we welcome submissions on the following topics:
● Development of machine force fields for structure prediction or high-throughput materials screening;
● Utilization of machine learning for predicting materials properties and its application in the design of functional and structural materials (e.g., superconducting materials, superhard materials, energy storage systems, batteries, organic crystals, and more);
● Combination of machine learning with other emerging techniques to achieve fast and accurate structure generation;
● Application of machine learning or deep learning techniques in global optimization of material structures.
Submission Deadline
31 Jul 2024
Submission Information
For Author Instructions, please refer to https://www.oaepublish.com/jmi/author_instructions
For Online Submission, please login at https://oaemesas.com/login?JournalId=jmi&SpecialIssueId=JMI230606
Submission Deadline: 31 Jul 2024
Contacts: Shirley Han, Assistant Editor, assistant_editor@jmijournal.com
Published Articles
Machine learning assisted crystal structure prediction made simple
Open Access Review 29 Sep 2024
DOI: 10.20517/jmi.2024.18
Views: Downloads:
Searching new cocrystal structures of CL-20 and HMX via evolutionary algorithm and machine learning potential
Open Access Research Article 21 May 2024
DOI: 10.20517/jmi.2023.37
Views: Downloads:
Crystal structure prediction using neural network potential and age-fitness Pareto genetic algorithm
Open Access Research Article 1 Mar 2024
DOI: 10.20517/jmi.2023.33
Views: Downloads: