Hot Keywords

Topic: Data-driven Materials Design via High-throughput Computation, High-throughput Experiments, Materials Database, and Artificial Intelligence/Machine Learning — Contributions Partially Selected from Conferences FAIR-DI 2022, CNNEM 2022, and ICM3-2022

A special issue of Journal of Materials Informatics

ISSN 2770-372X (Online)

Submission deadline: 30 Jun 2023

Guest Editor(s)

  • Prof. Yi Liu
    1Materials Genome Institute, Shanghai University, Shanghai, China.
    2Zhejiang Laboratory, Hangzhou, China.

    Website | E-mail

  • Prof. Abhishek K. Singh
    Materials Research Centre, Indian Institute of Science, India.

    Website | E-mail

  • Dr. Lei Shen
    Department of Mechanical Engineering, College of Design and Engineering, National University of Singapore, Singapore.

    Website | E-mail

  • Prof. Chaozheng He
    School of Materials Science and Chemical Engineering, Xi'an Technological University, Xi'an, Shaanxi, China.

    Website | E-mail

  • Prof. Yanning Zhang
    Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, Sichuan, China.

    Website | E-mail

  • Dr. Runhai Ouyang
    Materials Genome Institute, Shanghai University, Shanghai, China.

    Website | E-mail

Special Issue Introduction

Materials design drives the innovation of materials science and engineering to meet the increasing demands for high performance, low cost, and environmentally benign materials. The challenges of materials design originate from the complex materials parameters including compositions, structures, and processing parameters as well as the multiple materials properties often behaving with contradictory trends. It is a long-term challenging problem to discover the complex and usually highly nonlinear relationships between the composition/structure/processing and property/performance (CSP-PP). Thanks to the recent surge of big-data and artificial intelligence (AI) techniques, the data-driven approach emerges as the fourth research paradigm in addition to the experiment, theory, and computation. The data-driven methods, e.g., machine learning (ML), provide a new powerful tool to overcome the difficulty of discovering CSP-PP relationships that often lacks of explicit analytical theory. The ML methods can be developed on the basis of the large data extracted from the existing materials databases, collected from the published literatures, or generated by experimental or computational methods. The efficient generation of a large amount of data requires to carry out computations and experiments systematically in high-throughput manners. The ML applications in materials science gave birth to the emerging field of materials informatics with the naturally close integration with materials database, high-throughput computation, and high-throughput experiment, forming the motivation of this special issue.

Scope of the focus issue
This special issue invites the recent contributions generally covering the broad topics in materials informatics from academia and industry word-wide. The main topics focused by this special issue, but not limited to, are listed as follows:

1) The materials database construction: extraction, collection, and generation
A. The automatic collection of data from materials literatures;
B. The materials data standards for data storage, search, sharing, and analysis;
C. The construction of computational or experimental materials databases.

2) The development of machine learning methods with the applications in materials science
A. The feature engineering models suitable for organic, inorganic, and polymer materials;
B. The performance comparisons among various machine learning algorithms including deep learning methods;
C. The model interpretation: “Learning from machine” after machine learning.

3) High-throughput computational protocols and applications
A. The software or platform and applications for systematic high-throughput computations in various materials systems;
B. The development of effective and efficient computational workflow and selection criteria used in high-throughput computational screening;
C. The discovery of the trends and relationships in high-throughput computational data.

4) High-throughput experiments in materials synthesis and characterization
A. The development of high-throughput experimental facilities for materials synthesis and characterization including automatic robotic materials synthesis systems;
B. The machine learning-assisted iterative experiments for materials optimization;
C. The development of machine learning predictive models based on the experimental data in literatures or materials databases.

The integration works of the items listed above are strongly encouraged.

Besides the free submissions, this special issue also collaborates with three conferences FAIR-DI 2022, CNNEM 2022, and ICM3-2022 (see more details via the links below). Some contributions in this special issue will be selected from the conference presentations after additional peer-review.

International FAIR-DI Conference on a FAIR Data Infrastructure for Materials Genomics (2022):

The 14th International Symposium on Computational Nanoscience and New Energy Materials (CNNEM 2022):

The 14th International Conference of Multi-scale Modeling and Simulation of Materials (ICM3 - 2022).

Submission Deadline

30 Jun 2023

Submission Information

For Author Instructions, please refer to
For Online Submission, please login at
Submission Deadline: 30 Jun 2023
Contacts: Lijun Jin, Managing Editor,

Published Articles

© 2016-2023 OAE Publishing Inc., except certain content provided by third parties