EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data quantity governance for machine learning in materials science

Yue Liu, Zhengwei Yang, Xinxin Zou, Shuchang Ma, Dahui Liu, Maxim Avdeev, Siqi Shi iD

National Science Review · 31.05.2023 · 10 (7)

DOI: 10.1093/nsr/nwad125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift National Science Review, online erschienen am 01.05.2023. Verfasst von Yue Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Engineering and Science, Shanghai University, Shanghai200444, China. Die Arbeit wurde bisher 238-mal zitiert (Crossref) und nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Key Research Project of Zhejiang Laboratory.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data-driven machine learning (ML) is widely employed in the analysis of materials structure–activity relationships, performance optimization and materials design due to its superior ability to reveal latent data patterns and make accurate prediction. However, because of the laborious process of materials data acquisition, ML models encounter the issue of the mismatch between a high dimension of feature space and a small sample size (for traditional ML models) or the mismatch between model parameters and sample size (for deep-learning models), usually resulting in terrible performance. Here, we review the efforts for tackling this issue via feature reduction, sample augmentation and specific ML approaches, and show that the balance between the number of samples and features or model parameters should attract great attention during data quantity governance. Following this, we propose a synergistic data quantity governance flow with the incorporation of materials domain knowledge. After summarizing the approaches to incorporating materials domain knowledge into the process of ML, we provide examples of incorporating domain knowledge into governance schemes to demonstrate the advantages of the approach and applications. The work paves the way for obtaining the required high-quality data to accelerate materials design and discovery based on ML.

Schlagwörter

Stichwörter der Autor:innen

data governancedata quantitymachine learningmaterials science

Autor:innen und Institutionen

  • School of Computer Engineering and Science, Shanghai University, Shanghai200444, China.
  • Shanghai Engineering Research Center of Intelligent Computing System, Shanghai200444, China.
  • Australian Nuclear Science and Technology Organisation, Sydney 2232, Australia.
  • School of Chemistry, The University of Sydney, Sydney 2006, Australia.
  • State Key Laboratory of Advanced Special Steel, School of Materials Science and Engineering, Shanghai University, Shanghai200444, China.
  • Materials Genome Institute, Shanghai University, Shanghai200444, China.

ORCID-Profile: Siqi Shi

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Key Research Project of Zhejiang Laboratory

Zitieren

APA

Liu, Y., Yang, Z., Zou, X., Ma, S., Liu, D., Avdeev, M., & Shi, S. (2023). Data quantity governance for machine learning in materials science. National Science Review, 10(7). https://doi.org/10.1093/nsr/nwad125

Vancouver

Liu Y, Yang Z, Zou X, Ma S, Liu D, Avdeev M, et al. Data quantity governance for machine learning in materials science. National Science Review. 2023;10(7). doi:10.1093/nsr/nwad125

BibTeX
@article{Liu2023,
  author = {Liu, Yue and Yang, Zhengwei and Zou, Xinxin and Ma, Shuchang and Liu, Dahui and Avdeev, Maxim and Shi, Siqi},
  title = {Data quantity governance for machine learning in materials science},
  journal = {National Science Review},
  year = {2023},
  volume = {10},
  number = {7},
  doi = {10.1093/nsr/nwad125}
}
Kostenlos starten →