Effects of data bias on machine-learning–based material discovery using experimental property data
Rattachement africain : jp. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
Materials informatics (MI) research, which is the discovery of new materials through machine learning (ML) using large-scale material data, has attracted considerable attention in recent years. However, in general, the large-scale material data used in MI are biased owing to differences in the targeted material domains. Moreover, most studies on MI have not clearly demonstrated the influence of data bias on ML models. In this study, we clarify the influence of data bias on ML models by combining the concept of the applicability domain and clustering for large-scale experimental property data in the Starrydata2 material database previously developed by our group. The results show that data bias influences the error and reliability of the predictions made by the ML model. The predictions of the ML model within the applicability domain are highly reliable compared to those made outside the domain. This indicates that the material space that can be reliably discovered by the constructed ML model is limited. Nonetheless, we apply the ML model to a large dataset comprising various material classes and find that new materials similar to known materials can be proposed within a limited space. Thus, our findings demonstrate the importance of considering data bias when constructing and evaluating ML models in MI.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- Effects of data bias on machine-learning–based material discovery using experimental property data
- Date Crossref
- 15/08/2022
- Éditeur
- Informa UK Limited
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
Kyoto University Institute for Integrated Radiation and Nuclear Science pays non établi dans la noticeUniversité ou école supérieure
-
RIKEN Center for Advanced Intelligence Project pays non établi dans la noticeStructure de recherche
-
National Institute for Materials Science Research and Services Division of Materials Data and Integrated System (MaDIS) pays non établi dans la noticeStructure de recherche
-
The University of Tokyo pays non établi dans la noticeUniversité ou école supérieure
-
University of Fukui Research Institute of Nuclear Engineering pays non établi dans la noticeUniversité ou école supérieure
-
SAKURA Internet Research Center pays non établi dans la noticeStructure de recherche
-
Graduate School of Frontier Sciences pays non établi dans la noticeUniversité ou école supérieure
Institute for Integrated Radiation and Nuclear Science — Kyoto University, RIKEN Center for Advanced Intelligence Project et Research and Services Division of Materials Data and Integrated System (MaDIS) — National Institute for Materials Science, avec 4 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.