EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Composition Based Oxidation State Prediction of Materials Using Deep Learning Language Models

Nihang Fu, Jeffrey Hu, Ying Feng, Gregory Morrison, Hans-Conrad Zur Loye, Jianjun Hu iD

Advanced Science · 2023-10 · 10 (28)

DOI: 10.1002/advs.202301011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 07.08.2023. Verfasst von Nihang Fu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, 29201, USA. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF, Division of Materials Research, National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Oxidation states (OS) are the charges on atoms due to electrons gained or lost upon applying an ionic approximation to their bonds. As a fundamental property, OS has been widely used in charge‐neutrality verification, crystal structure determination, and reaction estimation. Currently, only heuristic rules exist for guessing the oxidation states of a given compound with many exceptions. Recent work has developed machine learning models based on heuristic structural features for predicting the oxidation states of metal ions. However, composition‐based oxidation state prediction still remains elusive so far, which has significant implications for the discovery of new materials for which the structures have not been determined. This work proposes a novel deep learning‐based BERT transformer language model BERTOS for predicting the oxidation states for all elements of inorganic compounds given only their chemical composition. This model achieves 96.82% accuracy for all‐element oxidation states prediction benchmarked on the cleaned ICSD dataset and achieves 97.61% accuracy for oxide materials. It is also demonstrated how it can be used to conduct large‐scale screening of hypothetical material compositions for materials discovery.

Schlagwörter

Stichwörter der Autor:innen

deep learninglanguage modelmaterial discoverymaterial screeningneural networksoxidation statestransformer

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, University of South Carolina, Columbia, SC, 29201, USA.
  • Dutch Fork High School, Irmo, SC, 29063, USA.
  • Hangzhou University of Electronic Science and Technology, Hangzhou, 311305, China.
  • Department of Chemistry and Biochemistry, University of South Carolina, Columbia, SC, 29201, USA.

ORCID-Profile: Jianjun Hu

Förderung

  • NSF
  • Division of Materials Research
  • National Science Foundation

Zitieren

APA

Fu, N., Hu, J., Feng, Y., Morrison, G., Loye, H. Z., & Hu, J. (2023). Composition Based Oxidation State Prediction of Materials Using Deep Learning Language Models. Advanced Science, 10(28). https://doi.org/10.1002/advs.202301011

Vancouver

Fu N, Hu J, Feng Y, Morrison G, Loye HZ, Hu J. Composition Based Oxidation State Prediction of Materials Using Deep Learning Language Models. Advanced Science. 2023;10(28). doi:10.1002/advs.202301011

BibTeX
@article{Fu2023,
  author = {Fu, Nihang and Hu, Jeffrey and Feng, Ying and Morrison, Gregory and Loye, Hans-Conrad Zur and Hu, Jianjun},
  title = {Composition Based Oxidation State Prediction of Materials Using Deep Learning Language Models},
  journal = {Advanced Science},
  year = {2023},
  volume = {10},
  number = {28},
  doi = {10.1002/advs.202301011}
}
Kostenlos starten →