Transformer-generated atomic embeddings to enhance prediction accuracy of crystal properties with machine learning

Luozhijie Jin, Zijian Du, Le Shu, Yan Cen (), Yuanfeng Xu, Yongfeng Mei and Hao Zhang ()
Additional contact information
Luozhijie Jin: Fudan University
Zijian Du: Fudan University
Le Shu: Fudan University
Yan Cen: Fudan University
Yuanfeng Xu: Shandong Jianzhu University
Yongfeng Mei: Fudan University
Hao Zhang: Fudan University

Nature Communications, 2025, vol. 16, issue 1, 1-11

Abstract: Abstract Accelerating the discovery of novel crystal materials by machine learning is crucial for advancing various technologies from clean energy to information processing. The machine-learning models for prediction of materials properties require embedding atomic information, while traditional methods have limited effectiveness in enhancing prediction accuracy. Here, we proposed an atomic embedding strategy called universal atomic embeddings (UAEs) for their broad applicability as atomic fingerprints, and generated the UAE tensors based on the proposed CrystalTransformer model. By performing experiments on widely-used materials database, our CrystalTransformer-based UAEs (ct-UAEs) are shown to accurately capture complex atomic features, leading to a 14% improvement in prediction accuracy on CGCNN and 18% on ALIGNN when using formation energies as the target, based on the Materials Project database. We also demonstrated the good transferability of ct-UAEs across various databases. Based on the clustering analysis for multi-task ct-UAEs, the elements in the periodic table can be categorized with reasonable connections between atomic features and targeted crystal properties. After applying ct-UAEs to predict formation energy in hybrid perovskites database, we realized an improvement in accuracy, with a 34% boost in MEGNET and 16% in CGCNN, showcasing their potential as atomic fingerprints to address the data scarcity challenges.

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-56481-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-56481-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-56481-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().