Same but different: how permutation degeneracy enhances machine learning in single-atom catalyst discovery

Zhengda Chen; Jianhua Wang; Xueqiang Fan; Guoxin Zhang; Yupeng Wei; Mengxiao Han; Yuhong Huang; Yongfeng Wang; Haiping Lin

doi:10.1039/d5ta09024e

Same but different: how permutation degeneracy enhances machine learning in single-atom catalyst discovery

Journal of Materials Chemistry A 2026

View at publisher

Authors: Zhengda Chen, Jianhua Wang, Xueqiang Fan, Guoxin Zhang, Yupeng Wei, Mengxiao Han, Yuhong Huang, Yongfeng Wang, Haiping Lin

DOI: 10.1039/d5ta09024e

Cited by: 2

References: 40

Abstract

Incorporating structural permutation degeneracy into machine learning descriptors significantly improves the accuracy and generalizability of catalytic activity predictions in single-atom catalysts.

Fields of Study & Subjects

Machine Learning in Materials Science Electrocatalysts for Energy Conversion CO2 Reduction Techniques and Catalysts

Publication details

Journal / source: Journal of Materials Chemistry A
Publisher: Royal Society of Chemistry (RSC)
Volume: 14
Issue: 17
Pages: 10101–10109
Publication date: 1 January 2026
Language: EN

References 40