Artificial-intelligence-assisted design principle for developing high-performance single-atom catalysts

Liangliang Xu; Xingkun Wang; Xiaojuan Hu; Yue Wang; Canhui Zhang; Wenwu Xu; Wenhui Zhao; Ning Xu; Dongyoon Woo; Hanxu Yao; Xiaofan Li; Heqing Jiang; Minghua Huang; Jinwoo Lee; Xiao Cheng Zeng; Zhong-Kang Han

doi:10.1016/j.xinn.2025.100911

Artificial-intelligence-assisted design principle for developing high-performance single-atom catalysts

Liangliang Xu (Co-first Author)
, Xingkun Wang (Co-first Author)
, Xiaojuan Hu (Co-first Author)
, Yue Wang (Co-first Author)
, Canhui Zhang
, Wenwu Xu
, Wenhui Zhao
, Ning Xu
, Dongyoon Woo
, Hanxu Yao
, Xiaofan Li
, Heqing Jiang
, Minghua Huang^*
, Jinwoo Lee^*
, Xiao Cheng Zeng^*
, Zhong-Kang Han^*

^*Corresponding author for this work

Department of Materials Science and Engineering

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

27 Citations (Scopus)

56 Downloads (CityUHK Scholars)

Abstract

Artificial intelligence (AI)-assisted approaches are powerful means for advancing catalyst design, as they can significantly accelerate the development of novel catalysts. However, the underlying mechanisms of these approaches often remain elusive, which may lead to unreliable results due to a lack of clear understanding of the involved processes. Herein, we present an AI strategy that combines machine learning (ML) and data mining (DM) to identify high-performance catalysts while elucidating the key factors that govern catalytic performance in complex reactions. Applying this AI strategy to evaluate the electrocatalytic oxygen reduction performance of 10,179 single-atom catalysts (SACs), we identified several high-performance SACs and determined the critical influencers of their activity. Experimental validations further confirm the effectiveness of the AI strategy, with the optimal target Co-S₂N₂/g-SAC achieving a high half-wave potential of 0.92 V. This AI-assisted approach significantly enhances the transparency and reliability of data-driven discoveries, providing new insights that benefit the rational design of materials. © 2025 The Author(s).

Original language	English
Article number	100911
Number of pages	10
Journal	Innovation(United States)
Volume	6
Issue number	7
Online published	17 Apr 2025
DOIs	https://doi.org/10.1016/j.xinn.2025.100911
Publication status	Online published - 17 Apr 2025

Funding

This work was supported by the National Key Research and Development Program of China (2023YFA1506902), the National Nature Science Foundation of China (U23A2086, 22302173, and 52261145700), the Leading Innovative and Entrepreneur Team Introduction Program of Zhejiang (2023R01007), the Qingdao New Energy Shandong Laboratory Open Project (QNESL OP202307), the Fundamental Research for the Central University, and National Research Foundation of Korea (NRF) grants funded by the Korean government (RS-2023-00243788 and RS-2023-00235596). X.C.Z. acknowledges support from the Hong Kong Global STEM Professorship Scheme and the Guangdong Basic and Applied Basic Research Foundation (2024A1515012307).

Research Keywords

artificial intelligence
data mining
machine learning
oxygen reduction reaction
single-atom catalysts

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-ND 4.0. https://creativecommons.org/licenses/by-nc-nd/4.0/

Access Output

10.1016/j.xinn.2025.100911

282815467.pdfFinal Published version, 2.3 MBLicence: CC BY-NC-ND

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Xu, L., Wang, X., Hu, X., Wang, Y., Zhang, C., Xu, W., Zhao, W., Xu, N., Woo, D., Yao, H., Li, X., Jiang, H., Huang, M., Lee, J., Zeng, X. C., & Han, Z.-K. (2025). Artificial-intelligence-assisted design principle for developing high-performance single-atom catalysts. Innovation(United States), 6(7), Article 100911. Advance online publication. https://doi.org/10.1016/j.xinn.2025.100911

@article{a61aca423594472d831112c258c5fc8a,

title = "Artificial-intelligence-assisted design principle for developing high-performance single-atom catalysts",

abstract = "Artificial intelligence (AI)-assisted approaches are powerful means for advancing catalyst design, as they can significantly accelerate the development of novel catalysts. However, the underlying mechanisms of these approaches often remain elusive, which may lead to unreliable results due to a lack of clear understanding of the involved processes. Herein, we present an AI strategy that combines machine learning (ML) and data mining (DM) to identify high-performance catalysts while elucidating the key factors that govern catalytic performance in complex reactions. Applying this AI strategy to evaluate the electrocatalytic oxygen reduction performance of 10,179 single-atom catalysts (SACs), we identified several high-performance SACs and determined the critical influencers of their activity. Experimental validations further confirm the effectiveness of the AI strategy, with the optimal target Co-S2N2/g-SAC achieving a high half-wave potential of 0.92 V. This AI-assisted approach significantly enhances the transparency and reliability of data-driven discoveries, providing new insights that benefit the rational design of materials. {\textcopyright} 2025 The Author(s).",

keywords = "artificial intelligence, data mining, machine learning, oxygen reduction reaction, single-atom catalysts",

author = "Liangliang Xu and Xingkun Wang and Xiaojuan Hu and Yue Wang and Canhui Zhang and Wenwu Xu and Wenhui Zhao and Ning Xu and Dongyoon Woo and Hanxu Yao and Xiaofan Li and Heqing Jiang and Minghua Huang and Jinwoo Lee and Zeng, \{Xiao Cheng\} and Zhong-Kang Han",

year = "2025",

month = apr,

day = "17",

doi = "10.1016/j.xinn.2025.100911",

language = "English",

volume = "6",

journal = "Innovation(United States)",

issn = "2666-6758",

publisher = "Cell Press",

number = "7",

}

Artificial-intelligence-assisted design principle for developing high-performance single-atom catalysts. / Xu, Liangliang (Co-first Author); Wang, Xingkun (Co-first Author); Hu, Xiaojuan (Co-first Author) et al.
In: Innovation(United States), Vol. 6, No. 7, 100911, 17.04.2025.

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

TY - JOUR

T1 - Artificial-intelligence-assisted design principle for developing high-performance single-atom catalysts

AU - Xu, Liangliang

AU - Wang, Xingkun

AU - Hu, Xiaojuan

AU - Wang, Yue

AU - Zhang, Canhui

AU - Xu, Wenwu

AU - Zhao, Wenhui

AU - Xu, Ning

AU - Woo, Dongyoon

AU - Yao, Hanxu

AU - Li, Xiaofan

AU - Jiang, Heqing

AU - Huang, Minghua

AU - Lee, Jinwoo

AU - Zeng, Xiao Cheng

AU - Han, Zhong-Kang

PY - 2025/4/17

Y1 - 2025/4/17

N2 - Artificial intelligence (AI)-assisted approaches are powerful means for advancing catalyst design, as they can significantly accelerate the development of novel catalysts. However, the underlying mechanisms of these approaches often remain elusive, which may lead to unreliable results due to a lack of clear understanding of the involved processes. Herein, we present an AI strategy that combines machine learning (ML) and data mining (DM) to identify high-performance catalysts while elucidating the key factors that govern catalytic performance in complex reactions. Applying this AI strategy to evaluate the electrocatalytic oxygen reduction performance of 10,179 single-atom catalysts (SACs), we identified several high-performance SACs and determined the critical influencers of their activity. Experimental validations further confirm the effectiveness of the AI strategy, with the optimal target Co-S2N2/g-SAC achieving a high half-wave potential of 0.92 V. This AI-assisted approach significantly enhances the transparency and reliability of data-driven discoveries, providing new insights that benefit the rational design of materials. © 2025 The Author(s).

AB - Artificial intelligence (AI)-assisted approaches are powerful means for advancing catalyst design, as they can significantly accelerate the development of novel catalysts. However, the underlying mechanisms of these approaches often remain elusive, which may lead to unreliable results due to a lack of clear understanding of the involved processes. Herein, we present an AI strategy that combines machine learning (ML) and data mining (DM) to identify high-performance catalysts while elucidating the key factors that govern catalytic performance in complex reactions. Applying this AI strategy to evaluate the electrocatalytic oxygen reduction performance of 10,179 single-atom catalysts (SACs), we identified several high-performance SACs and determined the critical influencers of their activity. Experimental validations further confirm the effectiveness of the AI strategy, with the optimal target Co-S2N2/g-SAC achieving a high half-wave potential of 0.92 V. This AI-assisted approach significantly enhances the transparency and reliability of data-driven discoveries, providing new insights that benefit the rational design of materials. © 2025 The Author(s).

KW - artificial intelligence

KW - data mining

KW - machine learning

KW - oxygen reduction reaction

KW - single-atom catalysts

UR - https://www.scopus.com/pages/publications/105004242095

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105004242095&origin=recordpage

U2 - 10.1016/j.xinn.2025.100911

DO - 10.1016/j.xinn.2025.100911

M3 - RGC 21 - Publication in refereed journal

C2 - 40697790

SN - 2666-6758

VL - 6

JO - Innovation(United States)

JF - Innovation(United States)

IS - 7

M1 - 100911

ER -

Artificial-intelligence-assisted design principle for developing high-performance single-atom catalysts

Abstract

Funding

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this