High‐Throughput Screening and Interpretable Machine Learning for Rational Design of Bimetallic Catalysts for Methane Activation
Advanced Science · 14.03.2026
DOI: 10.1002/advs.202524394 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 14.03.2026. Verfasst von Mingzhang Pan und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical Engineering, Guangxi University, Nanning, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Shaanxi Province, Shaanxi Sanqin Scholars Fund Project.
Abstract (Originalsprache)
Methane's efficient catalytic removal is vital for sustainable development. Bimetallic catalysts, though promising for methane activation, pose a design challenge due to their complex compositional space. This work introduces an integrated framework that combines high‐throughput density functional theory (DFT) and interpretable machine learning to accelerate the rational design of catalysts. Computational screening of face‐centered‐cubic (FCC) bimetallic catalyst surfaces identifies the bond cleavage energies of the first and the second C─H bonds and methyl adsorption energy as a key descriptor governing successive C─H activation and the shift in the rate‐determining step (RDS). Through the synergistic interaction of these descriptors, machine learning models can be constructed more effectively, leading to the discovery of a bimetallic catalyst for consecutive C─H bond cleavages that outperforms conventional natural gas engine aftertreatment systems. Based on the computationally derived DFT dataset, four machine learning models were trained using a particle swarm optimisation (PSO) algorithm, from which the optimal model capable of accurately predicting C─H bond energies was selected. This model also further revealed the dominant electronic structural features of the predictive model through SHapley additive interpretability (SHAP) analysis. This work establishes an interpretable, data‐driven methodology for designing high‐efficiency multicomponent catalysts.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Mechanical Engineering, Guangxi University, Nanning, China.
- Guangxi Institute of Artificial Intelligence, Guangxi University, Nanning, China.
- State Key Laboratory of Engines, Tianjin University, Tianjin, China.
- School of Chemistry, Engineering Research Center of Energy Storage Materials and Devices of Ministry of Education, National Innovation Platform (Center) for Industry-Education Integration of Energy Storage Technology, X…
ORCID-Profile: Yaqiong Su
Förderung
- National Natural Science Foundation of China
- Key Research and Development Program of Shaanxi Province
- Shaanxi Sanqin Scholars Fund Project
- Science and Technology Major Project of Guangxi
Zitieren
APA
Pan, M., Zhang, T., Dong, J., Xie, Y., Zhong, K., Guan, W., Wei, H., Fu, C., & Su, Y. (2026). High‐Throughput Screening and Interpretable Machine Learning for Rational Design of Bimetallic Catalysts for Methane Activation. Advanced Science. https://doi.org/10.1002/advs.202524394
Vancouver
Pan M, Zhang T, Dong J, Xie Y, Zhong K, Guan W, et al. High‐Throughput Screening and Interpretable Machine Learning for Rational Design of Bimetallic Catalysts for Methane Activation. Advanced Science. 2026. doi:10.1002/advs.202524394
BibTeX
@article{Pan2026,
author = {Pan, Mingzhang and Zhang, Tian and Dong, Jiawei and Xie, Yubao and Zhong, Kaifeng and Guan, Wei and Wei, Haiqiao and Fu, Changcheng and Su, Yaqiong},
title = {High‐Throughput Screening and Interpretable Machine Learning for Rational Design of Bimetallic Catalysts for Methane Activation},
journal = {Advanced Science},
year = {2026},
doi = {10.1002/advs.202524394}
}
EUVIMED