Unveiling high-performance single-atom alloy catalysts for alkane dehydrogenation through DFT and machine learning synergy

Unveiling high-performance single-atom alloy catalysts for alkane dehydrogenation through DFT and machine learning synergy

Journal of Catalysis

10.1016/j.jcat.2025.116213

https://doi.org/10.1016/j.jcat.2025.116213

Haisong Feng, Zhen Ge, Yuan Deng, Pengxin Pu, Shiquan Zhao, Xin Song, Hao Yuan, Yaze Wu, Jing Yang, Yubing Si, Antonio Politano, Xin Zhang, Yong-Wei Zhang

12 May 2025

Feng, H., Ge, Z., Deng, Y., Pu, P., Zhao, S., Song, X., Yuan, H., Wu, Y., Yang, J., Si, Y., Politano, A., Zhang, X., & Zhang, Y.-W. (2025). Unveiling high-performance single-atom alloy catalysts for alkane dehydrogenation through DFT and machine learning synergy. Journal of Catalysis, 448, 116213. https://doi.org/10.1016/j.jcat.2025.116213

The recent surge in shale gas production has renewed interest in efficient alkane dehydrogenation for the synthesis of fuels and high-value chemicals. However, developing cost-effective catalysts that exhibit high catalytic activity while minimizing over-dehydrogenation and carbon deposition remains a significant challenge. Here, we integrate density functional theory (DFT) calculations with machine learning (ML) to design single-atom alloy (SAA) catalysts for efficient alkane dehydrogenation. Using DFT, we calculate 92 Csingle bondH bond disassociation energy barriers to construct a dataset, which is used to train eight ML algorithms with 12 features. The top-performing Bagging Regression (BAR) model is then employed to predict Csingle bondH bond activation energy barriers on the surfaces of 53 SAA candidates, enabling rapid screening of methane dehydrogenation activity. Among these, the Ru1Cu SAA catalyst exhibits outstanding activity, outperforming pure Pt. Detailed DFT calculations confirm that Ru1Cu(111) not only exhibits superior performance in methane dehydrogenation, but also exceptional activity in the dehydrogenation of propane, ethane, and isobutane. Moreover, microkinetic simulations further confirm the high selectivity of the Ru1Cu(111) surface toward propylene during propane dehydrogenation. Feature engineering analyses reveal the critical roles of dehydrogenation steps and the surface energy of the single-atom metal in influencing Csingle bondH bond activation. These findings underscore the effectiveness of the DFT–ML framework for catalyst discovery and highlight Ru1Cu SAA as a highly active, selective, and stable catalyst with strong resistance to over-dehydrogenation and carbon deposition, making it a highly promising candidate for alkane dehydrogenation.

Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

This research / project is supported by the Agency for Science, Technology and Research - Italy-Singapore Science and Technology Cooperation
Grant Reference no. : R23101R040

This research / project is supported by the Agency for Science, Technology and Research - Science and Engineering Research Council - Central Research Fund
Grant Reference no. : NA

https://oar.a-star.edu.sg/communities-collections/articles/21849

0021-9517

Institute of High Performance Computing