Page 24 - Read Online

Liu et al. J. Mater. Inf. 2025, 5, 27 Journal of materials
DOI: 10.20517/jmi.2024.105 Informatics

Research Article Open Access

FT DP: large atomic model fine-tuned machine learn-
2
ing potential for accelerating atomistic simulation of
iron-based Fischer-Tropsch synthesis

3
2
4
Zhao-Qing Liu 1,# , Zhe Deng 1,# , Huabo Zhao , Han Wang , Mohan Chen , Hong Jiang 1,*
1 Beijing National Laboratory for Molecular Sciences, College of Chemistry and Molecular Engineering, Peking University, Beijing
100871, China.
2 National Institute of Clean and Low Carbon Energy, Beijing 102211, China.
3 Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics, Beijing 100088, China.
4 HEDPS, CAPT, College of Engineering, Peking University, Beijing 100871, China.
# Authors contributed equally.

* Correspondence to: Prof. Hong Jiang, Beijing National Laboratory for Molecular Sciences, College of Chemistry and
Molecular Engineering, Peking University, No.292 Chengfu Road, Beijing 100871, China. E-mail: jianghchem@pku.edu.cn
2
How to cite this article: Liu, Z. Q.; Deng, Z.; Zhao, H.; Wang, H.; Chen, M.; Jiang, H. FT DP: large atomic model fine-tuned ma-
chine learning potential for accelerating atomistic simulation of iron-based Fischer-Tropsch synthesis. J. Mater. Inf. 2025, 5, 27.
http://dx.doi.org/10.20517/jmi.2024.105
Received: 31 Dec 2024 First Decision: 23 Jan 2025 Revised: 28 Feb 2025 Accepted: 5 Mar 2025 Published: 26 Mar 2025

Academic Editor: Hao Li Copy Editor: Pei-Yun Wang Production Editor: Pei-Yun Wang

Abstract
Density-functional theory (DFT)-based atomistic simulation methods have been essential in studying the structure-
property relationships in heterogeneous catalysis. However, for complex catalytic processes, such as iron-based
Fischer-Tropsch synthesis (FTS), the temporal or spatial scales involved are generally too large to perform DFT cal-
culations. Recently, the development of machine learning potentials (MLPs) has demonstrated the capability for
atomistic simulation on a large scale and long duration, and the rise of large atomic models (LAMs) is gaining much
attention with unified descriptors incorporating a wide range of chemical knowledge and fine-tuning methodology
for efficiently deploying the model to downstream tasks. In this work, we construct a MLP named fine-tuned Fischer-
2
Tropsch deep potential (FT DP) model, which is fine-tuned from upstream DPA-2 LAM on a downstream dataset
focused on the iron-based FTS process. We further applied this model to investigate iron-based FTS in both surface
reactions and reconstructions of edge sites combined with the double-to-single transition state optimization method
and the local genetic algorithm. Our work demonstrated the capability and efficiency of our model for iron-based
FTS simulations, while revealing the reaction mechanism on common active sites containing [Fe 4C] squares, and the

© The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, shar-
ing, adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as long as you
give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate
if changes were made.

www.oaepublish.com/jmi