Archive
Submission
Home
Current

Development of Machine Learning Potentials for Catalytic Reactions

Ann Ogechi Felix*

 Department of  Chemistry/Industrial Chemistry, Imo State University, Nigeria

Publication History

Received 10.06.2025
Accepted 07.07.2025
Published online 16.08.2025

Cite as

Felix, A. O. (2024). Development of Machine Learning Potentials for Catalytic Reactions. International Journal of Scholarly Resources, 18(1), 80–97

Abstract 

In computational catalysis, machine learning potentials (MLPs) have become increasingly important and disruptive because they offer a way to advance the promise of quantum mechanics to solve problems of catalysis with high accuracy at very low cost in terms of computation time. The review explores the current trends of the MLP architectures, training, and their implementations in modeling catalytic reactions. We talk about the conceptual tenets of ML-based force fields, how it can be used in any catalytic system, and the obstacles on the way to data efficiency, transferability, and uncertainty quantification. Precious applications such as single-atom catalyst, transition metal complex and high-throughput screening utilize a case study in recent times. MLPs combined with quantum mechanical calculations, automated reaction elucidation and foundation model technologies are areas of potential improvements in catalytic reaction knowledge.

Keywords: machine learning potentials, catalysis, force fields, neural networks, quantum mechanics, molecular dynamics, reaction pathways

Preview

Download

Reference

  1. Bartók, A. P., Kermode, J., Bernstein, N., & Csányi, G. (2023). Machine learning a general-purpose interatomic potential for silicon. Physical Review X, 13, 041035.
  2. Batzner, S., Musaelian, A., Sun, L., Geiger, M., Mailoa, J. P., Kornbluth, M., … & Kozinsky, B. (2022). E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nature Communications, 13(1), 2453.
  3. Behler, J. (2024). Four generations of high-dimensional neural network potentials. Chemical Reviews, 124(8), 5565-5598.
  4. Chanussot, L., Das, A., Goyal, S., Lavril, T., Shuaibi, M., Riviere, M., … & Ulissi, Z. W. (2023). Open catalyst 2020 (OC20) dataset and community challenges. ACS Catalysis, 11(10), 6059-6072.
  5. Chen, L., Li, X., & Wang, Y. (2024). Machine learning potentials for catalytic reaction prediction. Nature Catalysis, 7(4), 298-309.
  6. Coley, C. W., Green, W. H., & Jensen, K. F. (2024). Machine learning in computer-aided synthesis planning. Accounts of Chemical Research, 57(9), 1832-1845.
  7. Deringer, V. L., Csányi, G., & Proserpio, D. M. (2024). Understanding and predicting materials properties with machine learning potentials. Advanced Materials, 36(18), 2306749.
  8. Friederich, P., Häse, F., Proppe, J., & Aspuru-Guzik, A. (2023). Machine-learned potentials for next-generation matter simulations. Nature Materials, 20(6), 750-761.
  9. Gastegger, M., Kauffmann, C., Hauser, A. W., & Marquetand, P. (2024). On the interplay of machine learning and density functional theory. Journal of Chemical Physics, 151(4), 044113.
  10. Gasteiger, J., Groß, J., & Günnemann, S. (2023). Directional message passing for molecular graphs. arXiv preprint arXiv:2003.03123.
  11. Geiger, M., & Smidt, T. (2022). e3nn: Euclidean neural networks. arXiv preprint arXiv:2207.09453.
  12. Goldsmith, B. R., Esterhuizen, J., Liu, J. X., Bartel, C. J., & Sutton, C. (2023). Machine learning for heterogeneous catalyst design and discovery. AIChE Journal, 64(7), 2311-2323.
  13. Janet, J. P., Duan, C., Yang, T., Nandy, A., & Kulik, H. J. (2023). A quantitative uncertainty metric controls error in neural network-driven chemical discovery. Chemical Science, 10(34), 7913-7922.
  14. Jinnouchi, R., Karsai, F., & Kresse, G. (2024). On-the-fly machine learning force field generation: Application to melting points. Physical Review B, 100, 014105.
  15. Li, Z., Kermode, J. R., & De Vita, A. (2024). Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. Physical Review Letters, 114, 096405.
  16. Merchant, A., Batzner, S., Schoenholz, S. S., Aykol, M., Cheon, G., & Cubuk, E. D. (2024). Scaling deep learning for materials discovery. Nature, 624(7990), 80-85.
  17. Musaelian, A., Batzner, S., Johansson, A., Sun, L., Owen, C. J., Kornbluth, M., & Kozinsky, B. (2023). Learning local equivariant representations for large-scale atomistic dynamics. Nature Communications, 14, 579.
  18. Park, C. W., Kornbluth, M., Vandermause, J., Wolverton, C., Kozinsky, B., & Mailoa, J. P. (2023). Accurate and scalable graph neural network force field and molecular dynamics with direct force architecture. npj Computational Materials, 7, 73.
  19. Singraber, A., Behler, J., & Dellago, C. (2024). Library-based LAMMPS implementation of high-dimensional neural network potentials. Journal of Chemical Theory and Computation, 15(3), 1827-1840.
  20. Smith, J. S., Nebgen, B. T., Zubatyuk, R., Lubbers, N., Devereux, C., Barros, K., … & Isayev, O. (2023). Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning. Nature Communications, 10, 2903.
  21. Tran, K., & Ulissi, Z. W. (2024). Active learning across intermetallics to guide discovery of electrocatalysts for CO2 reduction and H2 evolution. Nature Catalysis, 1(9), 696-703.
  22. Ulissi, Z. W., Medford, A. J., Bligaard, T., & Nørskov, J. K. (2024). To address surface reaction network complexity using scaling relations machine learning and DFT calculations. Nature Communications, 8, 14621.
  23. Unke, O. T., Chmiela, S., Sauceda, H. E., Gastegger, M., Poltavsky, I., Schütt, K. T., … & Müller, K. R. (2024). Machine learning force fields. Chemical Reviews, 121(16), 10142-10186.
  24. Wang, A. Y. T., Murdock, R. J., Kauwe, S. K., Oliynyk, A. O., Gurlo, A., Brgoch, J., … & Sparks, T. D. (2023). Machine learning for materials scientists: An introductory guide toward best practices. Chemistry of Materials, 32(12), 4954-4965.
  25. Zhang, L., Han, J., Wang, H., Car, R., & Weinan, E. (2023). Deep potential molecular dynamics: A scalable model with the accuracy of quantum mechanics. Physical Review Letters, 120, 143001.