Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

General reactive element-based machine learning potentials for heterogeneous catalysis

Nature Catalysis volume 8, pages 891–904 (2025)Cite this article

Subjects

Abstract

Developing truly universal machine learning potentials for heterogeneous catalysis remains challenging. Here we introduce our element-based machine learning potential (EMLP), trained on a unique random exploration via imaginary chemicals optimization (REICO) sampling strategy. REICO samples diverse local atomic environments to build a representative dataset of atomic interactions, making the EMLP inherently general and reactive, capable of accurately predicting elementary reactions without explicit structural or reaction pathway inputs. We demonstrate the generality and reactivity of our approach by building a Ag-Pd-C-H-O EMLP targeting Pd–Ag catalysts interacting with C/H/O-containing species, achieving quantitative agreement with density functional theory even for complex scenarios such as surface reconstruction, coverage effects and solvent environments, cases for which existing foundation models typically fail. Our method paves the way to replace density functional theory calculations for large and intricate systems in heterogeneous catalysis, and offers a general framework that can readily be extended to other catalytic systems, and to broader fields such as materials science.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Summary of the REICO sampling, EMLP training workflow and applications.
Fig. 2: Analysis of the RECIO-generated dataset and dimer scan performance.
Fig. 3: Structural predictions from the EMLP and other foundation models in MD and surface adsorption.
Fig. 4: Reaction predictions of CO oxidation on various palladium and Pd/Ag surfaces.
Fig. 5: Reaction predictions of C2H2 hydrogenation (the stepwise addition of hydrogen atoms to C2H2 to form C2H6) on various palladium-based surfaces with coverage effect.
Fig. 6: Reaction predictions of an extended reaction pathway for the Fischer–Tropsch process on Pd(100).
Fig. 7: Additional benchmarks across solid, liquid and gas phases.

Similar content being viewed by others

Data availability

The Ag-Pd-C-H-O model and its training dataset are publicly available under the Ag-Pd-C-H-O EMLP from GitHub via https://github.com/HuGroup-shanghaiTech/REICO. Details are provided in the corresponding section in Methods. All the electronic structure calculations are available from Fisgshare via https://figshare.com/articles/dataset/electronic_structure_calculations/29484686 (ref. 61). Source data are provided with this paper.

Code availability

The REICO code is available from GitHub via https://github.com/HuGroup-shanghaiTech/REICO.

References

  1. Liu, Z.-P. & Hu, P. General rules for predicting where a catalytic reaction should occur on metal surfaces: a density functional theory study of C–H and C–O bond breaking/making on flat, stepped, and kinked metal surfaces. J. Am. Chem. Soc. 125, 1958–1967 (2003).

    Article  PubMed  CAS  Google Scholar 

  2. Alavi, A., Hu, P., Deutsch, T., Silvestrelli, P. L. & Hutter, J. CO oxidation on Pt(111): an ab initio density functional theory study. Phys. Rev. Lett. 80, 3650–3653 (1998).

    Article  CAS  Google Scholar 

  3. Oganov, A. R., Pickard, C. J., Zhu, Q. & Needs, R. J. Structure prediction drives materials discovery. Nat. Rev. Mater. 4, 331–348 (2019).

    Article  Google Scholar 

  4. Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007).

    Article  PubMed  Google Scholar 

  5. Behler, J. First principles neural network potentials for reactive simulations of large molecular and condensed systems. Angew. Chem. Int. Ed. 56, 12828–12840 (2017).

    Article  CAS  Google Scholar 

  6. Zuo, Y. et al. Performance and cost assessment of machine learning interatomic potentials. J. Phys. Chem. A 124, 731–745 (2020).

    Article  PubMed  CAS  Google Scholar 

  7. Huang, S.-D., Shang, C., Zhang, X.-J. & Liu, Z.-P. Material discovery by combining stochastic surface walking global optimization with a neural network. Chem. Sci. 8, 6327–6337 (2017).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  8. Ma, S., Shang, C. & Liu, Z.-P. Heterogeneous catalysis from structure to activity via SSW-NN method. J. Chem. Phys. 151, 050901 (2019).

    Article  Google Scholar 

  9. Wang, H., Zhang, L., Han, J. & E, W. DeePMD-kit: a deep learning package for many-body potential energy representation and molecular dynamics. Comput. Phys. Commun. 228, 178–184 (2018).

    Article  CAS  Google Scholar 

  10. Zhang, Y., Xia, J. & Jiang, B. Physically motivated recursively embedded atom neural networks: incorporating local completeness and nonlocality. Phys. Rev. Lett. 127, 156002 (2021).

    Article  PubMed  CAS  Google Scholar 

  11. Batzner, S. et al. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat. Commun. 13, 2453 (2022).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  12. Batatia, I. et al. The design space of E(3)-equivariant atom-centred interatomic potentials. Nat. Mach. Intell. 7, 56–67 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

  13. Young, T. A., Johnston-Wood, T., Deringer, V. L. & Duarte, F. A transferable active-learning strategy for reactive molecular force fields. Chem. Sci. 12, 10944–10955 (2021).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  14. Smith, J. S. et al. Automated discovery of a robust interatomic potential for aluminum. Nat. Commun. 12, 1257 (2021).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  15. Xu, J., Xie, W., Han, Y. & Hu, P. Atomistic insights into the oxidation of flat and stepped platinum surfaces using large-scale machine learning potential-based grand-canonical Monte Carlo. ACS Catal. 12, 14812–14824 (2022).

    Article  CAS  Google Scholar 

  16. Liu, Y. & Guo, H. A Gaussian process based Δ-machine learning approach to reactive potential energy surfaces. J. Phys. Chem. A 127, 8765–8772 (2023).

    Article  PubMed  CAS  Google Scholar 

  17. Nandi, A., Qu, C., Houston, P. L., Conte, R. & Bowman, J. M. Δ -machine learning for potential energy surfaces: a PIP approach to bring a DFT-based PES to CCSD(T) level of theory. J. Chem. Phys. 154, 051102 (2021).

    Article  PubMed  CAS  Google Scholar 

  18. Morrow, J. D., Gardner, J. L. A. & Deringer, V. L. How to validate machine-learned interatomic potentials. J. Chem. Phys. 158, 121501 (2023).

    Article  PubMed  CAS  Google Scholar 

  19. Smith, J. S., Nebgen, B., Lubbers, N., Isayev, O. & Roitberg, A. E. Less is more: sampling chemical space with active learning. J. Chem. Phys. 148, 241733 (2018).

    Article  PubMed  Google Scholar 

  20. Schran, C. et al. Machine learning potentials for complex aqueous systems made simple. Proc. Natl Acad. Sci. USA 118, e2110077118 (2021).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  21. Shi, Y.-F., Kang, P.-L., Shang, C. & Liu, Z.-P. Methanol synthesis from CO2/CO mixture on Cu–Zn catalysts from microkinetics-guided machine learning pathway search. J. Am. Chem. Soc. 144, 13401–13414 (2022).

    Article  PubMed  CAS  Google Scholar 

  22. Han, Y., Xu, J., Xie, W., Wang, Z. & Hu, P. Comprehensive study of oxygen vacancies on the catalytic performance of ZnO for CO/H2 activation using machine learning-accelerated first-principles simulations. ACS Catal. 13, 5104–5113 (2023).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  23. Han, Y., Xu, J., Xie, W., Wang, Z. & Hu, P. Unravelling the impact of metal dopants and oxygen vacancies on syngas conversion over oxides: a machine learning-accelerated study of CO activation on Cr-doped ZnO surfaces. ACS Catal. 13, 15074–15086 (2023).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  24. Deringer, V. L., Caro, M. A. & Csányi, G. Machine learning interatomic potentials as emerging tools for materials science. Adv. Mater. 31, 1902765 (2019).

    Article  CAS  Google Scholar 

  25. Luo, L.-H., Huang, S.-D., Shang, C. & Liu, Z.-P. Resolving activation entropy of CO oxidation under the solid–gas and solid–liquid conditions from machine learning simulation. ACS Catal. 12, 6265–6275 (2022).

    Article  CAS  Google Scholar 

  26. Xie, W., Xu, J., Ding, Y. & Hu, P. Quantitative studies of the key aspects in selective acetylene hydrogenation on Pd(111) by microkinetic modeling with coverage effects and molecular dynamics. ACS Catal. 11, 4094–4106 (2021).

    Article  CAS  Google Scholar 

  27. Xie, W., Xu, J., Chen, J., Wang, H. & Hu, P. Achieving theory–experiment parity for activity and selectivity in heterogeneous catalysis using microkinetic modeling. Acc. Chem. Res. 55, 1237–1248 (2022).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  28. Deng, B. et al. Systematic softening in universal machine learning interatomic potentials. NPJ Comput. Mater. 11, 9 (2025).

    Article  CAS  Google Scholar 

  29. Zeng, J., Cao, L., Xu, M., Zhu, T. & Zhang, J. Z. H. Complex reaction processes in combustion unraveled by neural network-based molecular dynamics simulation. Nat. Commun. 11, 5713 (2020).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  30. Schaaf, L. L., Fako, E., De, S., Schäfer, A. & Csányi, G. Accurate energy barriers for catalytic reaction pathways: an automatic training protocol for machine learning force fields. NPJ Comput. Mater. 9, 180 (2023).

    Article  Google Scholar 

  31. Bernstein, N., Csányi, G. & Deringer, V. L. De novo exploration and self-guided learning of potential-energy surfaces. NPJ Comput. Mater. 5, 99 (2019).

    Article  Google Scholar 

  32. Morrow, J. D. & Deringer, V. L. Indirect learning and physically guided validation of interatomic potential models. J. Chem. Phys. 157, 104105 (2022).

    Article  PubMed  CAS  Google Scholar 

  33. Zhang, S. et al. Exploring the frontiers of condensed-phase chemistry with a general reactive machine learning potential. Nat. Chem. 16, 727–734 (2024).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  34. Chiang, Y. & Benner, P. mace-universal (Revision e5ebd9b). Hugging Face https://doi.org/10.57967/hf/1202 (2023).

  35. Liao, Y.-L., Wood, B. M., Das, A. & Smidt, T. EquiformerV2: improved equivariant transformer for scaling to higher-degree representations. In Twelfth International Conference on Learning Representations (2024).

  36. Chen, C. & Ong, S. P. A universal graph deep learning interatomic potential for the periodic table. Nat. Comput. Sci. 2, 718–728 (2022).

    Article  PubMed  Google Scholar 

  37. Hauschild, A. et al. Normal-incidence X-ray standing-wave determination of the adsorption geometry of PTCDA on Ag(111): comparison of the ordered room-temperature and disordered low-temperature phases. Phys. Rev. B 81, 125432 (2010).

    Article  Google Scholar 

  38. Ruiz, V. G., Liu, W., Zojer, E., Scheffler, M. & Tkatchenko, A. Density-functional theory with screened van der Waals Interactions for the modeling of hybrid inorganic–organic systems. Phys. Rev. Lett. 108, 146103 (2012).

    Article  PubMed  Google Scholar 

  39. Eren, B. et al. Activation of Cu(111) surface by decomposition into nanoclusters driven by CO adsorption. Science 351, 475–478 (2016).

    Article  PubMed  CAS  Google Scholar 

  40. Xu, L. & Mavrikakis, M. Adsorbate-induced adatom formation on lithium, iron, cobalt, ruthenium, and rhenium surfaces. JACS Au 3, 2216–2225 (2023).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  41. Xie, W. & Hu, P. Influence of surface defects on activity and selectivity: a quantitative study of structure sensitivity of Pd catalysts for acetylene hydrogenation. Catal. Sci. Technol. 11, 5212–5222 (2021).

    Article  CAS  Google Scholar 

  42. Wu, J., Chen, D., Chen, J. & Wang, H. Structural and composition evolution of palladium catalyst for CO oxidation under steady-state reaction conditions. J. Phys. Chem. C 127, 6262–6270 (2023).

    Article  CAS  Google Scholar 

  43. Li, X.-T., Chen, L., Shang, C. & Liu, Z.-P. In situ surface structures of PdAg catalyst and their influence on acetylene semihydrogenation revealed by machine learning and experiment. J. Am. Chem. Soc. 143, 6281–6292 (2021).

    Article  PubMed  CAS  Google Scholar 

  44. Baker, J. & Chan, F. The location of transition states: a comparison of Cartesian, Z-matrix, and natural internal coordinates. J. Comput. Chem. 17, 888–904 (1996).

    Article  CAS  Google Scholar 

  45. Cordero, B. et al. Covalent radii revisited. Dalton Trans. https://doi.org/10.1039/B801115J (2008).

  46. Bartók, A. P., Kondor, R. & Csányi, G. On representing chemical environments. Phys. Rev. B 87, 184115 (2013).

    Article  Google Scholar 

  47. Behler, J. Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J. Chem. Phys. 134, 074106 (2011).

    Article  PubMed  Google Scholar 

  48. Thompson, A. P., Swiler, L. P., Trott, C. R., Foiles, S. M. & Tucker, G. J. Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials. J. Comput. Phys. 285, 316–330 (2015).

    Article  CAS  Google Scholar 

  49. Mahoney, M. W. & Drineas, P. CUR matrix decompositions for improved data analysis. Proc. Natl Acad. Sci. USA 106, 697–702 (2009).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  50. Harris, C. R. et al. Array programming with NumPy. Nature 585, 357–362 (2020).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  51. Kresse, G. & Furthmüller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. Rev. B 54, 11169–11186 (1996).

    Article  CAS  Google Scholar 

  52. Perdew, J. P. et al. Restoring the density-gradient expansion for exchange in solids and surfaces. Phys. Rev. Lett. 100, 136406 (2008).

    Article  PubMed  Google Scholar 

  53. Kresse, G. & Joubert, D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. Rev. B 59, 1758–1775 (1999).

    Article  CAS  Google Scholar 

  54. Grimme, S., Antony, J., Ehrlich, S. & Krieg, H. A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H–Pu. J. Chem. Phys. 132, 154104 (2010).

    Article  PubMed  Google Scholar 

  55. Thompson, A. P. et al. LAMMPS—a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Comput. Phys. Commun. 271, 108171 (2022).

    Article  CAS  Google Scholar 

  56. Steinhardt, P. J., Nelson, D. R. & Ronchetti, M. Bond-orientational order in liquids and glasses. Phys. Rev. B 28, 784–805 (1983).

    Article  CAS  Google Scholar 

  57. Menon, S., Leines, G. & Rogal, J. pyscal: a Python module for structural analysis of atomic environments. J. Open Source Softw. 4, 1824 (2019).

    Article  Google Scholar 

  58. Larsen, A. H. et al. The atomic simulation environment—a Python library for working with atoms. J. Phys. Condens. Matter 29, 273002 (2017).

    Article  Google Scholar 

  59. Wang, H.-F. & Liu, Z.-P. Comprehensive mechanism and structure-sensitivity of ethanol oxidation on platinum: new transition-state searching method for resolving the complex reaction network. J. Am. Chem. Soc. 130, 10996–11004 (2008).

    Article  PubMed  CAS  Google Scholar 

  60. Henkelman, G., Uberuaga, B. P. & Jónsson, H. A climbing image nudged elastic band method for finding saddle points and minimum energy paths. J. Chem. Phys. 113, 9901–9904 (2000).

    Article  CAS  Google Scholar 

  61. Xie, W. Electronic structure calculations. Figshare https://doi.org/10.6084/m9.figshare.29484686.v1 (2025).

Download references

Acknowledgements

The authors thank B. Jiang, G. Zhang and J. Xu for fruitful discussions. This work was supported by the NKRDPC (2021YFA1500700) and the National Natural Science Foundation of China NSFC (22433004 and 22403064) and ShanghaiTech University. We are also grateful for the computing time provided by the HPC Platform of ShanghaiTech University and the High-Performance Computing Center (HPCC) at Nanjing University.

Author information

Author notes

  1. These authors contributed equally: Changxi Yang, Chenyu Wu, Wenbo Xie.

Authors and Affiliations

  1. School of Physical Science and Technology, ShanghaiTech University, Shanghai, China

    Changxi Yang, Chenyu Wu, Wenbo Xie & P. Hu

  2. State Key Laboratory of Green Chemical Engineering and Industrial Catalysis, Centre for Computational Chemistry and Research Institute of Industrial Catalysis, School of Chemistry and Molecular Engineering, East China University of Science and Technology, Shanghai, China

    Changxi Yang

  3. Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing, China

    Chenyu Wu & Daiqian Xie

  4. School of Chemistry and Chemical Engineering, The Queen’s University of Belfast, Belfast, UK

    P. Hu

Authors
  1. Changxi Yang
    View author publications

    Search author on:PubMed Google Scholar

  2. Chenyu Wu
    View author publications

    Search author on:PubMed Google Scholar

  3. Wenbo Xie
    View author publications

    Search author on:PubMed Google Scholar

  4. Daiqian Xie
    View author publications

    Search author on:PubMed Google Scholar

  5. P. Hu
    View author publications

    Search author on:PubMed Google Scholar

Contributions

P.H. and W.X. conceived the project and guided the research the project. The REICO code was written by C.Y. The Ag-Pd-C-H-O EMLP was trained by C.Y. and C.W. performed the generality tests and trained the MD-MLP. C.Y. performed the validation case studies. C.Y., C.W., W.X., D.X. and H.P discussed the results. W.X. wrote the original draft of the manuscript and designed Figs. 1–3 and 5–7. C.Y. designed Fig. 4. D.X. and H.P. provided the computational resources. All authors edited and revised the manuscript.

Corresponding authors

Correspondence to Wenbo Xie or P. Hu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Catalysis thanks Brett Savoie and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Figs. 1–20, Tables 1–12, Notes 1–19 and References.

Source data

Source Data Fig. 1

Statistical Source Data.

Source Data Fig. 2

Statistical Source Data.

Source Data Fig. 3

Statistical Source Data.

Source Data Fig. 4

Statistical Source Data.

Source Data Fig. 5

Statistical Source Data.

Source Data Fig. 6

Statistical Source Data.

Source Data Fig. 7

Statistical Source Data.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, C., Wu, C., Xie, W. et al. General reactive element-based machine learning potentials for heterogeneous catalysis. Nat Catal 8, 891–904 (2025). https://doi.org/10.1038/s41929-025-01398-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41929-025-01398-3

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing