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:

Interpretable machine learning-guided plasma catalysis for hydrogen production

Nature Chemical Engineering volume 2, pages 699–710 (2025)Cite this article

Subjects

Abstract

Low-carbon ammonia decomposition via nonthermal plasma is a promising method for on-site hydrogen production, but finding optimal catalysts is challenging. Here we use multiscale simulations to link catalytic activity to nitrogen adsorption energy (EN) and identify the best catalysts for conventional heating and nonthermal plasma: Ru and Co, respectively. With an ideal EN of −0.51 eV for plasma catalysis, we applied machine learning to screen 3,300+ catalysts and designed efficient, earth-abundant alloys such as Fe3Cu, Ni3Mo, Ni7Cu and Fe15Ni. Plasma catalytic experiments at 400 °C further validated that the above alloys achieved higher conversions than the individual metals, and they also have comparable performance to Co. Our techno-economic analysis demonstrated potential economic benefits of plasma catalytic ammonia decomposition over Ni3Mo, highlighting a H2 production cost below the US$1 per kg H2 target and a low carbon footprint of ~0.91 kg of CO2 per kg H2.

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

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

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

Fig. 1: BEP relationship between activation energy and reaction energy for NH3 decomposition over flat catalyst surfaces.
Fig. 2: Multiscale simulations for NH3 decomposition across various catalysts under the conditions of thermal heating only.
Fig. 3: MKM results in plasma catalytic ammonia decomposition.
Fig. 4: Interpretable machine learning (ML) model for predicting EN over bimetallic surfaces.
Fig. 5: Experimental validation of NH3 decomposition under heating only and NTP conditions.
Fig. 6: Comparative TEA and carbon footprint analysis for NH3 decomposition under thermal and NTP conditions.

Similar content being viewed by others

Data availability

Source data are provided with this paper. Data used for developing MKM, machine learning models, experimental work and TEA are available in Supplementary Data 1.

Code availability

The microkinetic models and the machine learning algorithms are included as Python modules, and data files used to create all the plots are provided in Supplementary Data 1.

References

  1. Global CO2 Emissions from Transport by Sub-sector in the Net Zero Scenario, 2000–2030 (International Energy Agency, 2022); https://www.iea.org/data-and-statistics

  2. Anika, O. C. et al. Prospects of low and zero-carbon renewable fuels in 1.5-degree net zero emission actualisation by 2050: a critical review. Carbon Capture Sci. Technol. 5, 100072 (2022).

    CAS  Google Scholar 

  3. Griffiths, S. & Uratani, J. Zero and low-carbon ammonia shipping fuel. Glob. Energy 28, 46–58 (2022).

    Google Scholar 

  4. Bagheri, S., Bagheri, H. & Rahimpour, M. R. in Progresses in Ammonia: Science, Technology and Membranes (eds Basile, A. & Rahimpour, M.R.) 281–305 (Elsevier, 2024).

  5. Cheddie, D. in Hydrogen Energy-Challenges and Perspectives (ed. Minić, D.) Ch. 13 (IntechOpen, 2012).

  6. Lin, L. et al. Techno-economic analysis and comprehensive optimization of an on-site hydrogen refuelling station system using ammonia: hybrid hydrogen purification with both high H2 purity and high recovery. Sustain. Energy Fuels 4, 3006–3017 (2020).

    Article  CAS  Google Scholar 

  7. Panić, I., Cuculić, A. & Ćelić, J. Color-coded hydrogen: production and storage in maritime sector. J. Mar. Sci. Eng. 10, 1995 (2022).

    Article  Google Scholar 

  8. Hansgen, D. A., Vlachos, D. G. & Chen, J. G. Using first principles to predict bimetallic catalysts for the ammonia decomposition reaction. Nat. Chem. 2, 484–489 (2010).

    Article  PubMed  CAS  Google Scholar 

  9. Yin, S.-F., Xu, B.-Q., Ng, C.-F. & Au, C.-T. Nano Ru/CNTs: a highly active and stable catalyst for the generation of COx-free hydrogen in ammonia decomposition. Appl. Catal. B 48, 237–241 (2004).

    Article  CAS  Google Scholar 

  10. Su, T. et al. Review on Ru-based and Ni-based catalysts for ammonia decomposition: research status, reaction mechanism, and perspectives. Energy Fuels 37, 8099–8127 (2023).

    Article  CAS  Google Scholar 

  11. Verschoor, J. C., de Jongh, P. E. & Ngene, P. Recent advances in thermocatalytic ammonia synthesis & decomposition. Curr. Opin. Green Sustain. Chem. 50, 100965 (2024).

    Article  CAS  Google Scholar 

  12. Bayer, B. N., Bhan, A. & Bruggeman, P. J. Reaction pathways and energy consumption in NH3 decomposition for H2 production by low temperature, atmospheric pressure plasma. Plasma Chem. Plasma Process. 44, 1–18 (2024).

    Article  Google Scholar 

  13. Salehabadi, A., Zanganeh, J. & Moghtaderi, B. Mixed metal oxides in catalytic ammonia cracking process for green hydrogen production: a review. Int. J. Hydrogen Energy 63, 828–843 (2024).

    Article  CAS  Google Scholar 

  14. Kidnay, A. J., Parrish, W. R. & McCartney, D. G. in Fundamentals of Natural Gas Processing (eds Kidnay, A. J. et al.) Ch. 6 (CRC Press, 2019).

  15. Andersen, J. et al. Ammonia decomposition in a dielectric barrier discharge plasma: insights from experiments and kinetic modeling. Chem. Eng. Sci. 271, 118550 (2023).

    Article  CAS  Google Scholar 

  16. Neyts, E. C., Ostrikov, K., Sunkara, M. K. & Bogaerts, A. Plasma catalysis: synergistic effects at the nanoscale. Chem. Rev. 115, 13408–13446 (2015).

    Article  PubMed  CAS  Google Scholar 

  17. Lefferts, L. Leveraging expertise in thermal catalysis to understand plasma catalysis. Angew. Chem. Int. Ed. 136, e202305322 (2024).

    Article  Google Scholar 

  18. Gao, H. et al. Plasma-activated mist: continuous-flow, scalable nitrogen fixation, and aeroponics. ACS Sustain. Chem. Eng. 11, 4420–4429 (2023).

    Article  CAS  Google Scholar 

  19. Zhu, N., Hong, Y., Qian, F. & Liang, J. Research progress on plasma-catalytic hydrogen production from ammonia: Influencing factors and reaction mechanism. Int. J. Hydrogen Energy 59, 791–807 (2024).

    Article  CAS  Google Scholar 

  20. Mehta, P. et al. Plasma-catalytic ammonia synthesis beyond the equilibrium limit. ACS Catal. 10, 6726–6734 (2020).

    Article  CAS  Google Scholar 

  21. Wang, L., Zhao, Y., Liu, C., Gong, W. & Guo, H. Plasma driven ammonia decomposition on a Fe-catalyst: eliminating surface nitrogen poisoning. Chem. Commun. 49, 3787–3789 (2013).

    Article  CAS  Google Scholar 

  22. El-Shafie, M., Kambara, S. & Hayakawa, Y. Plasma-enhanced catalytic ammonia decomposition over ruthenium (Ru/Al2O3) and soda glass (SiO2) materials. J. Energy Inst. 99, 145–153 (2021).

    Article  CAS  Google Scholar 

  23. Meng, S. et al. NH3 decomposition for H2 production by thermal and plasma catalysis using bimetallic catalysts. Chem. Eng. Sci. 283, 119449 (2024).

    Article  CAS  Google Scholar 

  24. Katebah, M. & Linke, P. Analysis of hydrogen production costs in Steam-Methane Reforming considering integration with electrolysis and CO2 capture. Cleaner Eng. Technol. 10, 100552 (2022).

    Article  Google Scholar 

  25. Andersen, J., Christensen, J., Østberg, M., Bogaerts, A. & Jensen, A. Plasma-catalytic ammonia decomposition using a packed-bed dielectric barrier discharge reactor. Int. J. Hydrogen Energy 47, 32081–32091 (2022).

    Article  CAS  Google Scholar 

  26. Mehta, P. et al. Overcoming ammonia synthesis scaling relations with plasma-enabled catalysis. Nat. Catal. 1, 269–275 (2018).

    Article  Google Scholar 

  27. Laidler, K. J. & King, M. C. The development of transition-state theory. J. Phys. Chem. 87, 2657–2664 (1983).

    Article  CAS  Google Scholar 

  28. Truhlar, D. G., Garrett, B. C. & Klippenstein, S. J. Current status of transition-state theory. J. Phys. Chem. 100, 12771–12800 (1996).

    Article  CAS  Google Scholar 

  29. Abild-Pedersen, F. et al. Scaling properties of adsorption energies for hydrogen-containing molecules on transition-metal surfaces. Phys. Rev. Lett. 99, 016105 (2007).

    Article  PubMed  CAS  Google Scholar 

  30. Guo, W. & Vlachos, D. G. Patched bimetallic surfaces are active catalysts for ammonia decomposition. Nat. Commun. 6, 8619 (2015).

    Article  PubMed  CAS  Google Scholar 

  31. Wolcott, C. A., Medford, A. J., Studt, F. & Campbell, C. T. Degree of rate control approach to computational catalyst screening. J. Catal. 330, 197–207 (2015).

    Article  CAS  Google Scholar 

  32. Yang, Y., Achar, S. K. & Kitchin, J. R. Evaluation of the degree of rate control via automatic differentiation. AIChE J. 68, e17653 (2022).

    Article  CAS  Google Scholar 

  33. Winter, L. R. & Chen, J. G. N2 fixation by plasma-activated processes. Joule 5, 300–315 (2021).

    Article  CAS  Google Scholar 

  34. Fridman, A. & Kennedy, L. A. in Plasma Physics and Engineering (eds Fridman, A. & Kennedy, L. A.) Ch. 3 (CRC Press, 2004).

  35. Bayer, B. N., Bruggeman, P. J. & Bhan, A. Species, pathways, and timescales for NH3 formation by low-temperature atmospheric pressure plasma catalysis. ACS Catal 13, 2619–2630 (2023).

    Article  CAS  Google Scholar 

  36. Ma, H. et al. Observation and rationalization of nitrogen oxidation enabled only by coupled plasma and catalyst. Nat. Commun. 13, 402 (2022).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  37. Hammer, B. & Nørskov, J. K. Electronic factors determining the reactivity of metal surfaces. Surf. Sci. 343, 211–220 (1995).

    Article  CAS  Google Scholar 

  38. Artrith, N., Lin, Z. & Chen, J. G. Predicting the activity and selectivity of bimetallic metal catalysts for ethanol reforming using machine learning. ACS Catal 10, 9438–9444 (2020).

    Article  CAS  Google Scholar 

  39. Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. In Proc. Advances in Neural Information Processing Systems Vol. 30 4765–4774 (Curran Associates, 2017).

  40. Bonizzoni, G. & Vassallo, E. Plasma physics and technology; industrial applications. Vacuum 64, 327–336 (2002).

    Article  CAS  Google Scholar 

  41. Mayyas, A. T., Ruth, M. F., Pivovar, B. S., Bender, G. & Wipke, K. B. Manufacturing Cost Analysis for Proton Exchange Membrane Water Electrolyzers (National Renewable Energy Laboratory, 2019).

  42. Renewable Power Generation Costs in 2022 (International Renewable Energy Agency, 2022); https://www.irena.org/Publications/2023/Aug/Renewable-Power-Generation-Costs-in-2022

  43. McNaul, S. et al. Strategies for Achieving the DOE Hydrogen Shot Goal: Thermal Conversion Approaches (National Energy Technology Laboratory, 2023); https://www.netl.doe.gov

  44. Bogaerts, A. & Neyts, E. C. Plasma technology: an emerging technology for energy storage. ACS Energy Lett. 3, 1013–1027 (2018).

    Article  CAS  Google Scholar 

  45. Araújo, K., Koerner, C., Carcas, F., Hampshire, J. & Peterson, K. An Assessment of Policies and Regional Diversification with Energy, Critical Minerals and Economic Development in Emerging Markets (US Department of Energy, 2023).

  46. Kresse, G. & Furthmüller, J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. Mater. Sci. 6, 15–50 (1996).

    Article  CAS  Google Scholar 

  47. Kresse, G. & Hafner, J. Norm-conserving and ultrasoft pseudopotentials for first-row and transition elements. J. Phys. Condens. Matter 6, 8245 (1994).

    Article  CAS  Google Scholar 

  48. Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865 (1996).

    Article  PubMed  CAS  Google Scholar 

  49. Wan, M., Yue, H., Notarangelo, J., Liu, H. & Che, F. Deep learning-assisted investigation of electric field–dipole effects on catalytic ammonia synthesis. JACS Au 2, 1338–1349 (2022).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  50. Wittreich, G. R., Alexopoulos, K. & Vlachos, D. G. in Handbook of Materials Modeling: Applications: Current and Emerging Materials (eds Andreoni, W. & Yip, S.) 1377–1404 (Springer, 2020).

  51. Prats, H., Illas, F. & Sayos, R. General concepts, assumptions, drawbacks, and misuses in kinetic Monte Carlo and microkinetic modeling simulations applied to computational heterogeneous catalysis. Int. J. Quantum Chem. 118, e25518 (2018).

    Article  Google Scholar 

  52. Biondo, O. et al. Insights into the limitations to vibrational excitation of CO2: validation of a kinetic model with pulsed glow discharge experiments. Plasma Sources Sci. Technol. 31, 074003 (2022).

    Article  CAS  Google Scholar 

  53. Bron, J. & Wolfsberg, M. Effect of vibrational anharmonicity on hydrogen-deuterium exchange equilibria involving ammonia molecules. J. Chem. Phys 57, 2862–2869 (1972).

    Article  CAS  Google Scholar 

  54. Fridman, A. in Plasma Chemistry (ed. Fridman, A.) Ch. 3 (Cambridge Univ. Press, 2008).

  55. Hamilton, R. I. & Papadopoulos, P. N. Using SHAP values and machine learning to understand trends in the transient stability limit. IEEE Trans. Power Syst. 39, 1384–1397 (2023).

    Article  Google Scholar 

  56. Mastropietro, A., Feldmann, C. & Bajorath, J. Calculation of exact Shapley values for explaining support vector machine models using the radial basis function kernel. Sci. Rep. 13, 19561 (2023).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  57. Winther, K. T. et al. Catalysis-Hub.org, an open electronic structure database for surface reactions. Sci. Data 6, 75 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

F.C., S.A.I. and C.M. acknowledge the support provided by the Department of Energy, Basic Energy Science, Catalysis Science, Early Career Research Program under award number DE-SC0024553. F.C., Q.L., Y.L. and J.Y. acknowledge the support by the Department of Energy, Fusion Energy Science, under award number DE-SC0025553 for developing the mechanism of plasma-induced radical–surface interactions and DFT-free machine learning workflow. F.C., S.A.I. and C.M. extend their thanks for the computational resources provided by Unity at Massachusetts Green High Performance Computing Center (MGHPCC), as well as the San Diego Supercomputer Center at University of California San Diego, and the Texas A&M High Performance Research Computing FASTER cluster, through allocation numbers CHM220074 and CHE200076 from the Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support (ACCESS) program. This research used the resources of the National Energy Research Scientific Computing Center (NERSC), a US Department of Energy Office of Science User Facility supported by the Office of Science of the US Department of Energy under contract number DE-AC02-05CH11231 using NERSC awards BES-ERCAP0027465 and BES-ERCAP0028368. Y.Y. acknowledges financially support by the National Natural Science Foundation of China (grant numbers 22472018, 22272015 and 21503032), Y.Y., S.M. and Y.S. acknowledge support from Frontier Science Center for Smart Materials and assistance from Instrumental Analysis Center (X. Gao), Dalian University of Technology for characterization of the catalysts. We acknowledge H. Liu for helpful discussions.

Author information

Author notes

  1. These authors contributed equally: Saleh Ahmat Ibrahim, Shengyan Meng.

Authors and Affiliations

  1. Department of Chemical Engineering, University of Massachusetts Lowell, Lowell, MA, USA

    Saleh Ahmat Ibrahim, Charles Milhans, Yilang Liu, Qiang Li, Jiaqi Yang & Fanglin Che

  2. Department of Chemical Engineering, Worcester Polytechnic Institute, Worcester, MA, USA

    Saleh Ahmat Ibrahim, Jiaqi Yang & Fanglin Che

  3. State Key Laboratory of Fine Chemicals, Frontier Science Center for Smart Materials, School of Chemical Engineering, Dalian University of Technology, Dalian, China

    Shengyan Meng, Yabing Sha & Yanhui Yi

  4. Department of Chemical Engineering, Northeastern University, Boston, MA, USA

    Magda H. Barecka

  5. Department of Chemistry and Chemical Biology, Northeastern University, Boston, MA, USA

    Magda H. Barecka

Authors
  1. Saleh Ahmat Ibrahim
    View author publications

    Search author on:PubMed Google Scholar

  2. Shengyan Meng
    View author publications

    Search author on:PubMed Google Scholar

  3. Charles Milhans
    View author publications

    Search author on:PubMed Google Scholar

  4. Magda H. Barecka
    View author publications

    Search author on:PubMed Google Scholar

  5. Yilang Liu
    View author publications

    Search author on:PubMed Google Scholar

  6. Qiang Li
    View author publications

    Search author on:PubMed Google Scholar

  7. Jiaqi Yang
    View author publications

    Search author on:PubMed Google Scholar

  8. Yabing Sha
    View author publications

    Search author on:PubMed Google Scholar

  9. Yanhui Yi
    View author publications

    Search author on:PubMed Google Scholar

  10. Fanglin Che
    View author publications

    Search author on:PubMed Google Scholar

Contributions

S.A.I., Y.L. and Q.L. performed the multiscale simulations and developed the MKM. S.M. and Y.S. conducted catalyst synthesis, characterization and ammonia decomposition experiments. C.M. and J.Y. developed machine learning models. M.H.B. carried out the TEA and helped to analyze the data. Y.Y. directed the experimental validation project and assisted with analysis of both the experimental and theoretical data. F.C. developed the idea of the project, supervised the study, contributed to theory and machine learning model development, helped to analyze both the theoretical and experimental data, and managed the project. All authors contributed to writing and editing the paper.

Corresponding authors

Correspondence to Yanhui Yi or Fanglin Che.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Chemical Engineering thanks the anonymous reviewers 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.

Extended data

Extended Data Fig. 1 Machine learning model and screening workflow for bimetallic surface design.

(a) Schematic of the Random Forest (RF) model to predict EN, utilizing d-band information and solid-state properties of bimetallic surfaces. Key features include d-band descriptors (filling, center, width, skewness, and kurtosis up to the Fermi level), local Pauling electronegativity (reflecting delocalized sp-states), and metal-specific physical constants (spatial extent of d-orbitals, squared adsorbate-metal d coupling matrix element, work function, atomic radius, ionization potential, electron affinity, and Pauling electronegativity). (b) Screening workflow used to evaluate over 3,300 bimetallic alloy compositions based on ML-predicted d-band fillings and nitrogen adsorption energy.

Supplementary information

Supplementary Information

Supplementary Figs. 1–43, Tables 1–38 and Notes 1–10.

Supplementary Data 1

Atomic coordinates of all the DFT models.

Supplementary Code 2

Python scripts and input files for machine learning-based screening and MKM.

Source data

Source Data Fig. 1

Source data for Fig. 1.

Source Data Fig. 2

Source data for Fig. 2.

Source Data Fig. 3

Source data for Fig. 3.

Source Data Fig. 4

Source data for Fig. 4.

Source Data Fig. 5

Source data for Fig. 5.

Source Data Fig. 6

Source data for Fig. 6.

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

Ahmat Ibrahim, S., Meng, S., Milhans, C. et al. Interpretable machine learning-guided plasma catalysis for hydrogen production. Nat Chem Eng 2, 699–710 (2025). https://doi.org/10.1038/s44286-025-00287-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s44286-025-00287-7

This article is cited by

Search

Advanced search

Quick links

Nature Briefing AI and Robotics

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

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