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.

  • Perspective
  • Published:

Role of the human-in-the-loop in emerging self-driving laboratories for heterogeneous catalysis

Nature Catalysis volume 8, pages 13–19 (2025)Cite this article

Subjects

Abstract

Self-driving laboratories (SDLs) represent a cutting-edge convergence of machine learning with laboratory automation. SDLs operate in active learning loops, in which a machine learning algorithm plans experiments that are subsequently executed by increasingly automated (robotic) modules. Here we present our view on emerging SDLs for accelerated discovery and process optimization in heterogeneous catalysis. We argue against the paradigm of full automation and the goal of keeping the human out of the loop. Based on analysis of the involved workflows, we instead conclude that crucial advances will come from establishing fast proxy experiments and re-engineering existing apparatuses and measurement protocols. Industrially relevant use cases will also require humans to be kept in the loop for continuous decision-making. In turn, active learning algorithms will have to be advanced that can flexibly deal with corresponding adaptations of the design space and varying information content and noise in the acquired data.

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: Active learning loops in catalyst discovery and process optimization.
Fig. 2: Role of the data-informed scientist in SDL loops.

Similar content being viewed by others

References

  1. Maier, W. F., Stöwe, K. & Sieg, S. Combinatorial and high-throughput materials science. Angew. Chem. Int. Ed. 46, 6016–6067 (2007).

    Article  CAS  Google Scholar 

  2. Potyrailo, R. et al. Combinatorial and high-throughput screening of materials libraries: review of state of the art. ACS Comb. Sci. 13, 579–633 (2011).

    Article  PubMed  CAS  Google Scholar 

  3. Stein, H. S. & Gregoire, J. M. Progress and prospects for accelerating materials science with automated and autonomous workflows. Chem. Sci. 10, 9640–9649 (2019).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  4. Toyao, T. et al. Machine learning for catalysis informatics: recent applications and prospects. ACS Catal. 10, 2260–2297 (2020).

    Article  CAS  Google Scholar 

  5. Terayama, K., Sumita, M., Tamura, R. & Tsuda, K. Black-box optimization for automated discovery. Acc. Chem. Res. 54, 1334–1346 (2021).

    Article  PubMed  CAS  Google Scholar 

  6. Peng, J. et al. Human- and machine-centred designs of molecules and materials for sustainability and decarbonization. Nat. Rev. Mater. 7, 991–1009 (2022).

    Article  Google Scholar 

  7. Margraf, J. T., Jung, H., Scheurer, C. & Reuter, K. Exploring catalytic reaction networks with machine learning. Nat. Catal. 6, 112–121 (2023).

    Article  Google Scholar 

  8. Lookman, T., Balachandran, P. V., Xue, D. & Yuan, R. Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design. NPJ Comp. Mater. 5, 21 (2019).

    Article  Google Scholar 

  9. Stach, E. et al. Autonomous experimentation systems for materials development: a community perspective. Matter 4, 2702–2726 (2021).

    Article  Google Scholar 

  10. Pacheco Gutierrez, D., Folkmann, L. M., Tribukait, H. & Roch, L. M. How to accelerate R&D and optimize experiment planning with machine learning and data science. Chimia 77, 7–16 (2023).

    Article  PubMed  Google Scholar 

  11. Tran, K. & Ulissi, Z. W. Active learning across intermetallics to guide discovery of electrocatalysts for CO2 reduction and H2 evolution. Nat. Catal. 1, 696–703 (2018).

    Article  CAS  Google Scholar 

  12. Jinnouchi, R., Miwa, K., Karsai, F., Kresse, G. & Asahi, R. On-the-fly active learning of interatomic potentials for large-scale atomistic simulations. J. Phys. Chem. Lett. 11, 6946–6955 (2020).

    Article  PubMed  CAS  Google Scholar 

  13. Kunkel, C., Margraf, J. T., Chen, K., Oberhofer, H. & Reuter, K. Active discovery of organic semiconductors. Nat. Commun. 12, 2422 (2021).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  14. Mou, T. et al. Bridging the complexity gap in computational heterogeneous catalysis with machine learning. Nat. Catal. 6, 122–136 (2023).

    Article  Google Scholar 

  15. Jung, H., Sauerland, L., Stocker, S., Reuter, K. & Margraf, J. T. Machine-learning driven global optimization of surface adsorbate geometries. NPJ Comp. Mater. 9, 114 (2023).

    Article  Google Scholar 

  16. Kavalsky, L. et al. By how much can closed-loop frameworks accelerate computational materials discovery? Digit. Discov. 2, 1112–1125 (2023).

    Article  CAS  Google Scholar 

  17. Stein, H. & Gregoire, J. Progress and prospects for accelerating materials science with automated and autonomous workflows. Chem. Sci. 10, 9640–9649 (2019).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  18. Ramirez, A. et al. Accelerated exploration of heterogeneous CO2 hydrogenation catalysts by Bayesian-optimized high-throughput and automated experimentation. Chem. Catal. 4, 100888 (2024).

    Article  CAS  Google Scholar 

  19. Kunkel, C. et al. Systematic exploration of a multi-promoter catalyst composition space with limited experiments: non-oxidative propane dehydrogenation to propylene. ACS Catal. 14, 9008 (2024).

    Article  CAS  Google Scholar 

  20. Suvarna, M. et al. Active learning streamlines development of high performance catalysts for higher alcohol synthesis. Nat. Commun. 15, 5844 (2024).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  21. Tom, G. et al. Self-driving laboratories for chemistry and materials science. Chem. Rev. 124, 9633–9732 (2024).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  22. Sanchez-Lengeling, B. & Aspuru-Guzik, A. Inverse molecular design using machine learning: generative models for matter engineering. Science 361, 360–365 (2018).

    Article  PubMed  CAS  Google Scholar 

  23. Segler, M., Preuss, M. & Waller, M. Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555, 604–610 (2018).

    Article  PubMed  CAS  Google Scholar 

  24. Granda, J., Donina, L., Dragone, V., Long, D.-L. & Cronin, L. Controlling an organic synthesis robot with machine learning to search for new reactivity. Nature 559, 377–381 (2018).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  25. Coley, C. W. et al. A robotic platform for flow synthesis of organic compounds informed by AI planning. Science 365, eaax1566 (2019).

    Article  PubMed  CAS  Google Scholar 

  26. MacLeod, B. P. et al. Self-driving laboratory for accelerated discovery of thin-film materials. Sci. Adv. 6, eaaz8867 (2020).

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  27. Burger, B. et al. A mobile robotic chemist. Nature 583, 237–241 (2020).

    Article  PubMed  CAS  Google Scholar 

  28. Trunschke, A. et al. Towards experimental handbooks in catalysis. Top. Catal. 63, 1683–1699 (2020).

    Article  CAS  Google Scholar 

  29. Zhao, Z.-J. et al. Theory-guided design of catalytic materials using scaling relationships and reactivity descriptors. Nat. Rev. Mater. 4, 792–804 (2019).

    Article  Google Scholar 

  30. Mai, H., Le, T. C., Chen, D., Winkler, D. A. & Caruso, R. A. Machine learning for electrocatalyst and photocatalyst design and discovery. Chem. Rev. 122, 13478–13515 (2022).

    Article  PubMed  CAS  Google Scholar 

  31. Mou, L. H., Han, T., Smith, P. E. S., Sharman, E. & Jiang, J. Machine learning descriptors for data-driven catalysis study. Adv. Sci. 10, e2301020 (2023).

    Article  Google Scholar 

  32. Kumar, B., Dikshit, O., Gupta, A. & Singh, M. K. Feature extraction for hyperspectral image classification: a review. Int. J. Remote Sens. 41, 6248–6287 (2020).

    Article  Google Scholar 

  33. Gierlich, C. & Palkovits, S. Featurizing chemistry for machine learning—methods and a coded example. Curr. Opin. Chem. Eng. 37, 100840 (2022).

    Article  Google Scholar 

  34. Taniike, T., Fujiwara, A., Nakanowatari, S., García-Escobar, F. & Takahashi, K. Automatic feature engineering for catalyst design using small data without prior knowledge of target catalysis. Commun. Chem. 7, 1–8 (2024).

    Article  Google Scholar 

  35. Li, Z., Ludwig, A., Savan, A., Springer, H. & Raabe, D. Combinatorial metallurgical synthesis and processing of high-entropy alloys. J. Mater. Res. 33, 3156–3169 (2018).

    Article  CAS  Google Scholar 

  36. Trapp, O. Boosting the throughput of separation techniques by “multiplexing”. Angew. Chem. Int. Ed. 46, 5609–5613 (2007).

    Article  CAS  Google Scholar 

  37. Wang, K. & Dowling, A. W. Bayesian optimization for chemical products and functional materials. Curr. Opin. Chem. Eng. 36, 100728 (2022).

    Article  Google Scholar 

  38. Fedorov, V. V., Studden, W. J. & Klimko, E. M. Theory of Optimal Experiments (Academic Press, 1972).

  39. Chaloner, K. & Verdinelli, I. Bayesian experimental design: a review. Stat. Sci. 10, 273–304 (1995).

    Article  Google Scholar 

  40. Fedorov, V. Optimal experimental design. Wiley Interdiscip. Rev. Comput. Stat. 2, 581–589 (2010).

    Article  Google Scholar 

  41. Esterhuizen, J. A., Goldsmith, B. R. & Linic, S. Interpretable machine learning for knowledge generation in heterogeneous catalysis. Nat. Catal. 5, 175–184 (2022).

    Article  Google Scholar 

  42. Xin, H., Mou, T., Pillai, H. S., Wang, S.-H. & Huang, Y. Interpretable machine learning for catalytic materials design toward sustainability. Acc. Mater. Res. 5, 22–34 (2024).

    Article  CAS  Google Scholar 

  43. Markou, M. & Singh, S. Novelty detection: a review—part 1: statistical approaches. Signal Proc. 83, 2481–2497 (2003).

    Article  Google Scholar 

  44. Markou, M. & Singh, S. Novelty detection: a review—part 2: neural network based approaches. Signal Proc. 83, 2499–2521 (2003).

    Article  Google Scholar 

  45. Von Stosch, M., Oliveira, R., Peres, J. & Feyo de Azevedo, S. Hybrid semi-parametric modeling in process systems engineering: past, present and future. Comp. Chem. Eng. 60, 86–101 (2014).

    Article  Google Scholar 

  46. Asrav, T. & Aydin, E. Physics-informed recurrent neural networks and hyper-parameter optimization for dynamic process systems. Comp. Chem. Eng. 173, 108195 (2023).

    Article  CAS  Google Scholar 

  47. Herwig, C., Pörtner, R. & Möller, J. Digital Twins: Applications to the Design and Optimization of Bioprocesses 1st edn (Springer, 2021).

  48. Hodge, V. & Austin, J. A survey of outlier detection methodologies. Artif. Int. Rev. 22, 85–126 (2004).

    Article  Google Scholar 

  49. ur Rehman, A. & Belhaouari, S. B. Unsupervised outlier detection in multidimensional data. J. Big Data 8, 80 (2021).

    Article  Google Scholar 

  50. Stier, S. et al. Materials acceleration platforms (MAPs): accelerating materials research and development to meet urgent societal challenges. Adv. Mater. 36, 2407791 (2024).

    Article  CAS  Google Scholar 

  51. Canty, R., Koscher, B., McDonald, M. & Jensen, K. Integrating autonomy into automated research platforms. Digit. Discov. 2, 1259–1268 (2023).

    Article  Google Scholar 

  52. MacLeod, B., Parlane, F., Brown, A., Hein, J. & Berlinguette, C. Flexible automation accelerates materials discovery. Nat. Mater. 21, 722–726 (2022).

    Article  PubMed  CAS  Google Scholar 

  53. Marshall, C., Schumann, J. & Trunschke, A. Achieving digital catalysis: strategies for data acquisition, storage and use. Angew. Chem. Int. Ed. 62, e202302971 (2023).

    Article  CAS  Google Scholar 

  54. Hysmith, H. et al. The future of self-driving laboratories: from human in the loop interactive AI to gamification. Digit. Discov. 3, 621–636 (2024).

    Article  Google Scholar 

  55. Asprey, S. P. & Macchietto, S. Statistical tools for optimal dynamic model building. Comp. Chem. Eng. 24, 1261–1267 (2000).

    Article  CAS  Google Scholar 

  56. Möller, J., Kuchemüller, K. B., Steinmetz, T., Koopmann, K. S. & Pörtner, R. Model-assisted design of experiments as a concept for knowledge-based bioprocess development. Bioprocess Biosyst. Eng. 42, 867–882 (2019).

    Article  PubMed  Google Scholar 

  57. Bayer, B., Diaz, R. D., Melcher, M., Striedner, G. & Duerkop, M. Digital twin application for model-based DoE to rapidly identify ideal process conditions for space-time yield optimization. Processes 9, 1109 (2021).

    Article  Google Scholar 

  58. Vanaret, C. et al. Two-phase approaches to optimal model-based design of experiments: how many experiments and which ones? Comp. Chem. Eng. 146, 107218 (2021).

    Article  CAS  Google Scholar 

  59. Le Riche, R., Mohammadi, H., Durrande, N., Touboul, E. & Bay, X. A comparison of regularization methods for Gaussian processes. In Proc. 12th SIAM Conference on Optimization (Society for Industrial and Applied Mathematics, 2017).

  60. Mohammadi, H., Riche, R. L., Durrande, N., Touboul, E. & Bay, X. An analytic comparison of regularization methods for Gaussian processes. Preprint at https://doi.org/10.48550/arXiv.1602.00853 (2017).

  61. Konakovic Lukovic, M., Tian, Y. & Matusik, W. Diversity-guided multi-objective Bayesian optimization with batch evaluations. Adv. Neural Inf. Proc. Syst. 33, 17708–17720 (2020).

    Google Scholar 

  62. Chen, J., Luo, F., Li, G. & Wang, Z. Batch Bayesian optimization with adaptive batch acquisition functions via multi-objective optimization. Swarm Evol. Comput. 79, 101293 (2023).

    Article  Google Scholar 

  63. Ren, J. & Sweet, D. Optimal initialization of batch Bayesian optimization. Preprint at https://doi.org/10.48550/arXiv.2404.17997 (2024).

  64. Daulton, S., Eriksson, D., Balandat, M. & Bakshy, E. Multi-objective Bayesian optimization over high-dimensional search spaces. In Proc. 38th Conference on Uncertainty in Artificial Intelligence Vol. 180, 507–517 (PMLR, 2022).

Download references

Acknowledgements

We acknowledge support from the Federal Ministry of Education and Research in Germany with the framework of the project CatLab (03EW0015B), as well as from the German Research Foundation for funding through DFG Cluster of Excellence e-conversion EXC 2089/1. We thank our experimental colleagues within CatLab and the BasCat (UniCat BASF JointLab) with whom we have started to implement the ideas delineated in this Perspective. We also thank S. Kangowski for skillful assistance with the graphics.

Author information

Authors and Affiliations

  1. Fritz-Haber-Institut der Max-Planck-Gesellschaft, Berlin, Germany

    Christoph Scheurer & Karsten Reuter

Authors
  1. Christoph Scheurer
    View author publications

    Search author on:PubMed Google Scholar

  2. Karsten Reuter
    View author publications

    Search author on:PubMed Google Scholar

Contributions

Both authors contributed to writing the manuscript.

Corresponding author

Correspondence to Karsten Reuter.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Catalysis thanks Federico Galvanin and Jason Hattrick-Simpers 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.

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

Scheurer, C., Reuter, K. Role of the human-in-the-loop in emerging self-driving laboratories for heterogeneous catalysis. Nat Catal 8, 13–19 (2025). https://doi.org/10.1038/s41929-024-01275-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41929-024-01275-5

This article is cited by

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