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:

Autonomous reaction Pareto-front mapping with a self-driving catalysis laboratory

Nature Chemical Engineering volume 1, pages 240–250 (2024)Cite this article

Subjects

Abstract

Ligands play a crucial role in enabling challenging chemical transformations with transition metal-mediated homogeneous catalysts. Despite their undisputed role in homogeneous catalysis, discovery and development of ligands have proven to be a challenging and resource-intensive undertaking. Here, in response, we present a self-driving catalysis laboratory, Fast-Cat, for autonomous and resource-efficient parameter space navigation and Pareto-front mapping of high-temperature, high-pressure, gas–liquid reactions. Fast-Cat enables autonomous ligand benchmarking and multi-objective catalyst performance evaluation with minimal human intervention. Specifically, we utilize Fast-Cat to perform rapid Pareto-front identification of the hydroformylation reaction between syngas (CO and H2) and olefin (1-octene) in the presence of rhodium and various classes of phosphorus-based ligands. By reactor benchmarking, we demonstrate Fast-Cat’s knowledge scalability, essential to fine/specialty chemical industries. We report the details of the modular flow chemistry platform of Fast-Cat and its autonomous experiment-selection strategy for the rapid generation of optimized experimental conditions and in-house data required for supplying machine-learning approaches to reaction and ligand investigations.

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: Schematic of the developed self-driving catalysis lab technology.
Fig. 2: Overview of the Fast-Cat’s automated experimental-selection workflow using the multi-objective Bayesian optimization technique.
Fig. 3: Autonomous normal and iso aldehyde Pareto-front mapping of L1 by Fast-Cat.
Fig. 4: Autonomous Pareto-front mapping of different tested ligands by Fast-Cat.
Fig. 5: ML-assisted assessment of the ligand effect in hydroformylation of 1-octene.

Similar content being viewed by others

Data availability

The authors declare that all data supporting the findings of this study are available within the main text and Supplementary Information.

Code availability

The source code for the Pareto-front mapping and digital twin models have been deposited in the repository ‘Fast-Cat’ (https://github.com/AbolhasaniLab).

References

  1. Franke, R., Selent, D. & Börner, A. Applied hydroformylation. Chem. Rev. 112, 5675–5732 (2012).

    CAS  PubMed  Google Scholar 

  2. Whiteker, G. T. & Cobley, C. J. in Organometallics as Catalysts in the Fine Chemical Industry 35–46 (Springer, 2012).

  3. Botteghi, C., Paganelli, S., Schionato, A. & Marchetti, M. The asymmetric hydroformylation in the synthesis of pharmaceuticals. Chirality 3, 355–369 (1991).

    CAS  PubMed  Google Scholar 

  4. Stanley, G. G. in Kirk‐Othmer Encyclopedia of Chemical Technology 1–19 (Wiley, 2017).

  5. Vilches-Herrera, M., Domke, L. & Börner, A. Isomerization–hydroformylation tandem reactions. ACS Catal. 4, 1706–1724 (2014).

    CAS  Google Scholar 

  6. Klein, H., Jackstell, R., Wiese, K. D., Borgmann, C. & Beller, M. Highly selective catalyst systems for the hydroformylation of internal olefins to linear aldehydes. Angew. Chem. Int. Ed. 40, 3408–3411 (2001).

    CAS  Google Scholar 

  7. Seayad, A. et al. Internal olefins to linear amines. Science 297, 1676 (2002).

    ADS  CAS  PubMed  Google Scholar 

  8. Yan, Y., Zhang, X. & Zhang, X. A tetraphosphorus ligand for highly regioselective isomerization–hydroformylation of internal olefins. J. Am. Chem. Soc. 128, 16058–16061 (2006).

    CAS  PubMed  Google Scholar 

  9. Breit, B. & Seiche, W. Hydrogen bonding as a construction element for bidentate donor ligands in homogeneous catalysis: regioselective hydroformylation of terminal alkenes. J. Am. Chem. Soc. 125, 6608–6609 (2003).

    CAS  PubMed  Google Scholar 

  10. van der Veen, L. A., Kamer, P. C. & van Leeuwen, P. W. Hydroformylation of internal olefins to linear aldehydes with novel rhodium catalysts. Angew. Chem. Int. Ed. 38, 336–338 (1999).

    Google Scholar 

  11. Jiao, Y., Torne, M. S., Gracia, J., Niemantsverdriet, J. H. & van Leeuwen, P. W. Ligand effects in rhodium-catalyzed hydroformylation with bisphosphines: steric or electronic? Catal. Sci. Technol. 7, 1404–1414 (2017).

    CAS  Google Scholar 

  12. Van Leeuwen, P. W. & Claver, C. Rhodium Catalyzed Hydroformylation Vol. 22 (Springer, 2002).

  13. Zhu, C. et al. Flow chemistry-enabled studies of rhodium-catalyzed hydroformylation reactions. ChemComm 54, 8567–8570 (2018).

    CAS  Google Scholar 

  14. Raghuvanshi, K. et al. Highly efficient 1-octene hydroformylation at low syngas pressure: from single-droplet screening to continuous flow synthesis. ACS Catal. 10, 7535–7542 (2020).

    CAS  Google Scholar 

  15. Van Rooy, A., de Bruijn, J. N., Roobeek, K. F., Kamer, P. C. & Van Leeuwen, P. W. Rhodium-catalysed hydroformylation of branched 1-alkenes; bulky phosphite vs. triphenylphosphine as modifying ligand. J. Organomet. Chem. 507, 69–73 (1996).

    Google Scholar 

  16. van Rooy, A., Orij, E. N., Kamer, P. C. & van Leeuwen, P. W. Hydroformylation with a rhodium/bulky phosphite modified catalyst. A comparison of the catalyst behavior for oct-1-ene, cyclohexene, and styrene. Organometallics 14, 34–43 (1995).

    Google Scholar 

  17. Diebolt, O., Tricas, H., Freixa, Z. & van Leeuwen, P. W. Strong π-acceptor ligands in rhodium-catalyzed hydroformylation of ethene and 1-octene: operando catalysis. ACS Catal. 3, 128–137 (2013).

    CAS  Google Scholar 

  18. Vogl, C., Paetzold, E., Fischer, C. & Kragl, U. Highly selective hydroformylation of internal and terminal olefins to terminal aldehydes using a rhodium-BIPHEPHOS-catalyst system. J. Mol. Catal. A 232, 41–44 (2005).

    CAS  Google Scholar 

  19. Kamer, P. C. J., van Leeuwen, P. W. N. M. & Reek, J. N. H. Wide bite angle diphosphines: Xantphos ligands in transition metal complexes and catalysis. Acc. Chem. Res. 34, 895–904 (2001).

    CAS  PubMed  Google Scholar 

  20. Ichihara, T., Nakano, K., Katayama, M. & Nozaki, K. Tandem hydroformylation–hydrogenation of 1-decene catalyzed by Rh-bidentate bis(trialkylphosphine)s. Asian J. Chem. 3, 1722–1728 (2008).

    CAS  Google Scholar 

  21. Fuchs, E., Keller, M. & Breit, B. Phosphabarrelenes as ligands in rhodium‐catalyzed hydroformylation of internal alkenes essentially free of alkene isomerization. Chem. Eur. J. 12, 6930–6939 (2006).

    CAS  PubMed  Google Scholar 

  22. Kuil, M., Soltner, T., van Leeuwen, P. W. & Reek, J. N. High-precision catalysts: regioselective hydroformylation of internal alkenes by encapsulated rhodium complexes. J. Am. Chem. Soc. 128, 11344–11345 (2006).

    CAS  PubMed  Google Scholar 

  23. Besset, T., Norman, D. W. & Reek, J. N. Supramolecular encapsulated rhodium catalysts for branched selective hydroformylation of alkenes at high temperature. Adv. Synth. Catal. 355, 348–352 (2013).

    CAS  Google Scholar 

  24. Gao, H. et al. Using machine learning to predict suitable conditions for organic reactions. ACS Cent. Sci. 4, 1465–1476 (2018).

    CAS  PubMed  PubMed Central  Google Scholar 

  25. Zhou, Z., Li, X. & Zare, R. N. Optimizing chemical reactions with deep reinforcement learning. ACS Cent. Sci. 3, 1337–1344 (2017).

    CAS  PubMed  PubMed Central  Google Scholar 

  26. Epps, R. W. et al. Artificial chemist: an autonomous quantum dot synthesis bot. Adv. Mater. 32, 2001626 (2020).

    CAS  Google Scholar 

  27. Schweidtmann, A. M. et al. Machine learning meets continuous flow chemistry: automated optimization towards the Pareto front of multiple objectives. J. Chem. Eng. 352, 277–282 (2018).

    CAS  Google Scholar 

  28. Abolhasani, M. & Kumacheva, E. The rise of self-driving labs in chemical and materials sciences. Nat. Synth. 2, 483–492 (2023).

    ADS  Google Scholar 

  29. Bennett, J. A. & Abolhasani, M. Autonomous chemical science and engineering enabled by self-driving laboratories. Curr. Opin. Chem. Eng. 36, 100831 (2022).

    Google Scholar 

  30. Epps, R. W., Volk, A. A., Ibrahim, M. Y. & Abolhasani, M. Universal self-driving laboratory for accelerated discovery of materials and molecules. Chem 7, 2541–2545 (2021).

    CAS  Google Scholar 

  31. Volk, A. A. & Abolhasani, M. Autonomous flow reactors for discovery and invention. Trends Chem. 3, 519–522 (2021).

    CAS  Google Scholar 

  32. Granda, J. M., 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).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  33. Sans, V., Porwol, L., Dragone, V. & Cronin, L. A self optimizing synthetic organic reactor system using real-time in-line NMR spectroscopy. Chem. Sci. 6, 1258–1264 (2015).

    CAS  PubMed  Google Scholar 

  34. Steiner, S. et al. Organic synthesis in a modular robotic system driven by a chemical programming language. Science 363, eaav2211 (2019).

    CAS  PubMed  Google Scholar 

  35. Bradford, E., Schweidtmann, A. M. & Lapkin, A. Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm. J. Glob. Optim. 71, 407–438 (2018).

    MathSciNet  Google Scholar 

  36. Clayton, A. D. et al. Automated self-optimisation of multi-step reaction and separation processes using machine learning. J. Chem. Eng. 384, 123340 (2020).

    CAS  Google Scholar 

  37. Christensen, M. et al. Data-science driven autonomous process optimization. Commun. Chem. 4, 112 (2021).

    PubMed  PubMed Central  Google Scholar 

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

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  39. Roch, L. M. et al. ChemOS: orchestrating autonomous experimentation. Sci. Robot. 3, eaat5559 (2018).

    PubMed  Google Scholar 

  40. Gómez-Bombarelli, R. et al. Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach. Nat. Mater. 15, 1120–1127 (2016).

    ADS  PubMed  Google Scholar 

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

    CAS  PubMed  Google Scholar 

  42. Taylor, C. J. et al. Accelerated chemical reaction optimization using multi-task learning. ACS Cent. Sci. 9, 957–968 (2023).

    CAS  PubMed  PubMed Central  Google Scholar 

  43. Shields, B. J. et al. Bayesian reaction optimization as a tool for chemical synthesis. Nature 590, 89–96 (2021).

    ADS  CAS  PubMed  Google Scholar 

  44. Ahneman, D. T., Estrada, J. G., Lin, S., Dreher, S. D. & Doyle, A. G. Predicting reaction performance in C–N cross-coupling using machine learning. Science 360, 186–190 (2018).

    ADS  CAS  PubMed  Google Scholar 

  45. Tabor, D. P. et al. Accelerating the discovery of materials for clean energy in the era of smart automation. Nat. Rev. Mater. 3, 5–20 (2018).

    ADS  CAS  Google Scholar 

  46. Volk, A. A. et al. AlphaFlow: autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning. Nat. Commun. 14, 1403 (2023).

    ADS  CAS  PubMed  PubMed Central  Google Scholar 

  47. Deneault, J. R. et al. Toward autonomous additive manufacturing: Bayesian optimization on a 3D printer. MRS Bull. 46, 566–575 (2021).

    ADS  Google Scholar 

  48. Gutmann, B., Cantillo, D. & Kappe, C. O. Continuous‐flow technology—a tool for the safe manufacturing of active pharmaceutical ingredients. Angew. Chem. Int. Ed. 54, 6688–6728 (2015).

    CAS  Google Scholar 

  49. Hartman, R. L., McMullen, J. P. & Jensen, K. F. Deciding whether to go with the flow: evaluating the merits of flow reactors for synthesis. Angew. Chem. Int. Ed. 50, 7502–7519 (2011).

    CAS  Google Scholar 

  50. Movsisyan, M. et al. Taming hazardous chemistry by continuous flow technology. Chem. Soc. Rev. 45, 4892–4928 (2016).

    CAS  PubMed  Google Scholar 

  51. Volk, A. A., Campbell, Z. S., Ibrahim, M. Y., Bennett, J. A. & Abolhasani, M. Flow chemistry: a sustainable voyage through the chemical universe en route to smart manufacturing. Annu. Rev. Chem. Biomol. Eng. 13, 45–72 (2022).

    CAS  PubMed  Google Scholar 

  52. Nambiar, A. M. K. et al. Bayesian optimization of computer-proposed multistep synthetic routes on an automated robotic flow platform. ACS Cent. Sci. 8, 825–836 (2022).

    CAS  PubMed  PubMed Central  Google Scholar 

  53. Nieves-Remacha, M. J. & Jensen, K. F. Mass transfer characteristics of ozonolysis in microreactors and advanced-flow reactors. J. Flow Chem. 5, 160–165 (2015).

    Google Scholar 

  54. Brzozowski, M., O’Brien, M., Ley, S. V. & Polyzos, A. Flow chemistry: intelligent processing of gas–liquid transformations using a tube-in-tube reactor. Acc. Chem. Res. 48, 349–362 (2015).

    CAS  PubMed  Google Scholar 

  55. Hessel, V., Kralisch, D., Kockmann, N., Noël, T. & Wang, Q. Novel process windows for enabling, accelerating, and uplifting flow chemistry. ChemSusChem 6, 746–789 (2013).

    CAS  PubMed  Google Scholar 

  56. Plutschack, M. B., Pieber, B. U., Gilmore, K. & Seeberger, P. H. The hitchhiker’s guide to flow chemistry||. Chem. Rev. 117, 11796–11893 (2017).

    CAS  PubMed  Google Scholar 

  57. Ibrahim, M. Y. S., Bennett, J. A., Mason, D., Rodgers, J. & Abolhasani, M. Flexible homogeneous hydroformylation: on-demand tuning of aldehyde branching with a cyclic fluorophosphite ligand. J. Catal. 409, 105–117 (2022).

    CAS  Google Scholar 

  58. Joshi, J. B., Pandit, A. B. & Sharma, M. M. Mechanically agitated gas–liquid reactors. Chem. Eng. Sci. 37, 813–844 (1982).

    CAS  Google Scholar 

  59. Gentric, C., Mignon, D., Bousquet, J. & Tanguy, P. A. Comparison of mixing in two industrial gas–liquid reactors using CFD simulations. Chem. Eng. Sci. 60, 2253–2272 (2005).

    CAS  Google Scholar 

  60. Günther, A., Jhunjhunwala, M., Thalmann, M., Schmidt, M. A. & Jensen, K. F. Micromixing of miscible liquids in segmented gas−liquid flow. Langmuir 21, 1547–1555 (2005).

    PubMed  Google Scholar 

  61. Günther, A., Khan, S. A., Thalmann, M., Trachsel, F. & Jensen, K. F. Transport and reaction in microscale segmented gas–liquid flow. Lab Chip 4, 278–286 (2004).

    PubMed  Google Scholar 

  62. Daulton, S., Balandat, M. & Bakshy, E. Differentiable expected hypervolume improvement for parallel multi-objective Bayesian optimization. Adv. Neural Inf. Process. Syst. 33, 9851–9864 (2020).

    Google Scholar 

  63. Jacobs, I., de Bruin, B. & Reek, J. N. Comparison of the full catalytic cycle of hydroformylation mediated by mono‐and bis‐ligated triphenylphosphine–rhodium complexes by using DFT calculations. ChemCatChem 7, 1708–1718 (2015).

    CAS  Google Scholar 

  64. Dieleman, C. B., Kamer, P. C., Reek, J. N. & van Leeuwen, P. W. Xantphite: a new family of ligands for catalysis. Applications in the hydroformylation of alkenes. Helv. Chim. Acta 84, 3269–3280 (2001).

    CAS  Google Scholar 

  65. Zuidema, E. et al. The rate‐determining step in the rhodium–Xantphos‐catalysed hydroformylation of 1‐octene. Chem. Eur. J. 14, 1843–1853 (2008).

    CAS  PubMed  Google Scholar 

  66. Shahhosseini, M., Hu, G. & Pham, H. Optimizing ensemble weights and hyperparameters of machine learning models for regression problems. Mach. Learn. Appl. 7, 100251 (2022).

    Google Scholar 

  67. Lundberg, S. M. & Lee, S.-I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, 106786–6795 (2017).

    Google Scholar 

  68. Bateni, F. Smart Dope: a self‐driving fluidic lab for accelerated development of doped perovskite quantum dots. Adv. Energy Mater. 14, 2302303 (2024).

  69. Sadeghi, S. et al. Autonomous nanomanufacturing of lead-free metal halide perovskite nanocrystals using a self-driving fluidic lab. Nanoscale 16, 580–591 (2024).

  70. Koscher, B. A. et al. Autonomous multi-property-driven molecular discovery: from predictions to measurements and back. Science 382, 6677 (2023).

Download references

Acknowledgements

J.A.B., N.O., M.K., S.S. and M.A. gratefully acknowledge the financial support from Eastman Chemical Company.

Author information

Authors and Affiliations

  1. Department of Chemical and Biomolecular Engineering, North Carolina State University, Raleigh, NC, USA

    J. A. Bennett, N. Orouji, M. Khan, S. Sadeghi & M. Abolhasani

  2. Eastman Chemical Company, Kingsport, TN, USA

    J. Rodgers

Authors
  1. J. A. Bennett
    View author publications

    Search author on:PubMed Google Scholar

  2. N. Orouji
    View author publications

    Search author on:PubMed Google Scholar

  3. M. Khan
    View author publications

    Search author on:PubMed Google Scholar

  4. S. Sadeghi
    View author publications

    Search author on:PubMed Google Scholar

  5. J. Rodgers
    View author publications

    Search author on:PubMed Google Scholar

  6. M. Abolhasani
    View author publications

    Search author on:PubMed Google Scholar

Contributions

M.A. and J.A.B. conceived the project. J.A.B., N.O., S.S. and M.A. designed the algorithms. J.A.B. programmed the Pareto-mapping algorithm and built the flow platform with M.K. N.O. programmed the digital twin models and performed Shapley analysis under advisement of J.R. and M.A. M.K. conducted the reactor benchmarking experiments. J.A.B. conducted the investigations and data anlayses under advisement of J.R. and M.A. M.A. acquired funding and directed the project. J.A.B., N.O. and M.A. drafted the paper. All authors provided feedback on the paper.

Corresponding author

Correspondence to M. Abolhasani.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Chemical Engineering thanks Xiaonan Wang 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.

Extended data

Extended Data Fig. 1 Different experimental strategies for fundamental and applied studies of homogeneous catalysis.

(a) Manual vs. (b) automated, vs. (c) autonomous experimental catalysis. Autonomous experimentation utilizes intelligent experiment-selection to fast-track unveiling the full performance map (red pins) of each catalyst/ligand system with minimum human intervention and experimental cost. The red flask represents a reactor for homogeneous catalysis.

Extended Data Fig. 2 Fast-Cat’s hardware validation and benchmarking to quantify the inherent experimental noise.

a) Reaction stabilization time for a given experimental condition in multiples of the reactor residence time. b) Reaction stability across multiple automatic refills of the syringe pumps from the reagent reservoirs (mean of 3 replicates +/− standard deviation). c) Consecutive in-line GC sampling of a single hydroformylation reaction condition. d) Fast-Cat’s experimental noise via random sampling; starting in-flow hydroformylation reaction with condition 1 followed by 5 randomly selected reaction conditions before returning to condition 1 (labelled as condition 7) (mean of 3 samples at each reaction condition +/− standard deviation). Detailed reaction conditions available in the Supplementary Information section Benchmarking and Validation Conditions.

Source data

Extended Data Fig. 3 The hydroformylation reaction space exploration of 1-octene with ligand L1 using the digital twin built by the in-house experimental data of Fast-Cat.

a) Surface plots of predicted aldehyde yield with L1 as a function of (i) pressure and temperature, (ii) pressure and olefin to Rh fraction, and (iii) temperature and olefin to Rh fraction. b) Surface plots of predicted aldehyde regioselectivity with L1 as a function of (i) temperature and H2 flowrate, (ii) temperature and ligand to Rh fraction, and (iii) ligand to Rh fraction and H2 flowrate. For all surface plots shown in panels A) and B), the process parameters other than the two variable parameters used for each surface plot were maintained at a constant value (Xi = 0.25, 0.5 and 0.75) for each surface.

Source data

Supplementary information

Supplementary Information

Supplementary Figs. 1–23, Discussion and Tables 1–12.

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 Extended Data Fig./Table 2

Statistical source data.

Source Data Extended Data Fig./Table 3

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

Bennett, J.A., Orouji, N., Khan, M. et al. Autonomous reaction Pareto-front mapping with a self-driving catalysis laboratory. Nat Chem Eng 1, 240–250 (2024). https://doi.org/10.1038/s44286-024-00033-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s44286-024-00033-5

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