On-the-fly closed-loop materials discovery via Bayesian active learning

Abstract

Active learning—the field of machine learning (ML) dedicated to optimal experiment design—has played a part in science as far back as the 18th century when Laplace used it to guide his discovery of celestial mechanics. In this work, we focus a closed-loop, active learning-driven autonomous system on another major challenge, the discovery of advanced materials against the exceedingly complex synthesis-processes-structure-property landscape. We demonstrate an autonomous materials discovery methodology for functional inorganic compounds which allow scientists to fail smarter, learn faster, and spend less resources in their studies, while simultaneously improving trust in scientific results and machine learning tools. This robot science enables science-over-the-network, reducing the economic impact of scientists being physically separated from their labs. The real-time closed-loop, autonomous system for materials exploration and optimization (CAMEO) is implemented at the synchrotron beamline to accelerate the interconnected tasks of phase mapping and property optimization, with each cycle taking seconds to minutes. We also demonstrate an embodiment of human-machine interaction, where human-in-the-loop is called to play a contributing role within each cycle. This work has resulted in the discovery of a novel epitaxial nanocomposite phase-change memory material.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 56

1. 1.

   National Science and Technology Council (US). “Materials Genome Initiative for Global Competitiveness.” Executive Office of the President, National Science and Technology Council (2011).

   Not in our library

2. 2.

   Toher C, et al. Unavoidable disorder and entropy in multi-component systems. Npj Comput. Mater. 2019;5:1-3.

   Not in our library10.1038/s41524-019-0206-z

3. 3.

   Hattrick-Simpers JR, et al. Perspective: Composition–structure–property mapping in high-throughput experiments: turning data into knowledge. APL Mater. 2016;4:053211.

   Not in our library10.1063/1.4950995

4. 4.

   Shapiro, E. et al. “Toward 2020 Science” Microsoft, (2006).

   Not in our library

5. 5.

   Licklider JCR. Man-computer symbiosis. IRE Tran. Hum. Facto. Elect. 1960;1:4-11.

   Not in our library10.1109/thfe2.1960.4503259

6. 6.

   Shneiderman B. Human-centered artificial intelligence: Reliable, safe & trustworthy. Int. J. Hum. Comput. Inter. 2020;36:495-504.

   Not in our library10.1080/10447318.2020.1741118

7. 7.

   Settles B. Active learning literature survey. Univ. Wis. Madison. 2010;52:11.

   Not in our library

8. 8.

   Jaynes, E. T. Bayesian methods: general background. (1986).

   Not in our library

9. 9.
   Accelerated search for materials with targeted properties by adaptive design · 2016

   No notice
10. 10.

    Yuan R, et al. Accelerated discovery of large electrostrains in BaTiO3-based piezoelectrics using active learning. Adv. Mater. 2018;30:1702884.

    Not in our library10.1002/adma.201702884

11. 11.

    Balachandran PV, et al. Experimental search for high-temperature ferroelectric perovskites guided by two-step machine learning. Nat. Commun. 2018;9:1668.

    Not in our library10.1038/s41467-018-03821-9

12. 12.

    Meredig B, et al. Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery. Mol. Syst. Des. Eng. 2018;3:819-825.

    Not in our library10.1039/c8me00012c

13. 13.
    Occurrence of the potent mutagens 2- nitrobenzanthrone and 3-nitrobenzanthrone in fine airborne particles · 2019

    No notice
14. 14.

    Korovina, K. et al. Chembo: Bayesian optimization of small organic molecules with synthesizable recommendations. International Conference on Artificial Intelligence and Statistics. PMLR, 3393-3403 (2020).

    Not in our library

15. 15.

    Li Z, et al. Robot-accelerated perovskite investigation and discovery. Chem. Mater. 2020;32:5650.

    Not in our library10.1021/acs.chemmater.0c01153

16. 16.

    Pendleton IM, et al. Experiment specification, capture and laboratory automation technology (ESCALATE): a software pipeline for automated chemical experimentation and data management. MRS Commun. 2019;9:846-859.

    Not in our library10.1557/mrc.2019.72

17. 17.

    Zhong M, et al. Accelerated discovery of CO2 electrocatalysts using active machine learning. Nature. 2020;581:178-183.

    Not in our library10.1038/s41586-020-2242-8

18. 18.

    Nikolaev P, et al. Autonomy in materials research: a case study in carbon nanotube growth. Npj Comput. Mater. 2016;2:16031.

    Not in our library10.1038/npjcompumats.2016.31

19. 19.

    Roch LM, et al. ChemOS: orchestrating autonomous experimentation. Sci. Robot. 2018;3:eaat5559.

    Not in our library10.1126/scirobotics.aat5559

20. 20.

    Attia PM, et al. Closed-loop optimization of fast-charging protocols for batteries with machine learning. Nature. 2020;578:397-402.

    Not in our library10.1038/s41586-020-1994-5

21. 21.

    Noack MM, et al. A kriging-based approach to autonomous experimentation with applications to x-ray scattering. Sci. Rep. 2019;9:1-19.

    Not in our library10.1038/s41598-019-48114-3

22. 22.

    Burger B, et al. A mobile robotic chemist. Nature. 2020;583:237-241.

    Not in our library10.1038/s41586-020-2442-2

23. 23.

    MacLeod BP, et al. Self-driving laboratory for accelerated discovery of thin-film materials. Sci. Adv. 2020;6:eaaz8867.

    Not in our library10.1126/sciadv.aaz8867

24. 24.

    Langner S, et al. Beyond ternary OPV: high‐throughput experimentation and self‐driving laboratories optimize multicomponent systems. Adv. Mater. 2020;32:1907801.

    Not in our library10.1002/adma.201907801

25. 25.

    Reyes KG, et al. The machine learning revolution in materials? MRS Bulletin. 2019;44:530-537.

    Not in our library10.1557/mrs.2019.153

26. 26.

    Stein HS, et al. Progress and prospects for accelerating materials science with automated and autonomous workflows. Chem. Sci. 2019;10:9640-9649.

    Not in our library10.1039/c9sc03766g

27. 27.

    Tabor DP, et al. Accelerating the discovery of materials for clean energy in the era of smart automation. Nat Rev. Mater. 2018;3:5-20.

    Not in our library10.1038/s41578-018-0005-z

28. 28.

    Jensen, K. F. et al. Autonomous discovery in the chemical sciences part I: Progress (Angewandte Chemie International Edition, 2019).

    Not in our library

29. 29.

    Geiger AC, et al. Autonomous science: big data tools for small data problems in chemistry. Mach. Learn. Chem. 2020;17:450.

    Not in our library

30. 30.

    Kolobov, A. V. et al. Springer Handbook of Electronic and Photonic Materials, (eds Kasap, S. & Capper, P.) (Springer International Publishing, Cham, 2017).

    Not in our library

31. 31.

    Burr GW, et al. Neuromorphic computing using non-volatile memory. Adv. Phys. X. 2016;2:89-124.

    Not in our library

32. 32.

    Li X, et al. Fast and reliable storage using a 5 bit, nonvolatile photonic memory cell. Optica. 2019;6:1-6.

    Not in our library10.1364/optica.6.000001

33. 33.

    Giannopoulos, I. et al. 8-bit precision in-memory multiplication with projected phase-change memory. IEEE International Electron Devices Meeting (IEDM), 27.7.1–27.7.4 (2018)

    Not in our library

34. 34.

    Simpson RE, et al. Interfacial phase-change memory. Nat. Nanotechnol. 2011;6:501-505.

    Not in our library10.1038/nnano.2011.96

35. 35.

    Ding K, et al. Phase-change heterostructure enables ultralow noise and drift for memory operation. Science. 2019;366:210-215.

    Not in our library10.1126/science.aay0291

36. 36.

    Kusne, A. G., “Materials Genome Initiative & Artificial Intelligence at NIST”, DOE AMO Workshop on Artificial Intelligence Applied to Materials Discovery and Design, Pittsburgh, PA (2017).

    Not in our library

37. 37.

    Green, M. et al. High-throughput experimental materials collaboratory, NIST materials genome initiative. https://mgi.nist.gov/htemc (2020)

    Not in our library

38. 38.

    Srinivas N, et al. Information-theoretic regret bounds for gaussian process optimization in the bandit setting. IEEE Trans. Inf. Theory. 2012;58:3250-3265.

    Not in our library10.1109/tit.2011.2182033

39. 39.

    Long C, et al. Rapid structural mapping of ternary metallic alloy systems using the combinatorial approach and cluster analysis. Rev. Sci. Instrum. 2007;78:072217.

    Not in our library10.1063/1.2755487

40. 40.

    spec Software for Diffraction, Certified Scientific Software. https://certif.com/spec.html. (2017)

    Not in our library

Cited by papers we hold 1

• Deep learning for visualization and novelty detection in large X-ray diffraction datasets · 2021
  Not checked

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.