An autonomous laboratory for the accelerated synthesis of novel materials

Nathan J Szymanski; Bernardus Rendy; Yuxing Fei; Rishi E Kumar; Tanjin He; David Milsted; Matthew J McDermott; Max Gallant; Ekin Dogus Cubuk; Amil Merchant; Haegyeom Kim; Anubhav Jain; Christopher J Bartel; Kristin Persson; Yan Zeng; Gerbrand Ceder

doi:10.1038/s41586-023-06734-w

An autonomous laboratory for the accelerated synthesis of novel materials

Nature. 2023 Dec;624(7990):86-91. doi: 10.1038/s41586-023-06734-w. Epub 2023 Nov 29.

Authors

Nathan J Szymanski^#^{1

2}, Bernardus Rendy^#^{1

2}, Yuxing Fei^#^{1

2}, Rishi E Kumar^#³, Tanjin He^{1

2}, David Milsted², Matthew J McDermott^{1

2}, Max Gallant^{1

2}, Ekin Dogus Cubuk⁴, Amil Merchant⁴, Haegyeom Kim², Anubhav Jain³, Christopher J Bartel², Kristin Persson^{1

2}, Yan Zeng⁵, Gerbrand Ceder^{6

7}

Affiliations

¹ Department of Materials Science and Engineering, University of California, Berkeley, Berkeley, CA, USA.
² Materials Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
³ Energy Technologies Area, Lawrence Berkeley National Laboratory, Berkeley, CA, USA.
⁴ Google DeepMind, London, UK.
⁵ Materials Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA. yanzeng@lbl.gov.
⁶ Department of Materials Science and Engineering, University of California, Berkeley, Berkeley, CA, USA. gceder@berkeley.edu.
⁷ Materials Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA. gceder@berkeley.edu.

^# Contributed equally.

Abstract

To close the gap between the rates of computational screening and experimental realization of novel materials^1,2, we introduce the A-Lab, an autonomous laboratory for the solid-state synthesis of inorganic powders. This platform uses computations, historical data from the literature, machine learning (ML) and active learning to plan and interpret the outcomes of experiments performed using robotics. Over 17 days of continuous operation, the A-Lab realized 41 novel compounds from a set of 58 targets including a variety of oxides and phosphates that were identified using large-scale ab initio phase-stability data from the Materials Project and Google DeepMind. Synthesis recipes were proposed by natural-language models trained on the literature and optimized using an active-learning approach grounded in thermodynamics. Analysis of the failed syntheses provides direct and actionable suggestions to improve current techniques for materials screening and synthesis design. The high success rate demonstrates the effectiveness of artificial-intelligence-driven platforms for autonomous materials discovery and motivates further integration of computations, historical knowledge and robotics.