An autonomous laboratory for the accelerated synthesis of novel materials

• Published in: Nature (London) Vol. 624; no. 7990; pp. 86 - 91
• Main Authors: Szymanski, Nathan J., Rendy, Bernardus, Fei, Yuxing, Kumar, Rishi E., He, Tanjin, Milsted, David, McDermott, Matthew J., Gallant, Max, Cubuk, Ekin Dogus, Merchant, Amil, Kim, Haegyeom, Jain, Anubhav, Bartel, Christopher J., Persson, Kristin, Zeng, Yan, Ceder, Gerbrand
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 07.12.2023; Nature Publishing Group
• Subjects: 119/118; 639/301/1034/1037; 639/301/930/1032; 639/301/930/12; Active learning; Algorithms; Artificial intelligence; Automation; Carbon dioxide; characterization and analytical techniques; computational methods; Convexity; Crystal structure; Decision making; Decomposition; Density functional theory; design, synthesis and processing; Diffraction patterns; Experiments; Humanities and Social Sciences; MATERIALS SCIENCE; multidisciplinary; Robotics; Route optimization; Science; Science (multidisciplinary); Success; Synthesis; Thermodynamics
• ISSN: 0028-0836; 1476-4687; 1476-4687
• DOI: 10.1038/s41586-023-06734-w

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. An autonomous laboratory, the A-Lab, is presented that combines computations, literature data, machine learning and active learning, which discovered and synthesized 41 novel compounds from a set of 58 targets after 17 days of operation.