TY - JOUR
T1 - An autonomous laboratory for the accelerated synthesis of novel materials
AU - Szymanski, Nathan J.
AU - Rendy, Bernardus
AU - Fei, Yuxing
AU - Kumar, Rishi E.
AU - He, Tanjin
AU - Milsted, David
AU - McDermott, Matthew J.
AU - Gallant, Max
AU - Cubuk, Ekin Dogus
AU - Merchant, Amil
AU - Kim, Haegyeom
AU - Jain, Anubhav
AU - Bartel, Christopher J.
AU - Persson, Kristin
AU - Zeng, Yan
AU - Ceder, Gerbrand
N1 - Publisher Copyright:
© 2023, The Author(s).
PY - 2023/12/7
Y1 - 2023/12/7
N2 - To close the gap between the rates of computational screening and experimental realization of novel materials1,2, 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.
AB - To close the gap between the rates of computational screening and experimental realization of novel materials1,2, 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.
UR - http://www.scopus.com/inward/record.url?scp=85177741639&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85177741639&partnerID=8YFLogxK
U2 - 10.1038/s41586-023-06734-w
DO - 10.1038/s41586-023-06734-w
M3 - Article
C2 - 38030721
AN - SCOPUS:85177741639
SN - 0028-0836
VL - 624
SP - 86
EP - 91
JO - Nature
JF - Nature
IS - 7990
ER -