Autonomous experimentation for accelerated materials discovery

Figure: The closed loop workflow used to discover and synthesize new materials in the A-Lab, an autonomous platform that integrates computations with robotics.


There is an urgent need to rapidly identify low-cost and high-performance materials that will enable a global transition to sustainable energy conversion and storage technologies. However, the current paradigm of materials design is still too slow; from idea conceptualization to market often takes over 10 years, in large part due to the manual and labor-intensive process of traditional experimentation. To address these challenges, the Ceder group is actively developing tools that can accelerate materials design and development through the automation of three key aspects: (1) robotic execution of synthesis experiments and characterization processes, (2) machine-learned interpretation of characterization data, and (3) decision making enabled by artificial intelligence. Our group has integrated these components into one fully autonomous, closed-loop system known as the A-Lab. As we continue to expand this system, we aim to achieve a rate of materials discovery that is 10-100× faster than the current standard.


Select Publications:

  1. N. J. Szymanski, B. Rendy, Y. Fei, R. E. Kumar, Y. Zeng, G. Ceder et al. An autonomous laboratory for the accelerated synthesis of novel materials. Nature (2023). https://doi.org/10.1038/s41586-023-06734-w
  2. N. J. Szymanski, Y. Zeng, H. Huo, C. Bartel, H. Kim, and G. Ceder, Toward Autonomous Design and Synthesis of Novel Inorganic Materials. Mater. Horiz. 2021, 8 (8), 2169–2198. https://doi.org/10.1039/D1MH00495F.
  3. N. J. Szymanski, P. Nevatia, C. Bartel, Y. Zeng, and G. Ceder, Autonomous and Dynamic Precursor Selection for Solid-state Materials Synthesis, Nat Commun. 14, 6956 (2023). https://doi.org/10.1038/s41467-023-42329-9
  4. N. J. Szymanski, C. J. Bartel, Y. Zeng, Q. Tu, and G. Ceder, Probabilistic Deep Learning Approach to Automate the Interpretation of Multi-phase Diffraction Spectra, Chem. Mater. 2021, 33 (11), 4204–4215. https://doi.org/10.1021/acs.chemmater.1c01071.
  5. N. J. Szymanski, C. J. Bartel, Y. Zeng, M. Diallo, H. Kim, and G. Ceder, Adaptively Driven X-ray Diffraction Guided by Machine Learning for Autonomous Phase Identification, npj Computational Materials 2023, 9:31 https://doi.org/10.1038/s41524-023-00984-y.