Collaborative breakthrough AI research involving Assistant Professor Chris Bartel published in 𝘕𝘢𝘵𝘶𝘳𝘦
Assistant Professor Chris Bartel is a member of a collaborative research team led by Lawrence Berkeley National Laboratory that recently published a paper, "An autonomous laboratory for the accelerated synthesis of novel materials" in Nature.
Computational methods have made great strides towards accelerated materials discovery. For instance, the Materials Project database, led by Lawrence Berkeley National Laboratory, hosts density functional theory calculations for more than 100,000 solid-state materials. However, before any of these materials can be deemed useful for some application (e.g., energy storage), significant trial-and-error is required to find a way to synthesize these materials in the lab. The authors of the recent article published in Nature established the A-Lab, an automated and closed-loop materials synthesis system, which worked 24 hours a day, 7 days a week for 17 days in an attempt to synthesize 58 hypothetical materials predicted by the Materials Project, succeeding in 41 cases. 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.
Bartel’s contributions to the project included the development of deep learning models to learn from the literature and interpret experimental characterization data as well as theory-guided methods to close the autonomous synthesis loop with adaptive optimization of synthesis recipes.
Computational methods have made great strides towards accelerated materials discovery. For instance, the Materials Project database, led by Lawrence Berkeley National Laboratory, hosts density functional theory calculations for more than 100,000 solid-state materials. However, before any of these materials can be deemed useful for some application (e.g., energy storage), significant trial-and-error is required to find a way to synthesize these materials in the lab. The authors of the recent article published in Nature established the A-Lab, an automated and closed-loop materials synthesis system, which worked 24 hours a day, 7 days a week for 17 days in an attempt to synthesize 58 hypothetical materials predicted by the Materials Project, succeeding in 41 cases. 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.
Bartel’s contributions to the project included the development of deep learning models to learn from the literature and interpret experimental characterization data as well as theory-guided methods to close the autonomous synthesis loop with adaptive optimization of synthesis recipes.
Read the full paper here: https://www.nature.com/articles/s41586-023-06734-w