Gust Seminar - Computational Materials Discovery in the Age of AI and Robotics
In the modern age of data science, there is more catalogued and query-able data than ever before. Here I will discuss how we can leverage high-throughput materials data from computational, experimental, and literature sources to accelerate the discovery of new functional materials. First, I will present a large stability map of the ternary metal nitrides, constructed using a suite of high-throughput computational materials discovery and informatics methods.1 Guided by our map, we experimentally realized a new class of ternary nitride semiconductors with tunable optoelectronic properties, expanding the palette of nitride semiconductors beyond Al/Ga/In-Nitrides.2 To more effectively design synthesis routes to computationally-predicted materials, we next demonstrate how Natural Language Processing algorithms can extract materials synthesis recipes from the scientific literature.2 By analyzing trends and anomalies in these published synthesis recipes, we hypothesized new design principles for highly-reactive precursors to complex multicomponent oxides. Using a robotic inorganic materials synthesis laboratory,4 we show that our predicted precursors substantially outperform traditional precursors. Robotic laboratories offer an exciting new platform for data-driven experimental synthesis science, from which we can develop new fundamental insights to guide both human and robotic chemists.
Wenhao Sun is the Dow Early Career Professor of Materials Science and Engineering at the University of Michigan. He double majored in Materials Science and Engineering and Applied Mathematics at Northwestern University, and obtained his PhD in Materials Science and Engineering from MIT. The Sun Research Group uses high-throughput density functional theory, applied thermodynamics, and materials informatics to deepen our fundamental understanding of synthesis–structure–property relationships, while exploring new chemical spaces for functional technological materials. Wenhao was named a 2020 Materials Horizons Emerging Investigator, was awarded the 2020 Department of Energy Early Career Award, as well as the 2022 Camille and Henry Dreyfus Award for Machine-Learning in the Chemical Sciences.