Artificial Intelligence Strategies for Materials Discovery with Explainable and Open Sharing Capabilities

Seminar Link: Picoelectrodynamics Theory Network - YouTube


In this talk, I will discuss some of the past and ongoing research in machine learning methods to efficiently guide materials design and discovery efforts. The overarching theme is efficient navigation of the vast search space, which is especially critical when brute-force evaluation of the search space is prohibitively expensive. Adaptive learning methods, such as active learning and Bayesian optimization, provide a promising solution to address this important problem.

One of the expected outcomes from an iterative adaptive learning loop is an improved black-box machine learning or surrogate model that is believed to capture the complexity of the structure-property relationships with sufficient accuracy. More recently, our group has expanded the adaptive learning paradigm in two directions:

(1) Incorporating novel post-hoc model explainable methods to peek inside the trained black-box models and explain the predictions for each observation in the data set.

(2) Build Web Applications that will allow the public to interact with our trained models and accelerate discoveries.

By Prof. Prasanna Balachandran

Prof. Prasanna Balachandran is currently an Assistant Professor in the Department of Materials Science and Engineering with a joint appointment in the Department of Mechanical and Aerospace Engineering at the University of Virginia (UVA). He earned his bachelor's Degree in Metallurgical Engineering from Anna University, India in 2007 and Ph.D. in Materials Science and Engineering from Iowa State University, USA in 2011. Prior to joining UVA in December 2017, he spent three and half years as a postdoctoral research associate in the Theoretical Division at Los Alamos National Laboratory (LANL), USA, and two years as a postdoctoral research associate at Drexel University, USA. His research interests are in the application of first-principles-based density functional theory calculations and information science methods for accelerating the design and discovery of new materials.