
The Fall 2021 MatSE 590 for graduate students consists of an exciting and jam-packed schedule. MATSE 590 is a colloquium (1-3 credits) consist of a series of individual lectures by faculty, students, or outside speakers.
Graduate students will receive a weekly email with information via @psu.edu email. Graduate students are required to attend all 590 Seminars. If you have any questions, please email Hayley Barnes at hjc24@psu.edu.
*Due to the ongoing Covid Pandemic this program is being offered virtually through Zoom. Please reference the weekly email from Hayley Barnes (hjc24@psu.edu) for Zoom link.
Thursday, November 11, 2021
"Towards active exploration of novel electronic materials "
James Rondinelli, Morris E. Fine Professor in Materials and Manufacturing, Northwestern University
Abstract
Over the last 10 years, functional electronic materials design has undergone a shift from chemical-intuition-based strategies to data-driven synthesis and simulation. Numerous machine learning models have been developed to successfully predict materials properties and generate new crystal structures. Many existing approaches, however, rely upon physical insights to construct handcrafted features (descriptors), which are not always readily available. For novel materials with sparse prior data and insufficient physical understanding, conventional machine learning models may display limited predictability. In this talk, I will address this challenge by introducing an adaptive optimization engine for materials composition optimization, where feature engineering is not explicitly required—so called featureless learning. I then describe a use case where multi-objective Bayesian optimization with latent-variable Gaussian processes is utilized to accelerate the design of electronic metal-insulator transition compounds [1]. I will then contrast this approach with supervised classification-based models for MIT compounds [2]. Last, I will highlight a recent quantitative study on structure-property relationship in crystal systems enabled by deep neural networks. The model, which learns the structural genome, identifies intrinsically similar structures in Fourier space. Finally, I propose how integration of the different modalities could lead to harmonious iterative exploration of novel functional materials.
Biographical Information
James M. Rondinelli is the Morris E. Fine Professor in Materials and Manufacturing at Northwestern University (NU) in the Materials Science and Engineering (MSE) Department and Applied Physics Program, where he leads the Materials Theory and Design Group. He serves as Co-Director of the https://www.mccormick.northwestern.edu/predictive-science-engineering-de... and Associate Director of the NSF Materials Research Science and Engineering Center (MRSEC) at NU. His research interests are in electronic structure theory and first-principles design of functional inorganic materials using picoscale structure-property relationships. He focuses on technical challenges and overcoming material disparities by strategically building functionality into materials through multiple tiers of materials theory, simulation, and machine-learning approaches. He has received numerous awards, including the Materials Research Society (MRS) Outstanding Young Investigator (2017), Sloan Research Fellowship in Physics (2016), and the Presidential Early Career Award for Scientists and Engineers (PECASE), among others. Rondinelli has (co)-authored more than 200 peer-reviewed publications and holds 2 patents. He is a former Member-at-Large for the American Physical Society’s Division of Materials Physics. He received his Ph.D. in Materials Science from the University of California, Santa Barbara (2010). From 2010-2011, he was the Joseph Katz Named Fellow in the X-Ray Science Division at Argonne National Laboratory. Prior to joining NU, he was an assistant professor at Drexel University (2011-14).
Attachment | Size |
---|---|
![]() | 1.83 MB |