465380 Combining Density Functional Theory Calculations, Supercomputing, and Data-Driven Methods to Design New Thermoelectric Materials

Sunday, November 13, 2016: 5:00 PM
Golden Gate 8 (Hilton San Francisco Union Square)
Anubhav Jain1, Umut Aydemir2, Hong Zhu3, Jan Pohls4, Zachary Gibbs5, Wei Chen6, Saneyuki Ohno2, Geoffroy Hautier7, Gerbrand Ceder8, Kristin Persson1, Mary Anne White4 and G. Jeffrey Snyder2, (1)Lawrence Berkeley Lab, Berkeley, CA, (2)Northwestern University, Evanston, IL, (3)Shanghai Jiao Tong University, Shanghai, China, (4)Dalhousie University, Halifax, NS, Canada, (5)California Institute of Technology, Pasadena, CA, (6)Illinois Institute of Technology, Chicago, IL, (7)Universite Catholique de Louvain, Louvain-la-Neuve, Belgium, (8)Materials Science and Engineering, University of California Berkeley, Berkeley, CA

Density functional theory (DFT) simulations solve for the electronic structure of materials starting from the Schrödinger equation. Many case studies have now demonstrated that researchers can often use DFT to design new compounds in the computer (e.g., for batteries, catalysts, and hydrogen storage) before synthesis and characterization in the lab. In this talk, I will focus on how DFT calculations can be executed on large supercomputing resources in order to generate very large data sets on new materials for functional applications. First, I will briefly describe the Materials Project, an effort at LBNL that has virtually characterized over 60,000 materials using DFT and has shared the results with over 17,000 registered users. Next, I will talk about how such data can help discover new materials, describing how preliminary computational screening led to the identification and confirmation of a new family of bulk AMX2 thermoelectric compounds with measured zT reaching 0.8. I will outline future plans for how such data-driven methods can be used to better understand the factors that control thermoelectric behavior, e.g., for the rational design of electronic band structures, in ways that are different from conventional approaches.

Extended Abstract: File Not Uploaded