MMAE Seminar - Data-driven Accelerated Materials Discovery: High-throughput Computing and Machine Learning

Armour College of Engineering's Mechanical, Materials & Aerospace Engineering Department will welcome Dr. Wei Chen, Postdoctoral Fellow at Lawrence Berkeley National Laboratory, to campus on Tuesday, March 31st to present his lecture, Data-driven Accelerated Materials Discovery: High-throughput Computing and Machine Learning.

Abstract

Accelerating the discovery of advanced materials is essential for sustainable development and manufacturing innovation. In the talk, I will introduce my contributions to the Materials Project, a core program of the Materials Genome Initiative that employs high-throughput computing and modern data analytics to uncover the properties of all known inorganic materials.

Overviews of current collaborative projects will be given to illustrate how the comprehensive datasets and computational frameworks can be leveraged to facilitate materials design. Specifically, I will elaborate a new integrated approach to solve the long-standing "Calcite-Aragonite Problem" – the observation that calcium carbonate precipitates as the metastable aragonite polymorph in marine environments, rather than the stable calcite phase. Our ability to quantify how solution parameters distinguish between polymorphs marks an important step towards the ab initio prediction of material synthesis pathways in solution.

I will also discuss the emerging field of materials informatics that applies machine-learning techniques to materials research. Examples will be given on data-driven predictive modeling to probe structure-property relationships of alloy surfaces in the complete configurational space.

Lastly, I will describe our recent efforts to chart the complete elastic properties of inorganic crystalline compounds. I will present an automated elastic tensor workflow and the largest database of calculated elastic tensors to date. The dataset has lead to the discovery of a new class of thermoelectric materials. I will conclude the talk by discussing a machine-learning model that accurately predicts elastic modulus.

Biography

Wei Chen is a postdoctoral fellow at Lawrence Berkeley National Laboratory working with Dr. Kristin Persson. He obtained his Ph.D in Materials Science and Engineering at Northwestern University under the advisory of Prof. Chris Wolverton. He received his B. Eng in Materials Science and Engineering from Shanghai Jiao Tong University and M.S. in Materials Physics and Chemistry from Chinese Academy of Sciences.