Ziheng Lu | Materials research from the perspective of computing: data, model, and more

<注:本视频仅用于学术交流,版权归报告人所有>

 

►【表面科学论坛(132) 】

报告题目:Materials research from the perspective of computing: data, model, and more

报告人:Ziheng Lu, Microsoft Research

报告时间:2022年08月18日(周四)上午10:00

报告地点:线上

报告摘要

The way people search for a new material is undergoing a transition from "experimental trial and error" to "rational design". While the current computational screening scheme based on existing databases has guided the synthesis of a number of key materials, the intrinsic limitation on chemical and structural space of the databases gradually impedes the further discovery of novel materials with desired functionality. This talk will briefly cover the current research paradigms, commonly used tools, and challenges in computational materials science. On that basis, the effort at Microsoft Research will be introduced, Local Similarity kernel Optimization (LOSIKO, a data-driven atomic structure optimizer for unlabeled data), MoLeR (a graph-based model for molecule generation), including Graphormer (a Transformer-based molecular modeling foundation model), and KD-DTI (a database for literature mining). Future perspectives will be discussed in the end.

报告人简介

Ziheng Lu is a Senior Researcher at Microsoft Research (MSR). He works at the intersection of materials science and machine learning. His current research focuses on computational and experimental design of new materials and their applications in downstream areas. His interest also falls into the general scope of ‘AI for science’. Ziheng earned his Ph.D. from the Hong Kong University of Science and Technology in 2018. He has published over 50 peer-reviewed articles. He also serves as the associate editor for Frontiers in Chemistry, the guest editor for Materials Reports: Energy and Frontiers in Energy Research, and the reviewer for > 10 journals including Joule, Nat. Comm., and Adv. Mater.