报告题目：Data-Driven Descriptor Identification with the Method SISSO for Accelerated Material Discovery

主讲嘉宾：欧阳润海 特聘副研究员（上海大学 材料基因组工程研究院）

活动时间：6月17日（周一）14:00

活动地点：李薰楼249会议室

报告简介： 

The Materials-Genome Initiative has fostered high-throughput calculations and experiments, leading to large amount of materials data available in literature and databases. Analyzing those data and finding physical descriptors that describe and predict the target materials properties and functions is crucial for knowledge-guided low-cost and fast material discovery. In this regard, efficient data-driven approaches for descriptor identification are required, and many methods falling under the umbrella name of (big-) data analytics (e.g. data mining, machine learning, compressed sensing, etc.) have being developed and applied to the wealth of Materials Science data. In this talk, Ouyang will introduce the recent data-driven method SISSO, which is based on the theory of compressed sensing, for identifying low-dimensional descriptors (A descriptor is defined a set of features that capture the underlying mechanisms of the target materials property or function; the dimension is the number of features in the descriptor) from huge features spaces. Then he will review several recent applications of SISSO across Materials Science and Chemistry to demonstrate the efficiency, e.g. the identification of a new tolerance factor for predicting the stability of perovskite, a physical descriptor for predicting the Gibbs free energy of crystalline solids, a materials map for predicting 2D topological insulators, and a descriptor for predicting the pressure-induced insulator→metal transition of binary crystals. In addition, he will also introduce the newly developed technique in SISSO for multi-task learning for finding a common descriptor for multiple materials properties.

嘉宾简介： 

欧阳润海博士，上海大学材料基因组工程研究院特聘副研究员，上海市青年东方学者。他于2013年博士毕业于中科院大连化物所理论催化课题组（导师：李微雪教授）；之后，他先后在澳大利亚悉尼大学、美国加州大学河滨分校、德国马普FHI研究所做博士后研究；并于2019年加入上海大学。特别地，在德国FHI期间，他隶属于FHI理论部大数据材料科学课题组，从事欧盟H2020地平线计划NOMAD项目的关于大数据分析方法及数据驱动新材料预测方面的研究；与Scheffler教授和Ghiringhelli博士等人一起发展了基于压缩感知理论框架的数据驱动方法SISSO。他编写的并行程序SISSO免费供学术和商业使用(github.com/rouyang2017/SISSO)，可广泛用于材料、化学等领域数据驱动描述符或模型的建立及新材料预测。

欢迎所内职工和研究生前来交流！