Accelerating simulation and design of energy-related materials via machine learning

by Dr Yunwei Zhang (University of Cambridge)

Wednesday 16 Dec 2020, 16:00 → 17:00 Asia/Shanghai

ONLINE

Abstract

Computational materials science is undergoing a second revolution empowered by machine learning (ML). ML methods do not completely reply on the theoretical understanding of the problem but take a data-driven approach to solve these problems. ML methods can describe and predict the notorious properties of materials, especially for those that can only be determined experimentally.

 

In this talk, I will present our works in applying ML to identify the degradation patterns of Li-ion batteries (Nat. Comms 11 (1), 1-6 (2020)) and design new high-temperature superconductors. I will show that combining advanced experimental technique and physical theory with ML can help us to understand the physical laws between materials features and properties from a new perspective.

Biography

Yunwei Zhang is a postdoctoral researcher at Cavendish Lab, the University of Cambridge. She got her Ph.D. in Condensed Matter Physics from Jilin University in China in 2018. During her Ph.D., she visited Singapore University of Technology and Design and University of Hong Kong as an exchange student. Her recent research focuses on combining machine learning methods with physical theory to accelerate functional materials design.

Division

Condensed Matter

Other information

Here is the Zoom link if you prefer to join us remotely:

https://zoom.com.cn/j/62063266920

Password: 140812