Prof. Ph. D. Xiaoying Zhuang

Prof. Ph. D. Xiaoying Zhuang
Address
Appelstr. 11A
30167 Hannover
Building
Room
Prof. Ph. D. Xiaoying Zhuang
Address
Appelstr. 11A
30167 Hannover
Building
Room

Research in PhoenixD

Prof. Xiaoying Zhuang’s key research areas are machine learning and computational mechanics with focus on multiphysics/multiscale modelling for the design of novel composites and metamaterials. She published so far over 200 papers in international journals such as Advanced Materials, Nano Energy attracting over 14000 citations in Web of Science. She is listed as Standford/Elsevier's Word's Top 2% Scientists and ISI Highly Cited Researcher. She is recognized by varioud awards including ERC Starting Grant, Heisenberg-Professor, Sofja Kovaleskaja Prize, Heinz-Maier Leibnitz Prizeand so on.

The team led by Prof. Zhuang at LUH has extensive experience in developing machine learning and deep learning methods for the inverse design of 2D materials and metamaterials. 2D materials have some unique properties that other usual materials do not have and thus attracted widespread attention in recent years. However, simulating new materials has historically been a time-consuming process, especially when there are not readily available potential functions for them. Traditional methods often require significant time and resources to develop and validate new potential functions. With the advancement of machine learning, methods like machine learning interatomic potentials (MLIP) have emerged to significantly expedite this process.

Prof. Zhuang’s team proposed the first framework of first-principles multiscale modelling based on MLIP, that is conveniently and rapidly trainable over short ab-initio datasets. It shows that mechanical and failure responses of complex nanostructures at continuum scale can be explored with the precision of sophisticated first-principles calculations, affordable computational cost, and without the need for empirical data. Such an approach shows great potential to develop fully automated and coupled platforms of new materials.

Machine learning-based of first-principles multiscale modelling for 2D materials
Inverse design of topological metaplates for flexural waves with machine learning