报告题目：Ab initio artificial intelligence

报告人：徐勇教授

主持人：杨小宝教授

时   间：2023年8月28日（星期一）下午3：00

地   点：物理楼（18号楼）二楼213室学术报告厅

欢迎广大师生参加!

                                                           物理与光电学院

2023年8月25日

摘要：Ab initio methods based on density functional theory (DFT) have become indispensable to the study of physics, chemistry, materials science, etc., but are bottlenecked by the efficiency-accuracy dilemma. In this talk, I will review an emerging interdisciplinary field of ab initio artificial intelligence, which has the potential to revolutionize modern computational materials science. In particular, I will introduce our recent works on developing a deep neural network framework to represent the DFT Hamiltonian (DeepH) as a function of material structure, aiming to bypass the computationally demanding self-consistent field iterations of DFT and substantially improve the efficiency of ab initio electronic-structure calculations [1-3]. High accuracy, high efficiency, and good transferability of the DeepH approach are generally demonstrated for various kinds of material systems and physical properties. The deep-learning method provides a solution to the accuracy-efficiency dilemma of DFT and opens opportunities for efficient ab initio study of large-scale materials.

References:

[1] H. Li, et al. Nature Computational Science 2, 367 (2022)

[2] X. Gong, et al. Nature Communications 14, 2848 (2023)

[3] H. Li, et al. Nature Computational Science Sci. 3, 321 (2023)

报告人简介：Dr. Yong Xu is currently a tenured professor at Department of Physics, Tsinghua University and a unit leader at Center for Emergent Matter Science (CEMS), RIKEN. He received his B.S. and Ph.D. degrees both at Tsinghua University, then worked at Fritz Haber Institute of Max Planck Society and Stanford University as a postdoc and a research scholar, respectively. He was awarded Alexander von Humboldt Fellowship of Germany and National Science Fund for Distinguished Young Scholars. His main research interest is to understand/predict emergent quantum phenomena and materials from first principles.