AI for Scientific Discoveries Lecture Series - From Quantum Mechanics to Materials Discovery: First Principles Meet AI

Abstract

Over the past century, progress from the advent of quantum mechanics to predictive computational materials science has enabled first-principles approaches—most notably density functional theory (DFT)—to design and predict materials at the atomic and electronic scales. Yet the steep computational cost of these methods limits their use in large-scale, high-throughput studies, creating a major bottleneck for data-driven materials discovery.

In this lecture, the speaker will present an emerging research direction that integrates deep learning with first-principles electronic structure calculations to address the computational bottlenecks of conventional methods. The lecture will focus on DeepH, a deep-learning Hamiltonian approach developed by our group that provides a general and transferable neural-network framework for DFT. By learning DFT Hamiltonians from calculations on small-scale structures, DeepH can generalize to larger materials systems and achieve orders-of-magnitude gains in computational efficiency while retaining first-principles accuracy. The speaker will discuss performance on representative applications and implications for scalable electronic-structure prediction.

Looking ahead, the availability of increasingly large training datasets may allow neural-network-based approaches to evolve into more efficient generative models for materials, creating new opportunities for AI-driven discovery in physics and materials science.


About the Speaker

Prof. Yong XU is a Professor in the Department of Physics at Tsinghua University. He received his B.S. and Ph.D. degrees from Tsinghua University and subsequently carried out research at the Fritz Haber Institute of the Max Planck Society and Stanford University. He has been recognized with several major honors, including the Yeh Chi-Sun Physics Prize from the Chinese Physical Society, the Beijing Zhongguancun Award for Distinguished Young Scholars, and the First Prize of the Ministry of Education Natural Science Award. His research spans topological quantum states of matter, first-principles materials design, and AI for Science.


For Attendees' Attention

Seating is on a first come, first served basis.