maokun li





Tsinghua University, China



Application of Deep Learning to Computational Electromagnetics


In recent years, research in deep learning techniques has attracted much attention. With the help of big data technology, massively parallel computing, and fast optimization algorithms, deep learning has dramatically improved the performance of many problems in speech and image research. In electromagnetic engineering, physical laws provide the theoretical foundation for research and development. With the development of deep learning, improvement in learning capacity may allow machines to “learn” from a large amount of physics data and “master” the physical law in certain controlled boundary conditions. In the long run, a hybridization of fundamental physical principles with “knowledge” from big data could unleash numerous engineering applications that are limited by a lack of data information and computation ability. In this talk, the presenter will share some of his learnings in deep learning techniques and discuss the potential and feasibility of applying deep learning in computational electromagnetics. The presenter hopes to explore the characteristics, feasibility, and challenges of deep learning in the field of computational electromagnetics through some examples, such as solving wave equations, array antenna synthesis, inverse scattering, etc.





Maokun Li received the B.S. degree in electronic engineering from Tsinghua University, Beijing, China, in 2002, and the M.S. and Ph.D. degrees in electrical engineering from University of Illinois at Urbana-Champaign, Champaign, IL, USA, in 2004 and 2007, respectively. He then worked as a Senior Research Scientist with Schlumberger-Doll Research, Cambridge, MA, USA. In 2014, he joined the Department of Electronic Engineering, Tsinghua University, Beijing. He is currently a professor at the Microwave and Antenna Institute. His interest is in electromagnetic theory and computational electromagnetics, especially in fast and reliable modeling and inversion algorithms for EM wave propagation in complex environments, with applications to geophysical exploration, biomedical imaging, etc. He coedited the book Applications of Deep Learning in Electromagnetics: Teaching Maxwell’s Equations to Machines, published by the Institution of Engineering and Technology (IET) in 2022. Several algorithms have been commercialized into the data processing workflow for geophysical and biomedical imaging systems. He serves as an associate editor of IEEE TAP and TGRS. He is also a member of the AP-S membership and benefits committee and serves as the IEEE AP-S Distinguished Lecturer (2023-2025). He received the 2017 IEEE Ulrich L. Rohde Innovative Conference Paper Award, the 2019 PIERS Young Scientist Award, and the 2021 Instructor Award for Excellent Ph.D. Thesis by China Education Society of Electronics. He was elected as a Fellow of the Applied Computational Electromagnetics Society (ACES) in 2022 and IEEE Fellow in 2025.