Costas

A recent report by the US Department of Energy defines the area of scientific machine learning as

“a core component of artificial intelligence (AI) and a computational technology that can be trained, with

scientific data, to augment or automate human skills”, which has “the potential to transform science and

energy research”. In this presentation, we discuss the potential of scientific machine learning methods to

problems in computational electromagnetics starting from standard electromagnetic structure analysis

and multi-physics modeling in the time-domain, employing unsupervised, supervised and reinforcement

learning.

An unsupervised learning strategy is based on a modified Physics-Informed Neural Network (PINN). PINNs

directly integrate physical laws into their loss function, so that the training process does not rely on the

generation of training ground truth data from simulations. We introduce a physics-informed deep-

operator-network (PI-DON) for Maxwell’s equations. We show applications of the PI-DON to the analysis,

design and uncertainty quantification study of finite and defect periodic structures, including frequency

selective surfaces and metasurfaces.

Moreover, we demonstrate the impact of machine learning on the computational modeling of radiowave

propagation scenarios and reconfigurable intelligent surfaces, using supervised learning. We build

convolutional neural network models that can process the geometry of indoor environments, along with

physics-inspired parameters, to rapidly estimate received signal strength (RSS) maps. Emphasis is placed

on the generalizability of these models, which is their ability to "learn" the physics of radiowave

propagation and produce accurate modeling predictions in new geometries well beyond those included in

their training set.

Finally, the use of reinforcement learning for the optimization of reconfigurable intelligent surfaces will be

discussed.

Biography:

Costas Sarris is a Professor with the Department of Electrical and Computer Engineering, University of

Toronto. His research area is computational electromagnetics, with an emphasis on time-domain

modeling. He also works on physics-based wireless propagation models (with full-wave, asymptotic, and

hybrid techniques), uncertainty quantification, and scientific machine learning.

Dr. Sarris is an IEEE Fellow and a Distinguished Lecturer of the IEEE Antennas and Propagation Society for

2024-2026. He was a recipient of the 2021 Premium Award for Best Paper in IET Microwaves, Antennas &

Propagation, and the IEEE MTT-S Outstanding Young Engineer Award in 2013. He was the TPC Chair of the

2015 IEEE AP-S International Symposium on Antennas and Propagation and the CNC/USNC Joint Meeting,

the 2019 and 2023 MTT-S Numerical Electromagnetics, Multiphysics and Optimization (NEMO)

Conference, the TPC Vice-Chair of the 2012 IEEE MTT-S International Microwave Symposium, and the Chair

of the MTT-S Technical Committee on Field Theory and Numerical Electromagnetics (2018–2020). In 2019-

2024, he was the Editor-in-Chief of the IEEE JOURNAL ON MULTISCALE AND MULTIPHYSICS

COMPUTATIONAL TECHNIQUES.

Email: