Physics-Informed Machine Learning for EMC: Techniques and Applications
EMC Professional Talk
In recent years, machine learning has become an essential tool for the design and analysis of complex RF and microwave systems. This talk highlights recent advances in machine learning–based methodologies, developed by considering the characteristics of the system under study and how its physical properties are represented in the training data (physic-informed approach). Both neural network–based techniques and data-efficient methods, particularly those relying on Gaussian processes, will be discussed. Their key characteristics will be outlined, along with their application to challenging electromagnetic compatibility (EMC) problems.
Date and Time
Location
Hosts
Registration
Add Event to Calendar
Speakers
Domenico
Physics-Informed Machine Learning for EMC: Techniques and Applications
In recent years, machine learning has become an essential tool for the design and analysis of complex RF and microwave systems. This talk highlights recent advances in machine learning–based methodologies, developed by considering the characteristics of the system under study and how its physical properties are represented in the training data (physic-informed approach). Both neural network–based techniques and data-efficient methods, particularly those relying on Gaussian processes, will be discussed. Their key characteristics will be outlined, along with their application to challenging electromagnetic compatibility (EMC) problems.
Biography:
Domenico Spina (Senior Member, IEEE) received the M.S. degree (cum laude) in electronics engineering from the University of L’Aquila, Italy, in 2010, and the joint Ph.D. degree in electrical engineering from Ghent University, Belgium, and the University of L’Aquila in 2014. From 2015 until 2023, he has been a Member of the Internet and Data Science Lab (IDLab) of the Department of Information Technology (INTEC), Ghent University - imec, first as Postdoctoral Researcher and then as R&D Technical Lead. He is currently a professor at the ELEC department of the Vrije Universiteit Brussel. His research interests include modeling and simulation, uncertainty quantification, and machine learning for EMC/SI/PI problems.
Email: