Tutorial at ACC2023

🔎 Physics-informed machine learning (PIML) stands at the crossroads of machine learning algorithms and physical constraints, offering a more informed approach compared to purely data-driven methods. The tutorial aims to provide an overview of recent advances in PIML for dynamical system modeling and control, discussing theory, methods, tools, and applications.

Organizers:
Truong Xuan Nghiem, Northern Arizona University
Colin Jones, École Polytechnique Fédérale de Lausanne (EPFL)
Ján Drgoňa, Pacific Northwest National Laboratory
Zoltan Nagy, The University of Texas at Austin
Ankush Chakrabarty, Mitsubishi Electric Research Laboratories (MERL)

📚 Key topics will include:
Physics-informed system identification
Physics-informed learning-based control
Analysis, verification, and uncertainty quantification of PIML models
Physics-informed digital twins

📊 The tutorial will also feature specific applications of PIML in data-driven modeling and control. A valuable opportunity for new researchers and graduate students interested in the field!

🎙️Presenters:
Truong Xuan Nghiem, Ján Drgoňa, Colin Jones, Zoltan Nagy, Roland Schwan, Biswadip Dey, Ankush Chakrabarty, Stefano Di Cairano, Joel Paulson, Andrea Carron, Melanie Zeilinger, Wenceslao Shaw Cortez, and Draguna Vrabie: “Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems: Opportunities and Challenges”
Loris Di Natale and Colin Jone: “Physics-Inspired Neural Networks for Modeling and Control”
Ján Drgoňa: “Differentiable Programming for Modeling and Control of Energy Systems”
Biswadip Dey: “Physics-Informed Machine Learning for Inverse Problems”

More here: https://www.linkedin.com/posts/american-control-conference_acc2023-acc2023-physicsinformedml-activity-7062284144642297857-0bbm?utm_source=share&utm_medium=member_desktop