MO-A4.1A.5
Efficient Uncertainty Analysis for Printed Microstrip Antennas Using a Physics-Informed Deep Operator Network
Shutong Qi, Costas Sarris, University of Toronto, Canada
Session:
Optimization and Machine Learning Oral
Track:
AP-S: Computational and Analytical Techniques
Location:
Room 212
Session Time:
Mon, 14 Jul, 08:00 - 09:40
Presentation Time:
Mon, 14 Jul, 09:20 - 09:40
Session Co-Chairs:
Vikass Monebhurrun, CentraleSupélec and Agostino Monorchio, Università di Pisa
Presentation
Discussion
Session MO-A4.1A
MO-A4.1A.1: Physics-Constrained Neural Networks for Electromagnetic Surrogate Modelling
Niels Skovgaard Jensen, Frederik Faye, Lasse Hjuler Christiansen, Oscar Borries, Min Zhou, TICRA, Denmark; Erio Gandini, ESA-ESTEC, Denmark
MO-A4.1A.2: Smart Absorbing Material Positioning for Bistatic RCS Reduction: a Reinforcement Learning Approach
Edoardo Giusti, Pierpaolo Usai, Danilo Brizi, Agostino Monorchio, Università di Pisa, Italy
MO-A4.1A.3: Non-Parametric and Surrogate Model Assisted Optimization of Stacked Patch Antenna in CST Studio Suite
Md Khadimul Islam, Bidisha Barman, Enow Tanjong, Apra Pandey, Dassault Systemes, United States
MO-A4.1A.4: Novel application of GUM for uncertainty quantification in SAR simulations
Yiwen Zhang, Vikass Monebhurrun, CentraleSupélec, France
MO-A4.1A.5: Efficient Uncertainty Analysis for Printed Microstrip Antennas Using a Physics-Informed Deep Operator Network
Shutong Qi, Costas Sarris, University of Toronto, Canada
Resources
No resources available.