2025

Prof. Eleni Chatzi from ETH Zurich will present on the role of structural dynamics in learning, monitoring, and digital twinning as part of the ongoing EVACES IA Webinar Series.

New paper out, led by Lingzhen Li (Empa / SMM Group, ETH Zurich / Hong Kong Polytechnic University) in collaboration with Sizhe Wang (Empa / Nanyang Technological University), Tao Chen (Tongji University), Eleni Chatzi (SMM Group, ETH Zurich), Hossein Heydarinouri (Empa), and Elyas Ghafoori (Leibniz University Hannover)

Our research team from the Future Resilient Systems (FRS) programme at the Singapore-ETH Centre (SEC) conducted a successful pilot test in collaboration with the BE-FIT project under the Future Health Technologies (FHT) programme. The test marks a significant step toward understanding built environment factors affecting mobility.

This new survey paper, led by Hao Dong, explores the evolving landscape of multimodal adaptation and generalization, bridging traditional techniques with the power of foundation models.

The Chair of Structural Mechanics and Monitoring at ETH Zurich was well represented at IMAC 2025, held in Orlando, Florida. Our researchers and collaborators contributed to discussions on structural dynamics, uncertainty quantification, and vibration analysis, showcasing cutting-edge methodologies and novel applications.

Gregory Duthé offered an input talk on use of Graph Neural Network methods for wind farm predictive modelling during the Applied Machine Learning Days (AMLD), in the Machine Learning for Science and Engineering session, organized by Olga Fink and Johannes Brandstetter.

Members of the Chair of Structural Mechanics and Monitoring at ETH Zurich, including Konstantinos Vlachas, Kyriakos Chondrogiannis, and Marcus Haywood-Alexander, are actively participating in the ReCharged MSCA Staff Exchanges program. Their efforts contribute to advancing critical asset resilience through cutting-edge research and international collaboration.

Our group at the Singapore-ETH Centre (SEC) and the SMM Group at ETH Zurich presents a novel framework for input estimation in monitored systems using Imitation Learning from Observation (ILfO). Published in MSSP, the method reformulates input estimation as a Partially Observable Markov Decision Process (POMDP), integrating both known and learned dynamics. Validated through simulations and real-world experiments, it marks a significant step in advancing structural monitoring.