{"692146":{"#nid":"692146","#data":{"type":"event","title":"ISyE Seminar - Eunshin Byon ","body":[{"value":"\u003Cp\u003ETitle:\u003C\/p\u003E\u003Cp\u003ELearning What Matters: Scalable Offline and Online Calibration of Digital Twins\u003C\/p\u003E\u003Cp\u003EAbstract:\u003C\/p\u003E\u003Cp\u003EDigital twins promise continuous, high-fidelity representations of physical systems, yet their practical deployment is often constrained by the computational cost of simulation and calibration. This talk presents a unified perspective on making digital twin calibration more efficient, adaptive, and scalable by learning where computational effort matters most.\u003C\/p\u003E\u003Cp\u003EThe first part addresses offline calibration of block-structured models. I introduce a doubly importance-driven calibration method that learns which parameter blocks and which observations are most informative, and directs simulation effort toward the parts of the problem that contribute most to the optimization. This targeted allocation substantially reduces computational cost while preserving calibration accuracy.\u003C\/p\u003E\u003Cp\u003EThe second part turns to online calibration, where model parameters evolve over time and computational resources are limited. The proposed framework combines fast, edge-side surrogate filtering with periodic, cloud-side discrepancy correction based on high-fidelity simulations. This two-tier architecture enables real-time parameter adaptation while maintaining consistency with the underlying digital twin.\u003C\/p\u003E\u003Cp\u003ETogether, these methods show how learning what matters\u2014in parameters, observations, and computation\u2014can support digital twins that remain accurate, scalable, and continuously adaptive in practice.\u003C\/p\u003E\u003Cp\u003EBio:\u003C\/p\u003E\u003Cp\u003EDr. Eunshin Byon is a Professor in the Department of Industrial and Operations Engineering at the University of Michigan, Ann Arbor, where she also serves as Director of the Master\u0027s Program. She received her Ph.D. in Industrial and Systems Engineering from Texas A\u0026amp;M University in 2010. Her research spans data science, digital twin modeling and analysis, and quality and reliability engineering, with applications in energy, healthcare, and manufacturing systems. She served as Chair of the Quality, Statistics, and Reliability (QSR) Section of INFORMS in 2019\u20132020, and her research group has received multiple research and teaching awards from INFORMS, IISE, and IEEE. Dr. Byon is currently a Senior Editor for the INFORMS Journal on Data Science (2024\u2013present) and a Department Editor for IISE Transactions (2021\u2013present). She previously served as an Associate Editor for IISE Transactions (2019\u20132021), the INFORMS Journal on Data Science (2020\u20132024), and IEEE Transactions on Automation Science and Engineering (2019\u20132021).\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EDigital twins promise continuous, high-fidelity representations of physical systems, yet their practical deployment is often constrained by the computational cost of simulation and calibration. This talk presents a unified perspective on making digital twin calibration more efficient, adaptive, and scalable by learning where computational effort matters most.\u003C\/p\u003E\u003Cp\u003EThe first part addresses offline calibration of block-structured models. I introduce a doubly importance-driven calibration method that learns which parameter blocks and which observations are most informative, and directs simulation effort toward the parts of the problem that contribute most to the optimization. This targeted allocation substantially reduces computational cost while preserving calibration accuracy.\u003C\/p\u003E\u003Cp\u003EThe second part turns to online calibration, where model parameters evolve over time and computational resources are limited. The proposed framework combines fast, edge-side surrogate filtering with periodic, cloud-side discrepancy correction based on high-fidelity simulations. This two-tier architecture enables real-time parameter adaptation while maintaining consistency with the underlying digital twin.\u003C\/p\u003E\u003Cp\u003ETogether, these methods show how learning what matters\u2014in parameters, observations, and computation\u2014can support digital twins that remain accurate, scalable, and continuously adaptive in practice.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Learning What Matters: Scalable Offline and Online Calibration of Digital Twins"}],"uid":"36870","created_gmt":"2026-09-01 12:59:04","changed_gmt":"2026-09-01 13:02:37","author":"bjones434","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2026-09-11T11:00:00-04:00","event_time_end":"2026-09-11T12:00:00-04:00","event_time_end_last":"2026-09-11T12:00:00-04:00","gmt_time_start":"2026-09-11 15:00:00","gmt_time_end":"2026-09-11 16:00:00","gmt_time_end_last":"2026-09-11 16:00:00","rrule":null,"timezone":"America\/New_York"},"location":"George Tower 15th Floor. Room 1502","extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"194945","name":"Alumni"},{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}