Demystifying Digital Twin (DT)-Enabling Technologies for Nuclear Systems: An International Collaborative Effort
Dr. Syed Alam (Syed Bahauddin Alam) will be presenting ongoing work on "IDEA–Intelligent Digital Twins with Explainable AI," an international collaborative project with partners from the US: (Oracle Lab, INL, ORNL, Framatome, General Atomics); UK: (University of Bristol, University of Sheffield), Canada: Ontario Tech; and India: IIT Delhi. According to both US DOE and NRC, the nuclear industry has yet to fully leverage the recent advances in machine learning/artificial intelligence (ML/AI) techniques, and Digital Twin (DT) will play a significant role in risk-informed decision-making in this regard. For example, " NRC FY2021-23 Planned Research Activities" and "NRC Future Focused Research" state that "Methodology and Evaluation Tools for Digital Twin Applications" is one of the top priority strategic areas. However, the major challenges related to DT are (a) Incorporating trustworthy data analytics algorithm, (b) Treatment of noisy or erroneous data and data unavailability, (c) Uncertainty quantification, (d) Robust optimization, and (e) Update module in DT by solving the "On-the-fly Inverse Problem." This seminar will encompass the ongoing activities performed by Dr. Alam's group on different aspects of technical challenges in DT-enabling technologies for nuclear systems in terms of surrogate model development, physics-informed hybrid ML/AI, uncertainty quantification with sensitivity, and operational digital twin framework.
Bio: Dr. Syed Alam is an Assistant Professor of Nuclear Engineering and Radiation Science at the Missouri University of Science and Technology (Missouri S&T). He received Ph.D. (2018) and MPhil (2013) in Nuclear Engineering from the University of Cambridge. Prior to joining Missouri S&T, he was a Researcher at French Atomic Energy Commission. He also worked as a MeV Fellow at Argonne National Laboratory and a Nonproliferation Fellow at the Korea Advanced Institute of Science and Technology.
Dr. Alam’s research interests and expertise broadly lie in the intersection of nuclear systems, explainable machine learning, and computational materials — focusing on hybrid physics and data-driven analysis that warrants frequent excursions among the boundaries of applied mathematics and data science. To date, Dr. Alam published 70+ peer-reviewed articles. He received several awards and honors for his research and teaching. He received the University Outstanding Teaching Award 2021 by Missouri S&T. He was awarded the Most Exemplary Graduate Fellow on “Nuclear Nonproliferation Fellowship 2017” by the Korea Advanced Institute of Science & Tech (KAIST). He was also the winner of the ANS Best Student Paper Award (ICAPP 2016), nominated for the Young generation/Student Award for the Outstanding Paper (ICAPP 2017), and ANS Best Technical Poster Award (NURETH-16). For the continuation of an exceptionally promising piece of Ph.D. research, he was also awarded the Cambridge Philosophical Society Research Studentships Award (2017). His work has also been featured in the “ICE Business Times” Magazine and invited for a TV interview on Channel S (a UK-based TV Channel).