The nuclear industry, as highlighted by both the U.S. Nuclear Regulatory Commission (NRC) and the Department of Energy (DOE), has yet to fully harness the potential of recent advancements in AI/ML techniques. In this context, Digital Twin (DT) technology is poised to play a pivotal role in facilitating risk-informed decision-making. The NRC's "FY2021-23 Planned Research Activities" and "NRC Future Focused Research" identify "Methodology and Evaluation Tools for Digital Twin Applications" as a top-priority strategic area. However, the implementation of DT in nuclear systems poses significant challenges that need to be addressed. These challenges encompass various aspects, including: (a) Incorporating trustworthy data analytics algorithms, (b) Dealing with noisy or erroneous data and addressing data unavailability, (c) Quantifying uncertainties associated with DT, (d) Ensuring robust optimization techniques, and (e) Developing update modules in DT through the resolution of "On-the-fly Inverse Problems." In this panel session, we will explore the enabling technologies and components required to establish DT in the nuclear industry. Our discussion will delve into the solutions for tackling the aforementioned challenges and unlocking the potential benefits of DT for nuclear systems.


  • Askin Guler Yigitoglu (ORNL)
  • Daniel Nichols (United States Department of Energy)
  • Kishor Datta Gupta (Clark Atlanta Univ.)
  • Syed Bahauddin Alam (Univ. Illinois, Urbana-Champaign)


To join the conversation, you must be logged in and registered for the meeting.

Register NowLog In