Jamie Coble joined the UW-Madison Department of Nuclear Engineering and Engineering Physics as a professor in August 2026. She is an expert in online monitoring, diagnostics and prognostics; risk-informed decision making; and advanced control for nuclear systems.
Coble grew up in Johnson City, Tennessee, and received all four of her degrees from the University of Tennessee, Knoxville. She earned a bachelor’s degree in nuclear engineering and mathematics in 2005, a master’s degree in nuclear engineering in 2006, a master’s degree in reliability and maintenance engineering in 2009, and a PhD in nuclear engineering in 2010. She comes to UW-Madison from the University of Tennessee, Knoxville, where she was a professor of nuclear engineering. She was hired through UW-Madison’s RISE-AI initiative.
In this Q&A, Coble talks about her research and passion for sparking students’ interest in nuclear sub-fields they might not have considered pursuing.
What is the focus of your research?
The work my research group does is broadly in data analytics and machine learning for a variety of nuclear applications. A lot of my work focuses on using the data already being collected from nuclear power and fuel cycle facilities to monitor what’s happening in the system and make data-driven, risk-informed decisions about operations and maintenance.
A lot of the inspection and maintenance in nuclear power plants is time-based, periodic maintenance. It’s like when you change the oil in your car every 3,000 miles—but maybe the oil was fine and you could have driven 5,000 miles, or maybe something happened and you need to change the oil sooner. In my research, we’re looking at how we can defer the periodic maintenance that doesn’t actually need to happen without missing any indicators of problems that could lead to equipment failures while the plant is operating. A significant amount of the cost of generating electricity from nuclear power is operations and maintenance, so looking at how we can better manage those costs in a way that doesn’t affect nuclear safety can have a big economic impact.
We also apply our data analytics techniques to nuclear security applications, where we might want to detect indications of proliferation or diversion of nuclear material or other facility misuse. The same monitoring approaches that we use to determine when the performance of equipment has changed can tell us when other changes occur in a system, like removal of material. Right now, we’re working on developing new AI-driven methods to test safeguards and security postures for fuel cycle facilities to identify vulnerabilities and optimize monitoring and detection systems. I’m also exploring opportunities to develop digital twins of fuel cycle-relevant labs that can explore both the digital twin capabilities and security of information and data transfer across institutions.
My research also has applications outside of nuclear. I’ve historically done a lot of work on monitoring the health of rotating equipment. Anything that rotates has a bearing in it—from pumps and motors to vehicle drivetrains. The evolving health of those bearings and other rotating components can tell a lot about how the equipment will perform and when maintenance will be required.
What attracted you to UW-Madison?
UW-Madison NEEP has a long reputation for being an outstanding department. A big draw for me was the UW Nuclear Reactor. I’m excited to explore what I can do with the reactor in terms of research—instrumentation and controls, digitalization, system monitoring or digital twin development—and even pursuing a license to operate the reactor!
What achievements are you most proud of in your career so far?
The thing I’m most proud of is the students I’ve had the opportunity to work with, both in my research group and in courses and less formal mentoring roles. Students from my group have gone on to make major contributions in careers at the IAEA (International Atomic Energy Agency), national labs and universities. Watching these graduates grow as engineers, researchers and nuclear leaders has given meaning to my career that I had never anticipated.
What courses will you be teaching?
I’ll be teaching a course in nuclear system dynamics in spring 2027 that will explore light water reactor system modeling and stability analysis. I hope to develop a follow-on course in the future that focuses on control systems and operational strategies for nuclear power plants. I’m also developing a new course that will cover how we can use data analytics and machine learning in nuclear applications; I hope to offer this course in fall 2027 for advanced undergraduate students and early graduate students interested in doing more with their data! I love working with students, and one of my favorite things is seeing students get engaged in a topic area that maybe isn’t exactly what they thought they’d be interested in initially.
What’s one thing you hope students who take a class with you will come away with?
In all the classes I’ve taught, I’ve tried to help students develop their skills in critical thinking, engineering judgment and clear communication. These skills can take students incredibly far in an engineering career, and they all need intentional development and practice. I also hope at least a few students come away excited about the opportunities available in nuclear instrumentation and controls and operations and maintenance, because there are so many exciting advancements to make in these areas. Outside of research, these areas make up a big part of the overall nuclear industry.
What are your hobbies and other interests?
I enjoy reading fiction of all types. My goal each year is to wear out my library card. I’ve got a 4-year-old son, and most of my time outside work revolves around fighting pretend bad guys, chasing after wobbly bicycles and building large structures out of moving boxes.
Photo of Jamie Coble by Joel Hallberg