Today, there are 94 nuclear power plants operating in the United States, more than any other country in the world, and these units together provide about 20 percent of the nation’s electricity. That’s a big achievement, according to Dean Price, but he believes our country needs more nuclear power, especially at a time when alternatives to fossil fuel-based power plants are being sought. He became a nuclear engineer for this reason – to make sure that nuclear technology is up to the task of delivering in this time of great need.
“Nuclear energy has been a large part of our nation’s energy infrastructure for the past 60 years, and the number of people who maintain that infrastructure is very small,” said Price, MIT assistant professor in the Department of Nuclear Science and Engineering (NSE), and the Atlantic Richfield Career Development Professor in Energy Studies. “By becoming a nuclear engineer, you become one of a select number of people responsible for producing carbon-free energy in the United States.”
That was a task he was eager to participate in, and his goals were far from modest: He wanted to help design and introduce a new class of nuclear devices, building on the safety, economics, and reliability of existing nuclear ships.
Price has never wavered from this goal, and has received encouragement along the way. The nuclear engineering community, he says, is “small, close-knit, and very welcoming.
Illuminating relationships between physical processes
In his first research project as an undergraduate at the University of Illinois Urbana in Champaign, Price studied the safety of steel and concrete boxes used to store spent reactor fuel rods after they have cooled in water tanks, often for several years. His analysis showed that this last method is safe, although the question of what should be done with these fuel boxes, in terms of long-term disposal, remains open in this country.
After starting graduate studies at the University of Michigan in 2020, Price took on a different line of research that he continues to do today. That area of study, called multiphysics modeling, involves looking at the various physical processes that take place in the context of a nuclear reactor to see how they interact – another way to study these processes simultaneously.
One important process, neutronics, concerns how neutrons circulating in the reactor core cause nuclear fission, which in turn produces energy. The second process, called thermal hydraulics, involves cooling the reactor to remove the heat produced by neutrons. Multiphysics simulations, which analyze how these two processes interact, can show that the heat absorbed as the reactor produces power affects the behavior of neutrons, because the hotter the fuel, the less likely it is to cause a fission.
“If you want to change your power level, or do anything with a reactor, the temperature of the fuel is an important parameter to know,” Price said. “Multiphysics modeling allows us to relate the fission neutronics processes to the thermal environment, the temperature. That can help us predict how the reactor will behave under different conditions.”
Multiphysics models of light water reactors, which are operating today with capacities on the order of 1,000 megawatts, are well established, Price said. But the modeling methods for advanced reactors – small modular reactors (SMRs with capacities ranging from about 20 to 300 MW) and microreactors (scaled from 1 to 20 MW) – have advanced significantly. Very few of these generators are in operation today, but Price has focused his efforts on them because of their potential to generate cheaper and safer power, as well as greater flexibility in power and size.
Although multiphysics simulations have provided the nuclear community with a wealth of knowledge, they can require supercomputers to solve, or find approximate, complex and complex solutions for nonlinear equations. Hoping to greatly reduce the computational burden, Price is actively exploring artificial intelligence methods that can provide similar answers while skipping those burdensome calculations altogether. That has been a central theme of his research agenda since he joined the MIT faculty in September 2025.
The important role of artificial intelligence
What artificial intelligence methods and machine learning methods, in particular, are good at is finding hidden patterns within data, such as correlations between important variables in the operation of a nuclear plant. For example, Price says, “if you tell me the power level of your reactor, it is [AI] it can tell you what the temperature of the fuel is and tell you the 3-dimensional temperature distribution of your spine.” And if this can be done without solving any complex differential equations, the computational cost can be greatly reduced.
Price is investigating several applications where AI might be particularly useful, such as helping with the design of novel types of reactors. “We can rely on the safety framework that was built 50 years ago to do a safety analysis of the proposed project,” he said. “In this way, the AI will not directly interact with anything that is very important to security.” As he sees it, the role of AI can be to augment established processes, rather than replace them, helping to fill existing gaps in knowledge.
If a machine learning model is given a sufficient amount of data to learn from, it can help us better understand the relationships between important physical processes – and without having to solve nonlinear differential equations.
“By getting those relationships down, we can make better design decisions at the beginning,” Price said. “And when that technology is developed and deployed, AI can help us make smarter control decisions that will enable us to operate our reactors in a safer and more cost-effective manner.”
Giving back to the community that raised him
Simply put, one of his main goals is to bring AI benefits to the nuclear industry, and he sees hundreds of untapped opportunities. Price also believes he is well placed as a professor at MIT to bring us closer to the nuclear future he envisions. As he sees it, he is not only working to develop the next generation of reactors, but also to help prepare the next generation of leaders in the field.
Price met other members of that “next generation” in a design course he co-taught with Curtis Smith, KEPCO Professor of the Practice of Nuclear Science and Engineering. For Price, that introduction lasted just a few months, but it was long enough for him to discover that MIT students are exceptionally motivated, hardworking, and talented. Not surprisingly, those same qualities are what he hopes to find in the students who join his research team.
Price remembers well the support he received when he took his first tentative steps in the industry. Now that he has risen through the ranks from undergraduate to professor, and gained a body of knowledge along the way, he wants his students to “feel that feeling I had when I entered the field.” Aside from his specific goals of improving the design and performance of nuclear reactors, Price says, “I hope to continue the same fun and healthy environment that made me fall in love with nuclear engineering in the first place.”
