There are currently 94 nuclear reactors in operation in the United States, more than in any other country in the world, and these units collectively provide almost 20 percent of the nation’s electricity. Dean Price says this is a major achievement, but he believes that our country needs much more nuclear energy, especially at a time when we are desperately looking for alternatives to fossil fuel power plants. He became a nuclear engineer for precisely this reason – to ensure that nuclear technology was up to the task in this time of significant need.
“Nuclear power has been a huge part of our nation’s energy infrastructure for the last 60 years, and the number of people maintaining that infrastructure is incredibly small,” says Price, an assistant professor at MIT in the Department of Nuclear Science and Engineering (NSE) and the Atlantic Richfield Career Development Professor of Energy Studies. “When you become a nuclear engineer, you become one of the chosen people responsible for generating carbon-free energy in the United States.”
It was a mission he was eager to be a part of, and the goals he set for himself were not modest: he wanted to aid design and field a recent class of nuclear reactors, building on the safety, economics, and reliability of the existing nuclear fleet.
Price never strayed from that goal, and found nothing but encouragement along the way. The nuclear engineering community, he says, “is small, tight-knit and very friendly. Once you join it, most people don’t want to do anything else.”
Illuminating connections between physical processes
For his first research project as an undergraduate at the University of Illinois Urbana in Champaign, Price studied the safety of steel and concrete barrels used to store spent reactor fuel rods after they had been cooled in tanks of water, usually for several years. His analysis showed that this method of storage is reasonably safe and sound, although the question of what should ultimately be done with fuel drums for long-term disposal in this country remains open.
After entering graduate school at the University of Michigan in 2020, Price embarked on a different line of research, which he continues to pursue today. This field of research, called multiphysics modeling, involves looking at various physical processes taking place in the core of a nuclear reactor to see how they interact with each other. This is an alternative to studying these processes individually.
One key process, neutronics, involves how neutrons buzz around a reactor core, causing nuclear fission, which generates energy. The second process, called thermal hydraulics, involves cooling the reactor to extract the heat produced by the neutrons. A multiphysics simulation examining the interaction of these two processes could show how the heat removed when the reactor generates power affects the behavior of neutrons, because the hotter the fuel, the less likely it is to cause fission.
“If you ever want to change power levels or do anything to the reactor, fuel temperature is a key parameter you need to know,” Price says. “Multiphysics modeling allows us to link neutronic fission processes with a thermal property, i.e. temperature. This, in turn, can help us predict how the reactor will behave under different conditions.”
Multiphysics modeling of lightweight water reactors, which are currently operating at around 1,000 megawatts, is fairly well established, Price says. However, methods for modeling advanced reactors – diminutive modular reactors (SMRs with a capacity of approximately 20 to 300 MW) and microreactors (with a capacity of 1 to 20 MW) – are much less advanced. Only a diminutive number of these reactors are currently operating, but Price is focusing his efforts on them because of their potential for cheaper and safer energy production, as well as greater flexibility in power and size.
While multiphysics simulations have provided a wealth of information to the nuclear community, they may require supercomputers to solve or find approximate solutions to coupled and extremely arduous nonlinear equations. Hoping to significantly reduce the computational burden, Price is actively exploring AI-based approaches that could provide similar answers while bypassing these cumbersome equations altogether. This has been a central theme of his research agenda since he joined the MIT faculty in September 2025.
The key role of artificial intelligence
In particular, artificial intelligence and machine learning methods are good at finding patterns hidden in data, such as correlations between variables critical to the operation of a nuclear power plant. For example, Price says, “If you tell me what the power level of your reactor is, then yes [AI] it could tell you what the temperature of the fuel is and even the three-dimensional temperature distribution in your core. And if this can be done without solving complex differential equations, computational costs can be significantly reduced.
Price is exploring several applications where artificial intelligence could be particularly useful, such as helping to design novel types of reactors. “We could then rely on the security frameworks developed over the last 50 years to conduct a security analysis of the proposed design,” he says. “This way, the AI won’t be communicating directly with anything that is security-critical.” In his opinion, the role of artificial intelligence would be to improve established procedures, not to replace them and aid fill existing knowledge gaps.
When a machine learning model is given enough data to learn from, it can aid us better understand the relationship between key physical processes – again, without having to solve nonlinear differential equations.
“By really establishing these relationships, we can make better design decisions in the early stages,” says Price. “And once this technology is developed and deployed, AI can help us make more intelligent control decisions that will enable us to operate our reactors in a safer and more economical way.”
He gave back to the community that raised him
Simply put, one of its main goals is to bring the benefits of artificial intelligence to the nuclear industry, and its opportunities are seen as enormous and largely untapped. Price also believes that as a professor at MIT, he is in a good position to bring us closer to the nuclear future he envisions. According to him, he is working not only on developing next-generation reactors, but also on preparing the next generation of leaders in this field.
Price met some potential members of the “next generation” during a design course he co-taught last fall Curtis SmithKEPCO Professor of the Practice of Nuclear Science and Engineering. For Price, this introduction lasted only a few months, but it was enough for him to discover that MIT students were exceptionally motivated, hard-working and capable. Not surprisingly, these are the same qualities he hopes to discover in the students who join his research team.
Price clearly remembers the support he received when he took his first, tentative steps into this field. Now that he has risen from undergraduate to professor and gained a significant amount of knowledge along the way, he wants his students to “feel the same feeling I had when I started working in this field.” Beyond his specific goals of improving the design and operation of nuclear reactors, Price says, “I hope to perpetuate the same fun and healthy environment that made me love nuclear engineering in the first place.”