Working to advance the nuclear renaissance | MIT News | Massachusetts Institute of Technology

In an era when the world is urgently seeking alternatives to fossil fuels, nuclear power stands as one of the most promising sources of carbon-free energy. With 94 nuclear reactors operating across the United States—more than in any other country—these facilities already provide nearly 20% of the nation's electricity. Yet, according to MIT Assistant Professor Dean Price, this represents just the beginning of what nuclear energy could achieve.

Price, who serves as both an assistant professor in the Department of Nuclear Science and Engineering (NSE) and the Atlantic Richfield Career Development Professor in Energy Studies, has dedicated his career to advancing nuclear technology. His vision extends beyond simply maintaining the existing fleet; he aims to design and usher in a new generation of reactors that offer enhanced safety, improved economics, and greater reliability.

"Nuclear energy has been a tremendous part of our nation's energy infrastructure for the past 60 years, and the number of people who maintain that infrastructure is incredibly small," Price explains. "By becoming a nuclear engineer, you become one of a select number of people responsible for carbon-free energy generation in the United States." This sense of mission drew him to the field, and he has pursued it with unwavering determination.

The Challenge of Advanced Reactor Design

As a nuclear engineering undergraduate at the University of Illinois Urbana-Champaign, Price began his research journey by studying the safety of steel and concrete casks used to store spent reactor fuel rods. His analysis confirmed the safety of this storage method, though he noted that long-term disposal solutions remain an open question in the United States.

During his graduate studies at the University of Michigan starting in 2020, Price shifted his focus to multiphysics modeling—a sophisticated approach to understanding the complex interactions of various physical processes within a nuclear reactor core. This represents a significant departure from traditional methods that study these processes in isolation.

Within a nuclear reactor, two primary physical processes demand attention: neutronics and thermal hydraulics. Neutronics involves the behavior of neutrons that cause nuclear fission, generating power. Thermal hydraulics concerns the cooling systems that remove heat from the reactor core. These processes are deeply interconnected—fuel temperature, for instance, directly affects neutron behavior and fission rates.

"If you ever want to change your power level, or do anything with the reactor, the temperature of the fuel is a critical input that you need to know," Price explains. "Multiphysics modeling allows us to correlate the fission neutronics processes with a thermal property, temperature. That, in turn, can help us predict how the reactor will behave under different conditions."

While multiphysics modeling for traditional light water reactors (which generate approximately 1,000 megawatts) is well-established, methods for modeling advanced reactors remain far less developed. These include small modular reactors (SMRs with capacities from 20 to 300 MW) and microreactors (rated at 1 to 20 MW), which offer significant advantages in terms of cost, safety, and flexibility.

"Only a very small number of these reactors are operating today, but I'm focusing my efforts on them because of their potential to produce power more cheaply and more safely, along with their greater flexibility in power and size," Price notes.

The Computational Challenge

Multiphysics simulations, while invaluable, present substantial computational hurdles. They require solving or approximating coupled, extremely difficult nonlinear equations—a task that often demands supercomputing resources and significant time.

This computational bottleneck has limited the widespread adoption of advanced multiphysics modeling in the nuclear industry. For smaller companies and research institutions without access to massive computing resources, these sophisticated simulations remain out of reach.

Recognizing this limitation, Price has been actively exploring artificial intelligence approaches that could provide similar insights while bypassing the need to solve those complex equations directly. This focus on AI applications has become a central theme of his research agenda since he joined the MIT faculty in September 2025.

AI: A Transformative Tool for Nuclear Engineering

Artificial intelligence and machine learning excel at identifying patterns within complex data sets—precisely what's needed to understand the intricate relationships between variables in nuclear reactor operation.

"For example, if you tell me the power level of your reactor, [AI] could tell you what the fuel temperature is and even tell you the 3-dimensional temperature distribution in your core," Price illustrates. "And if this can be done without solving any complicated differential equations, computational costs could be greatly reduced."

This capability has profound implications for the nuclear industry. Reduced computational requirements would make advanced modeling accessible to a broader range of organizations, accelerating innovation and improving reactor designs.

Price is investigating several specific applications where AI could prove particularly valuable. One promising area is in the design of novel reactor types. "We could then rely on the safety frameworks developed over the past 50 years to carry out a safety analysis of the proposed design," he explains. "In this way, AI will not be directly interfacing with anything that is safety-critical."

According to Price, AI's role should be to augment established procedures rather than replace them, helping to fill gaps in existing knowledge. When trained on sufficient data, machine learning models can reveal relationships between physical processes that might otherwise remain hidden.

"By really pinning down those relationships, we can make better design decisions in the early stages," Price states. "And when that 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."

Bridging Research and Education

Beyond his technical research, Price is committed to nurturing the next generation of nuclear engineers. Last fall, he co-taught a design course with Curtis Smith, the KEPCO Professor of the Practice of Nuclear Science and Engineering. This brief interaction was enough for him to recognize the exceptional qualities of MIT students.

"MIT students are exceptionally motivated, hard-working, and capable," Price observes. These are precisely the qualities he seeks in students who join his research team.

His own journey in nuclear engineering has been marked by the support he received from mentors and colleagues. Having progressed from undergraduate to professor and accumulated substantial expertise along the way, he now aims to provide similar guidance to his students.

"I hope to perpetuate the same fun and healthy environment that made me love nuclear engineering in the first place," Price reflects.

The Path Forward

Price's work sits at the intersection of two transformative fields: nuclear engineering and artificial intelligence. By bringing these domains together, he aims to accelerate the development of advanced nuclear reactors that could play a crucial role in global efforts to combat climate change.

The potential impact extends beyond technical innovation. By making advanced modeling more accessible through AI, Price's research could democratize nuclear reactor design, allowing smaller companies and institutions to contribute to the nuclear renaissance.

As he continues his work at MIT, Price remains focused on both immediate technical challenges and the broader vision of a future where nuclear energy provides a substantial portion of the world's electricity—safely, economically, and sustainably.

"By becoming a nuclear engineer, you become one of a select number of people responsible for carbon-free energy generation in the United States," Price reiterates, highlighting the unique opportunity and responsibility that comes with working in this field. "That was a mission I was eager to take part in, and the goals I set for myself were far from modest: I wanted to help design and usher in a new class of nuclear reactors, building on the safety, economics, and reliability of the existing nuclear fleet."

With the integration of artificial intelligence into nuclear engineering, Price and his colleagues may well be on the cusp of realizing that vision.