Artificial intelligence (AI) technologies could bring us closer to practical nuclear fusion energy, which could transform the energy sector worldwide.
AI has cracked the code of nuclear fusion to destroy oil and gas
MIT scientists have completed one of the most demanding calculations in fusion science using a machine learning technique. According to a recently published paper, the method reduced the CPU time needed to perform the calculations while maintaining the accuracy of the solution. It's part of a growing effort to use AI to solve the mathematical and engineering problems of controlling fusion energy.
“AI is a tool that allows scientists to run experiments faster, make better predictions about how plasma behaves under extreme conditions, and build new fusion devices with greater precision,” Andrew Holland, CEO of the Fusion Industry Association, told Lifewire in an email interview.
MIT researchers Pablo Rodriguez-Fernandez and Nathan Howard are working to predict the expected performance in the SPARC device, a compact, high-magnetic-field fusion experiment currently under construction. Although the calculation required a huge amount of computer time (more than 8 million CPU hours), the researchers were able to reduce the time required.
