Advanced computing is being utilized to predict a key occurrence in nuclear fission reactions, which could help improve energy production in future plants, according to a new study in the journal Nuclear Science & Techniques.
While the effort likely won't immediately yield a power plant, the improved modeling can aid nuclear scientists' understanding of vital performance metrics — including the fission product yields of thorium-232 — benefiting emerging thorium-based reactors.
In a press release, the experts from Henan Normal University, Peking University, and the China Institute of Atomic Energy summarized their findings.
"By addressing specific gaps in existing nuclear databases while maintaining consistency with established physical principles, this methodology offers a highly promising approach for future nuclear data assessment efforts," the press release stated.
The team used a Bayesian neural network framework — an artificial intelligence and probability-based predictive model — to provide better thorium-232 yield data across different neutron irradiation energy levels.
"The scarcity of experimental data between these energies presents challenges for reactor design and safety analysis," the press release explained.
Scientists hoped their findings would have direct applications for next-generation thorium-based reactors, such as a molten salt reactor project in China.
The World Nuclear Association reported that there are about 440 fission plants worldwide, producing about 9% of the planet's electricity.
The United States had 94 reactors as of April 2024, according to the U.S. Energy Information Administration. As the International Atomic Energy Agency noted, molten salt is a design feature under development, offering enhanced safety and other benefits.
Fission plants split atoms through particle collisions, producing heat that can power a turbine to create electricity.
TCD Picks » Quince Spotlight
💡These best-sellers from Quince deliver affordable, sustainable luxury for all
|
Which of these savings plans for rooftop solar panels would be most appealing for you?
Click your choice to see results and speak your mind. |
Save $1,000 this year 💸 While the abundant energy source doesn't produce harmful carbon pollution, it does produce long-lasting radioactive waste and carries well-documented, yet rare, meltdown risks.
Green America cited weapons proliferation, security, and high costs among the downsides of nuclear energy.
As for costs, the Colorado-based energy think tank RMI found that solar and wind were among the cheapest energy sources to develop, especially when compared to coal, oil, and gas. Nuclear proponents consider the investment and risks worth the energy production.
Nuclear waste exists in the form of solid pellets, and the Department of Energy determined that the U.S. generates enough to fill nearly half of an Olympic-size swimming pool each year.
While easier to deal with than the nuclear "ooze" seen in pop culture, spent fuel can remain hazardous for centuries.
Energy developments like these are encouraging news, as electricity rates nationwide are reported to be rising faster than inflation.
But homeowners don't have to wait for long and costly nuclear research to yield results, as home solar can greatly reduce or even eliminate utility bills. TCD's Solar Explorer can connect you with the right system for the best price.
In China, the researchers are proving that AI can play a role in creating energy sources for the future.
"This approach represents an evolution in nuclear data evaluation methodology by effectively integrating machine learning capabilities with established physical principles," the release stated.
"The work demonstrates that machine learning methods can powerfully complement traditional nuclear physics approaches when properly constrained by physical principles."
Get TCD's free newsletters for easy tips to save more, waste less, and make smarter choices — and earn up to $5,000 toward clean upgrades in TCD's exclusive Rewards Club.
Cool Picks
