Skip to main content

UF researchers using machine learning to pursue fusion power

Inside of a tokamak fusion reactor

UF researchers are improving the predictability of the plasma inside nuclear fusion reactor tokamak chambers like the one in this photo.

  • Ionized gas plasma contained inside a tokamak reactor is the engine that drives nuclear fusion, a potential source of green energy 
  • Off-normal events in the plasma are a substantial impediment to the success of tokamaks 
  • UF Nuclear Engineering researchers are using specialized machine learning algorithms running on HiPerGator to understand, predict and prevent off-normal plasma events 

Fusion research seeks to recreate on earth the processes responsible for powering the sun. Fusing atoms, which requires temperatures in excess of 100 million degrees Celsius, promises an abundant, carbon-free source of energy.  

But first, researchers need to tame the beast — the ionized gas plasma held in magnetic fields inside a reactor known as a tokamak. Armed with recent federal grants, University of Florida researchers are working to do just that.  

For Christopher McDevitt, Ph.D., a plasma physicist and professor in UF’s Nuclear Engineering program, understanding, predicting and ultimately preventing “off-normal” plasma behaviors inside a tokamak is the central challenge facing researchers around the world as they try to harness the energy released by fusing atoms together.  

Read full story on UF News.