Researchers from Princeton University and its Princeton Plasma Physics Laboratory have developed an AI model that predicts and prevents plasma from becoming unstable and escaping the strong magnetic fields inside donut-shaped reactors. This is a significant step towards generating fusion energy. The model can predict so-called tearing mode instabilities 300 milliseconds before they occur, providing enough time to control the plasma. The AI system was tested on a real reactor, the DIII-D National Fusion Facility in San Diego, and was found to effectively control the power being pumped into the reactor and the shape of the plasma to keep the particles in check
Read more at: https://www.vice.com