Machine learning, harnessed to extreme computing, aids fusion energy development

MIT scientists completed one of the most demanding calculations in fusion science: predicting the temperature and density profiles of a magnetically confined plasma via first-principles simulation of plasma turbulence. The researchers used an optimization methodology developed for machine learning to dramatically reduce the CPU time required while maintaining the accuracy of the solution.

Related Keywords

Netherlands ,Dutch ,Jonathan Citrin ,Nathan Howard ,Pablo Rodriguez Fernandez ,Dutch Institute For Fundamental Energy Research ,Eindhoven University Of Technology ,Fusion Center ,Nuclear Fusion ,National Energy Research Scientific Computing Center ,Commonwealth Fusion Systems ,General Atomics ,Jeff Candy ,Eindhoven University ,Dutch Institute ,Fundamental Energy Research ,Energy Office ,Science User ,Plasma Science And Fusion Center Psfc ,Plasma Turbulence ,Parc ,Tokamak Reactors ,Martin Greenwald ,Gyro Code ,Ommonwealth Fusion Systems Cfs ,Nersc ,