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.
Jonathan Citrin Nathan Howard Pablo Rodriguez Fernandez Dutch Institute For Fundamental Energy Research Eindhoven University Of Technology Fusion Center
Source: mit.edu