- Other states following Assam's cancer care model: Himanta Biswa Sarma
- TalentSprint announces new program ‘WISH’ for Women Engineering students
- IAF C-130J makes safe landing at Begumpet airport after technical snag
- Canadian International School hosts its 10th edition of Model United Nations conference
- Nirmala Sitharaman launches Rs 1,000 cr worth infra projects
- Arun Singh Dhumal welcomes England team with 'perfect conditions' at HPCA
- Hindu teacher acquitted in blasphemy case after five years in Pakistan
- 10 Manipur tribal MLAs urge Centre not to cancel 'Suspension of Operations' pact with Kuki militant outfits
- Financial Intelligence Unit slaps Rs 5.49 cr penalty on Paytm Payments Bank
- I want to quit as Trinamool spokesman, but continue as party soldier: Kunal Ghosh
Machine Learning may help capture fusion energy on Earth
A team of researchers in the US have used Machine Learning (ML) to rapidly control plasma that fuels fusion reactions, paving the way to help Earth...
A team of researchers in the US have used Machine Learning (ML) to rapidly control plasma that fuels fusion reactions, paving the way to help Earth get the clean fusion energy that lights the Sun and stars.
Researchers at the U.S. Department of Energy's (DOE) Princeton Plasma Physics Laboratory (PPPL) are using ML to create a model for rapid control of plasma -- the state of matter composed of free electrons and atomic nuclei, or ions.
The Sun and most stars are giant balls of plasma that undergo constant fusion reactions. Here on Earth, scientists must heat and control the plasma to cause the particles to fuse and release their energy. Researchers now show ML can facilitate such control.
The team led by physicist Dan Boyer trained neural networks -- the core of ML software -- on data produced in the first operational campaign of the National Spherical Torus Experiment-Upgrade (NSTX-U), the flagship fusion facility at PPPL.
The trained model accurately reproduced predictions of the behaviour of the energetic particles produced by powerful neutral beam injection (NBI) that is used to fuel NSTX-U plasmas and heat them to million-degree, fusion-relevant temperatures.
"The new ML software reduces the time needed to accurately predict the behavior of energetic particles to under 150 microseconds -- enabling the calculations to be done online during the experiment," the findings showed.
The rapid evaluations will also help operators make better-informed adjustments between experiments that are executed every 15-20 minutes during operations. "Accelerated modeling capabilities could show operators how to adjust NBI settings to improve the next experiment," said Boyer, lead author of a paper in the journal Nuclear Fusion.