Accelerating Plasma Simulations for Fusion Reactors Using Artificial Intelligence
Our researchers Nikola Vukasinović, Ivona Vasileska, Leon Kos and Uroš Urbas have published a new article in the journal Engineering Applications of Artificial Intelligence:
“Accelerating Particle-in-Cell simulations in Tokamak Scrape-off Layer using segmented surrogate models”
The article presents how machine learning can significantly speed up calculations in fusion reactors. Instead of slow but highly accurate PIC simulations, the authors use a segmented surrogate model that enables faster predictions of plasma properties in the Scrape-off Layer region. This means faster design cycles, better understanding of plasma behavior, and a step closer to efficient fusion energy.✨
Congratulations on this new research achievement, which makes an important contribution to the development of advanced methods for accelerating plasma simulations !
