Parameterization of Pedestal Values in Fusion Plasma-ParaPED Using Machine Learning
Title: Parameterization of Pedestal Values in Fusion Plasma-ParaPED Using Machine Learning
SNIC Project: SNIC 2018/7-41
Project Type: SNIC Small Compute
Principal Investigator: Rongzhen Chen <rongzhen@chalmers.se>
Affiliation: Chalmers tekniska högskola
Duration: 2018-07-19 – 2020-08-01
Classification: 10201
Homepage: https://www.chalmers.se/en/staff/Pages/rongzhen.aspx
Keywords:

Abstract

Fusion power is one of very few long-term solutions for a sustainable electricity production. Fusion power is highly sensitive to the pedestal height and a reliable model of the pedestal is therefore essential. A predictive model for the pedestal height called Europed is being developed. However, a single calculated data point for Europed takes about 1 hr wall time. Therefore, it prohibits the direct inclusion of the calculated results from Europed into the predictive transport codes. Hence a model, which predicts the pedestal height accurately and encapsulates the non-linear behaviour of physical model, would be exceedingly useful. In this project, the parameterization will be predicted and analysed by machine learning and deep neural network methods. This will require much computation time, especially for the deep neural network method. Moreover, GPU architecture in Triolith can be beneficial for this project as well.