4 papers
Application of Gaussian process regression to plasma turbulent transport model validation via integrated modelling
Aaron Ho, Jonathan Citrin, Fulvio Auriemma +7
This paper outlines an approach towards improved rigour in tokamak turbulence transport model validation within integrated modelling. Gaussian process regression (GPR) techniques w…
Neural network surrogate of QuaLiKiz using JET experimental data to populate training space
Aaron Ho, Jonathan Citrin, Clarisse Bourdelle +5
Within integrated tokamak plasma modelling, turbulent transport codes are typically the computational bottleneck limiting their routine use outside of post-discharge analysis. Neur…
Fast modeling of turbulent transport in fusion plasmas using neural networks
Karel Lucas van de Plassche, Jonathan Citrin, Clarisse Bourdelle +7
We present an ultrafast neural network (NN) model, QLKNN, which predicts core tokamak transport heat and particle fluxes. QLKNN is a surrogate model based on a database of 300 mill…
Global scaling of the heat transport in fusion plasmas
Sara Moradi, Johan Anderson, Michele Romanelli +2
A global heat flux model based on a fractional derivative of plasma pressure is proposed for the heat transport in fusion plasmas. The degree of the fractional derivative of the he…