Dataset Open Access

QLKNN10D training set

Karel Lucas van de Plassche; Jonathan Citrin

Karel Lucas van de Plassche
Work package leader(s)
Jonathan Citrin

This dataset contain a large-scale run of 300 million flux calculations of the quasilinear gyrokinetic transport model QuaLiKiz. QuaLiKiz is used in many Fusion integrated modelling suites within Europe, and is openly available at This dataset was generated with v2.4.0 'Big dataset edition' of QuaLiKiz, see Note that GyroBohm fluxes were rescaled to match the normalizations of fluxes with a instead of R0, as is the case for v2.4.1 and later. The dataset was used to train neural network versions of QuaLiKiz, which when integrated in modelling suites allow for near-real time tokamak core transport simulations. Please check our proof-of-principle and application in RAPTOR, short paper for the EPS 2019 conference, and published in the Physics of Plasmas ICDDPS2 Special Issue This paper is also available on arXiv and zenodo 10.5281/zenodo.3595558.

Related repositories:

This work has been carried out within the framework of the EUROfusion Consortium and has received funding from the Euratom research and training programme 2014-2018 and 2019-2020 under grant agreement No 633053. The views and opinions expressed herein do not necessarily reflect those of the European Commission.
Files (32.1 GB)
Name Size
240 Bytes Download
13.3 GB Download
4.6 kB Download
12.6 GB Download
6.2 GB Download
  • F. Felici et al. (2018). Real-time-capable prediction of temperature and density profiles in a tokamak using RAPTOR and a first-principle-based transport model (

  • J. Citrin et al. (2015). Real-time capable first principle based modelling of tokamak turbulent transport (

All versions This version
Views 137137
Downloads 134134
Data volume 822.4 GB822.4 GB
Unique views 116116
Unique downloads 3030


Cite as