QLKNN10D training set
Description
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 qualikiz.com. This dataset was generated with v2.4.0 'Big dataset edition' of QuaLiKiz, see https://gitlab.com/qualikiz-group/QuaLiKiz/-/tags/v2.4.0. 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 https://aip.scitation.org/doi/10.1063/1.5134126. This paper is also available on arXiv https://arxiv.org/abs/1911.05617 and zenodo 10.5281/zenodo.3595558.
Related repositories:
- Training, plotting, filtering, and auxiliary tools https://gitlab.com/Karel-van-de-Plassche/QLKNN-develop
- QuaLiKiz related tools https://gitlab.com/qualikiz-group/QuaLiKiz-pythontools
- FORTRAN QLKNN implementation with wrapper for Python and MATLAB https://gitlab.com/qualikiz-group/QLKNN-fortran
- Weights and biases of 'hyperrectangle style' QLKNN https://gitlab.com/qualikiz-group/qlknn-hyper
Notes
Files
README.md
Files
(32.1 GB)
Name | Size | Download all |
---|---|---|
md5:cf46f6c855996de219e35dfdaa471fce
|
240 Bytes | Download |
md5:a4125ffb96672badf2526d51137df512
|
13.3 GB | Download |
md5:2e0cd6344e3269a6aca196f9913d6fff
|
4.6 kB | Preview Download |
md5:ad5b69e2e670f33c48b5e8242e4c0196
|
12.6 GB | Download |
md5:398bbe89a43e9563c7d30ee5ad2fee53
|
6.2 GB | Download |
Additional details
Related works
- Is cited by
- Journal article: 10.1063/1.5134126 (DOI)
- 10.5281/zenodo.3595558 (DOI)
- https://arxiv.org/abs/1911.05617 (URL)
Funding
References
- J. Citrin et al. (2015). Real-time capable first principle based modelling of tokamak turbulent transport (doi.org/10.1088/0029-5515/55/9/092001)
- 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 (doi.org/10.1088/0029-5515/55/9/092001)