12 citations · 30 across the 6 of their papers we have counts for
6 papers
Machine learning methods for modelling local, linear gyrokinetic simulations of MAST-U pedestal turbulence
Anna Niemelä, Daniel Jordan, Aaro Järvinen +8
Gyrokinetic (GK) stability strongly influences the performance of high-confinement-mode pedestals in spherical tokamak plasmas. High-fidelity gyrokinetic codes such as GENE can mod…
On learning latent dynamics of the AUG plasma state
A. Kit, A. E. Järvinen, Y. R. J. Poels +5
In this work, we demonstrate the utility of state representation learning applied to modeling the time evolution of electron density and temperature profiles at ASDEX-Upgrade (AUG)…
Deep or Not Deep: Supervised Learning Approaches to Modeling the Pedestal Density
Adam Kit, Aaro Jaervinen, Lorenzo Frassinetti +2
Pedestal is the key to conventional high performance plasma scenarios in tokamaks. However, high fidelity simulations of pedestal plasmas are extremely challenging due to the multi…
Parametric scaling of power exhaust in EU-DEMO alternative divertor simulations
A. E. Järvinen, L. Aho-Mantila, T. Lunt +3
Investigations of parametric scaling of power exhaust in the alternative divertor configuration (ADC) SOLPS-ITER simulation database of the EU-DEMO are conducted and compared to pr…
Bayesian approach for validation of runaway electron simulations
Aaro Järvinen, Tünde Fülöp, Eero Hirvijoki +3
Plasma-terminating disruptions in future fusion reactors may result in conversion of the initial current to a relativistic runaway electron beam. Validated predictive tools are req…
Developing Deep Learning Algorithms for Inferring Upstream Separatrix Density at JET
A. Kit, A. Jaervinen, S. Wiesen +2
Predictive and real-time inference capability for the upstream separatrix electron density, , is essential for design and control of core-edge integrated plasma sc…