skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Self-consistent core-pedestal transport simulations with neural network accelerated models

Journal Article · · Nuclear Fusion
 [1];  [1];  [1];  [1];  [1];  [1];  [1];  [1];  [1];  [2];  [3]; ORCiD logo [4]
  1. General Atomics, San Diego, CA (United States)
  2. Politecnico di Torino, Torino (Italy)
  3. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
  4. Princeton Plasma Physics Lab. (PPPL), Princeton, NJ (United States)

Fusion whole device modeling simulations require comprehensive models that are simultaneously physically accurate, fast, robust, and predictive. In this paper we describe the development of two neural-network (NN) based models as a means to perform a snon-linear multivariate regression of theory-based models for the core turbulent transport fluxes, and the pedestal structure. Specifically, we find that a NN-based approach can be used to consistently reproduce the results of the TGLF and EPED1 theory-based models over a broad range of plasma regimes, and with a computational speedup of several orders of magnitudes. These models are then integrated into a predictive workflow that allows prediction with self-consistent core-pedestal coupling of the kinetic profiles within the last closed flux surface of the plasma. Finally, the NN paradigm is capable of breaking the speed-accuracy trade-off that is expected of traditional numerical physics models, and can provide the missing link towards self-consistent coupled core-pedestal whole device modeling simulations that are physically accurate and yet take only seconds to run.

Research Organization:
General Atomics, San Diego, CA (United States)
Sponsoring Organization:
USDOE Office of Nuclear Energy (NE)
Grant/Contract Number:
FG02-95ER54309
OSTI ID:
1374389
Journal Information:
Nuclear Fusion, Vol. 57, Issue 8; ISSN 0029-5515
Publisher:
IOP ScienceCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 58 works
Citation information provided by
Web of Science

References (41)

A theory-based transport model with comprehensive physics journal May 2007
Development and validation of a predictive model for the pedestal height journal May 2009
Tokamak profile prediction using direct gyrokinetic and neoclassical simulation journal June 2009
30 years of adaptive neural networks: perceptron, Madaline, and backpropagation journal January 1990
Integrated modeling applications for tokamak experiments with OMFIT journal July 2015
Multi-scale gyrokinetic simulations: Comparison with experiment and implications for predicting turbulence and transport journal April 2016
The first transport code simulations using the trapped gyro-Landau-fluid model journal May 2008
Predicting temperature and density profiles in tokamaks journal May 1998
A gyro-Landau-fluid transport model journal July 1997
Physics basis of Multi-Mode anomalous transport module journal March 2013
Gyro-Landau fluid equations for trapped and passing particles journal October 2005
An Eulerian gyrokinetic-Maxwell solver journal April 2003
Kinetic calculation of neoclassical transport including self-consistent electron and impurity dynamics journal July 2008
An Eulerian method for the solution of the multi-species drift-kinetic equation journal June 2009
Fully electromagnetic gyrokinetic eigenmode analysis of high-beta shaped plasmas journal November 2010
L-mode validation studies of gyrokinetic turbulence simulations via multiscale and multifield turbulence measurements on the DIII-D tokamak journal May 2011
Ion temperature profile stiffness: non-linear gyrokinetic simulations and comparison with experiment journal February 2014
Gyrokinetic studies of core turbulence features in ASDEX Upgrade H-mode plasmas journal April 2015
Nonlinear gyrokinetic simulations of the I-mode high confinement regime and comparisons with experimenta) journal May 2015
Noncircular, finite aspect ratio, local equilibrium model journal April 1998
Real-time capable first principle based modelling of tokamak turbulent transport journal July 2015
Validation studies of gyrofluid and gyrokinetic predictions of transport and turbulence stiffness using the DIII-D tokamak journal July 2013
Stable numeric scheme for diffusion equation with a stiff transport journal October 2008
Transport properties of H-mode plasmas with dominant electron heating in comparison to dominant ion heating at ASDEX Upgrade journal February 2015
A first-principles predictive model of the pedestal height and width: development, testing and ITER optimization with the EPED model journal August 2011
The EPED pedestal model and edge localized mode-suppressed regimes: Studies of quiescent H-mode and development of a model for edge localized mode suppression via resonant magnetic perturbations journal May 2012
Integrated fusion simulation with self-consistent core-pedestal coupling journal April 2016
Variational moment solutions to the Grad–Shafranov equation journal January 1981
Edge localized modes and the pedestal: A model based on coupled peeling–ballooning modes journal May 2002
Numerical studies of edge localized instabilities in tokamaks journal April 2002
Stability and dynamics of the edge pedestal in the low collisionality regime: physics mechanisms for steady-state ELM-free operation journal August 2007
Exploration of the Super H-mode regime on DIII-D and potential advantages for burning plasma devices journal March 2016
The Design and Implementation of the SWIM Integrated Plasma Simulator
  • Elwasif, Wael R.; Bernholdt, David E.; Shet, Aniruddha G.
  • 2010 18th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP), 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing https://doi.org/10.1109/PDP.2010.63
conference February 2010
Multi-level concurrency in a framework for integrated loosely coupled plasma simulations conference December 2011
Parameter Sweep and Optimization of Loosely Coupled Simulations Using the DAKOTA Toolkit conference December 2012
Chapter 1: Overview and summary journal December 1999
ELMs and constraints on the H-mode pedestal: peeling–ballooning stability calculation and comparison with experiment journal January 2004
Theory of plasma transport in toroidal confinement systems journal April 1976
Effect of finite aspect ratio on the neoclassical ion thermal conductivity in the banana regime journal January 1982
Ion temperature profile stiffness: non-linear gyrokinetic simulations and comparison with experiment text January 2013
Real-time capable first principle based modelling of tokamak turbulent transport text January 2015

Cited By (16)

Integrated Tokamak modeling: When physics informs engineering and research planning journal May 2018
Predict-first experimental analysis using automated and integrated magnetohydrodynamic modeling journal May 2018
Propagation of input parameter uncertainties in transport models journal October 2018
Predict-first experiments and modeling of perturbative cold pulses in the DIII-D tokamak journal June 2019
Machine-learning assisted steady-state profile predictions using global optimization techniques journal October 2019
Fast modeling of turbulent transport in fusion plasmas using neural networks journal February 2020
Progress and challenges in understanding core transport in tokamaks in support to ITER operations journal December 2019
Real-time-capable prediction of temperature and density profiles in a tokamak using RAPTOR and a first-principle-based transport model journal July 2018
Real-time capable modeling of neutral beam injection on NSTX-U using neural networks journal March 2019
Neural-network-based semi-empirical turbulent particle transport modelling founded on gyrokinetic analyses of JT-60U plasmas journal August 2019
Deep neural network Grad–Shafranov solver constrained with measured magnetic signals journal December 2019
Investigation of a Multiple-Timescale Turbulence-Transport Coupling Method in the Presence of Random Fluctuations journal July 2018
Fast modeling of turbulent transport in fusion plasmas using neural networks text January 2019
Fast modeling of turbulent transport in fusion plasmas using neural networks text January 2019
Fast modeling of turbulent transport in fusion plasmas using neural networks text January 2019
Investigation of a Multiple-Timescale Turbulence-Transport Coupling Method in the Presence of Random Fluctuations text January 2018

Similar Records

Integrated fusion simulation with self-consistent core-pedestal coupling
Journal Article · Wed Apr 20 00:00:00 EDT 2016 · Physics of Plasmas · OSTI ID:1374389

Core-Pedestal Plasma Configurations in Advanced Tokamaks
Journal Article · Mon Jan 30 00:00:00 EST 2023 · Fusion Science and Technology · OSTI ID:1374389

Elevating zero dimensional global scaling predictions to self-consistent theory-based simulations
Journal Article · Mon Jul 31 00:00:00 EDT 2023 · Physics of Plasmas · OSTI ID:1374389