TY - JOUR
T1 - Fast neural Poincaré maps for toroidal magnetic fields
AU - Burby, J. W.
AU - Tang, Q.
AU - Maulik, R.
N1 - Publisher Copyright:
© Not subject to copyright in the USA. Contribution of Department of Energy.
PY - 2021/2
Y1 - 2021/2
N2 - Poincaré maps for toroidal magnetic fields are routinely employed to study gross confinement properties in devices built to contain hot plasmas. In most practical applications, evaluating a Poincaré map requires numerical integration of a magnetic field line, a process that can be slow and that cannot be easily accelerated using parallel computations. We propose a novel neural network architecture, the HénonNet, and show that it is capable of accurately learning realistic Poincaré maps from observations of a conventional field-line-following algorithm. After training, such learned Poincaré maps evaluate much faster than the field-line integration method. Moreover, the HénonNet architecture exactly reproduces the primary physics constraint imposed on field-line Poincaré maps: flux preservation. This structure-preserving property is the consequence of each layer in a HénonNet being a symplectic map. We demonstrate empirically that a HénonNet can learn to mock the confinement properties of a large magnetic island by using coiled hyperbolic invariant manifolds to produce a sticky chaotic region at the desired island location. This suggests a novel approach to designing magnetic fields with good confinement properties that may be more flexible than ensuring confinement using KAM tori.
AB - Poincaré maps for toroidal magnetic fields are routinely employed to study gross confinement properties in devices built to contain hot plasmas. In most practical applications, evaluating a Poincaré map requires numerical integration of a magnetic field line, a process that can be slow and that cannot be easily accelerated using parallel computations. We propose a novel neural network architecture, the HénonNet, and show that it is capable of accurately learning realistic Poincaré maps from observations of a conventional field-line-following algorithm. After training, such learned Poincaré maps evaluate much faster than the field-line integration method. Moreover, the HénonNet architecture exactly reproduces the primary physics constraint imposed on field-line Poincaré maps: flux preservation. This structure-preserving property is the consequence of each layer in a HénonNet being a symplectic map. We demonstrate empirically that a HénonNet can learn to mock the confinement properties of a large magnetic island by using coiled hyperbolic invariant manifolds to produce a sticky chaotic region at the desired island location. This suggests a novel approach to designing magnetic fields with good confinement properties that may be more flexible than ensuring confinement using KAM tori.
UR - http://www.scopus.com/inward/record.url?scp=85098271146&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098271146&partnerID=8YFLogxK
U2 - 10.1088/1361-6587/abcbaa
DO - 10.1088/1361-6587/abcbaa
M3 - Article
AN - SCOPUS:85098271146
SN - 0741-3335
VL - 63
JO - Plasma Physics and Controlled Fusion
JF - Plasma Physics and Controlled Fusion
IS - 2
M1 - 024001
ER -