Salvato in:
Dettagli Bibliografici
Autori principali: Citrin, Jonathan, Goodfellow, Ian, Raju, Akhil, Chen, Jeremy, Degrave, Jonas, Donner, Craig, Felici, Federico, Hamel, Philippe, Huber, Andrea, Nikulin, Dmitry, Pfau, David, Tracey, Brendan, Riedmiller, Martin, Kohli, Pushmeet
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.06718
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910732109479936
author Citrin, Jonathan
Goodfellow, Ian
Raju, Akhil
Chen, Jeremy
Degrave, Jonas
Donner, Craig
Felici, Federico
Hamel, Philippe
Huber, Andrea
Nikulin, Dmitry
Pfau, David
Tracey, Brendan
Riedmiller, Martin
Kohli, Pushmeet
author_facet Citrin, Jonathan
Goodfellow, Ian
Raju, Akhil
Chen, Jeremy
Degrave, Jonas
Donner, Craig
Felici, Federico
Hamel, Philippe
Huber, Andrea
Nikulin, Dmitry
Pfau, David
Tracey, Brendan
Riedmiller, Martin
Kohli, Pushmeet
contents We present TORAX, a new, open-source, differentiable tokamak core transport simulator implemented in Python using the JAX framework. TORAX solves the coupled equations for ion heat transport, electron heat transport, particle transport, and current diffusion, incorporating modular physics-based and ML models. JAX's just-in-time compilation ensures fast runtimes, while its automatic differentiation capability enables gradient-based optimization workflows and simplifies the use of Jacobian-based PDE solvers. Coupling to ML-surrogates of physics models is greatly facilitated by JAX's intrinsic support for neural network development and inference. TORAX is verified against the established RAPTOR code, demonstrating agreement in simulated plasma profiles. TORAX provides a powerful and versatile tool for accelerating research in tokamak scenario modeling, pulse design, and control.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06718
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX
Citrin, Jonathan
Goodfellow, Ian
Raju, Akhil
Chen, Jeremy
Degrave, Jonas
Donner, Craig
Felici, Federico
Hamel, Philippe
Huber, Andrea
Nikulin, Dmitry
Pfau, David
Tracey, Brendan
Riedmiller, Martin
Kohli, Pushmeet
Plasma Physics
We present TORAX, a new, open-source, differentiable tokamak core transport simulator implemented in Python using the JAX framework. TORAX solves the coupled equations for ion heat transport, electron heat transport, particle transport, and current diffusion, incorporating modular physics-based and ML models. JAX's just-in-time compilation ensures fast runtimes, while its automatic differentiation capability enables gradient-based optimization workflows and simplifies the use of Jacobian-based PDE solvers. Coupling to ML-surrogates of physics models is greatly facilitated by JAX's intrinsic support for neural network development and inference. TORAX is verified against the established RAPTOR code, demonstrating agreement in simulated plasma profiles. TORAX provides a powerful and versatile tool for accelerating research in tokamak scenario modeling, pulse design, and control.
title TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX
topic Plasma Physics
url https://arxiv.org/abs/2406.06718