Fast Dynamic 1D Simulation of Divertor Plasmas with Neural PDE Surrogates

• URL: http://arxiv.org/abs/2305.18944v3
• Date: Fri, 29 Sep 2023 12:44:24 GMT
• Title: Fast Dynamic 1D Simulation of Divertor Plasmas with Neural PDE Surrogates
• Authors: Yoeri Poels, Gijs Derks, Egbert Westerhof, Koen Minartz, Sven Wiesen, Vlado Menkovski
• Abstract summary: Managing divertor plasmas is crucial for operating reactor scale tokamak devices due to heat and particle flux constraints on the divertor target. We address this lack of fast simulators using neural PDE surrogates, data-driven neural network-based surrogate models trained using solutions generated with a classical numerical method. We simulate a realistic TCV divertor plasma with dynamics induced by upstream density ramps and provide an exploratory outlook towards fast transients.
• Score: 3.6443770850509423
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Managing divertor plasmas is crucial for operating reactor scale tokamak devices due to heat and particle flux constraints on the divertor target. Simulation is an important tool to understand and control these plasmas, however, for real-time applications or exhaustive parameter scans only simple approximations are currently fast enough. We address this lack of fast simulators using neural PDE surrogates, data-driven neural network-based surrogate models trained using solutions generated with a classical numerical method. The surrogate approximates a time-stepping operator that evolves the full spatial solution of a reference physics-based model over time. We use DIV1D, a 1D dynamic model of the divertor plasma, as reference model to generate data. DIV1D's domain covers a 1D heat flux tube from the X-point (upstream) to the target. We simulate a realistic TCV divertor plasma with dynamics induced by upstream density ramps and provide an exploratory outlook towards fast transients. State-of-the-art neural PDE surrogates are evaluated in a common framework and extended for properties of the DIV1D data. We evaluate (1) the speed-accuracy trade-off; (2) recreating non-linear behavior; (3) data efficiency; and (4) parameter inter- and extrapolation. Once trained, neural PDE surrogates can faithfully approximate DIV1D's divertor plasma dynamics at sub real-time computation speeds: In the proposed configuration, 2ms of plasma dynamics can be computed in $\approx$0.63ms of wall-clock time, several orders of magnitude faster than DIV1D.

Related papers

• Plasma Surrogate Modelling using Fourier Neural Operators [57.52074029826172]
  Predicting plasma evolution within a Tokamak reactor is crucial to realizing the goal of sustainable fusion. We demonstrate accurate predictions of evolution plasma using deep learning-based surrogate modelling tools, viz., Neural Operators (FNO) We show that FNO has a speedup of six orders of magnitude over traditional solvers in predicting the plasma dynamics simulated from magnetohydrodynamic models. FNOs can also predict plasma evolution on real-world experimental data observed by the cameras positioned within the MAST Tokamak.
  arXiv  Detail & Related papers  (2023-11-10T10:05:00Z)
• Hybridizing Physics and Neural ODEs for Predicting Plasma Inductance Dynamics in Tokamak Fusion Reactors [0.0]
  We train both physics-based and neural network models on data from the Alcator C-Mod fusion reactor. We find that a model that combines physics-based equations with a neural ODE performs better than both existing physics-motivated ODEs and a pure neural ODE model.
  arXiv  Detail & Related papers  (2023-10-30T23:25:54Z)
• Learning Controllable Adaptive Simulation for Multi-resolution Physics [86.8993558124143]
  We introduce Learning controllable Adaptive simulation for Multi-resolution Physics (LAMP) as the first full deep learning-based surrogate model. LAMP consists of a Graph Neural Network (GNN) for learning the forward evolution, and a GNN-based actor-critic for learning the policy of spatial refinement and coarsening. We demonstrate that our LAMP outperforms state-of-the-art deep learning surrogate models, and can adaptively trade-off computation to improve long-term prediction error.
  arXiv  Detail & Related papers  (2023-05-01T23:20:27Z)
• Learning to Accelerate Partial Differential Equations via Latent Global Evolution [64.72624347511498]
  Latent Evolution of PDEs (LE-PDE) is a simple, fast and scalable method to accelerate the simulation and inverse optimization of PDEs. We introduce new learning objectives to effectively learn such latent dynamics to ensure long-term stability. We demonstrate up to 128x reduction in the dimensions to update, and up to 15x improvement in speed, while achieving competitive accuracy.
  arXiv  Detail & Related papers  (2022-06-15T17:31:24Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Deep Learning Architecture Based Approach For 2D-Simulation of Microwave Plasma Interaction [5.467400475482668]
  This paper presents a convolutional neural network (CNN)-based deep learning model, inspired from UNet with series of encoder and decoder units with skip connections, for the simulation of microwave-plasma interaction. The training data associated with microwave-plasma interaction has been generated using 2D-FDTD (Finite Difference Time Domain) based simulations. The trained deep learning model is then used to reproduce the scattered electric field values for the 1GHz incident microwave on different plasma profiles with error margin of less than 2%.
  arXiv  Detail & Related papers  (2022-06-02T19:37:41Z)
• Dynamic Mode Decomposition in Adaptive Mesh Refinement and Coarsening Simulations [58.720142291102135]
  Dynamic Mode Decomposition (DMD) is a powerful data-driven method used to extract coherent schemes. This paper proposes a strategy to enable DMD to extract from observations with different mesh topologies and dimensions.
  arXiv  Detail & Related papers  (2021-04-28T22:14:25Z)
• Machine learning for rapid discovery of laminar flow channel wall modifications that enhance heat transfer [56.34005280792013]
  We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels and machine learning models predicting drag coefficient and Stanton number. We show that convolutional neural networks (CNN) can accurately predict the target properties at a fraction of the time of numerical simulations.
  arXiv  Detail & Related papers  (2021-01-19T16:14:02Z)
• A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder [0.19116784879310023]
  nonlinear manifold ROM (NM-ROM) can better approximate high-fidelity model solutions with a smaller latent space dimension than the LS-ROMs. Results show that neural networks can learn a more efficient latent space representation on advection-dominated data.
  arXiv  Detail & Related papers  (2020-09-25T00:48:19Z)
• Learning Compact Physics-Aware Delayed Photocurrent Models Using Dynamic Mode Decomposition [1.933681537640272]
  Radiation-induced photocurrent in semiconductor devices can be simulated using complex physics-based models. It is computationally infeasible to evaluate detailed models for multiple individual circuit elements. We show a procedure for learning compact delayed photocurrent models that are efficient enough to implement in large-scale circuit simulations.
  arXiv  Detail & Related papers  (2020-08-27T18:21:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.