RECORD
Data-driven, multi-moment fluid modeling of Landau damping
Plasma Physics · Submitted 10 Sep 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Based on the learned fluid closure, the data-driven, multi-moment fluid modeling can well reproduce all the physical quantities derived from the fully kinetic model.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Deriving governing equations of complex physical systems based on first principles can be quite challenging when there are certain unknown terms and hidden physical mechanisms in the systems. In this work, we apply a deep learning architecture to learn fluid partial differential equations (PDEs) of a plasma system based on the data acquired from a fully kinetic model. The learned multi-moment fluid PDEs are demonstrated to incorporate kinetic effects such as Landau damping. Based on the learned fluid closure, the data-driven, multi-moment fluid modeling can well reproduce all the physical quantities derived from the fully kinetic model. The calculated damping rate of Landau damping is consistent with both the fully kinetic simulation and the linear theory. The data-driven fluid modeling of PDEs for complex physical systems may be applied to improve fluid closure and reduce the computational cost of multi-scale modeling of global systems.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Deriving governing equations of complex physical systems based on first principles can be quite challenging when there are certain unknown terms and hidden physical mechanisms in the systems. | background 0.96 | 0.05 | 0.02 | asserted 0.90 |
| s1 | In this work, we apply a deep learning architecture to learn fluid partial differential equations (PDEs) of a plasma system based on the data acquired from a fully kinetic model. | method 0.70 | 0.96 | 0.07 | asserted 1.00 |
| s2 | The learned multi-moment fluid PDEs are demonstrated to incorporate kinetic effects such as Landau damping. | result 0.97 | 0.93 | 0.28 | asserted 1.00 |
| s3 | Based on the learned fluid closure, the data-driven, multi-moment fluid modeling can well reproduce all the physical quantities derived from the fully kinetic model. | result 1.00 | 0.94 | 0.46 | asserted 0.99 |
| s4 | The calculated damping rate of Landau damping is consistent with both the fully kinetic simulation and the linear theory. | result 1.00 | 0.93 | 0.21 | asserted 0.50 |
| s5 | The data-driven fluid modeling of PDEs for complex physical systems may be applied to improve fluid closure and reduce the computational cost of multi-scale modeling of global systems. | future work 0.62 | 0.14 | 0.25 | hedged possibility 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Deriving governing equations of complex physical systems based on first principles can be quite challenging when there are certain unknown terms and hidden physical mechanisms in the systems. In this work, we apply a deep learning architecture to learn fluid partial differential equations (PDEs) of a plasma system based on the data acquired from a fully kinetic model. The learned multi-moment fluid PDEs are demonstrated to incorporate kinetic effects such as Landau damping. Based on the learned fluid closure, the data-driven, multi-moment fluid modeling can well reproduce all the physical quantities derived from the fully kinetic model. The calculated damping rate of Landau damping is consistent with both the fully kinetic simulation and the linear theory. The data-driven fluid modeling of PDEs for complex physical systems may be applied to improve fluid closure and reduce the computational cost of multi-scale modeling of global systems.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites
Builds on 2 papers
-
The mPDE-Net method is extended to learn multiple-moment fluid model based on the work of Xiong et al. [ref] and the original method in Long et al. [ref] .
PDE-Net: Learning PDEs from Data · Introduction · 0.99
-
The mPDE-Net method is extended to learn multiple-moment fluid model based on the work of Xiong et al. [ref] and the original method in Long et al. [ref] .
Data-driven Discovery of Partial Differential Equations for Multiple-Physics Electromagnetic Problem · Introduction · 0.99
Uses the method or tool of 1 paper
-
The forward Euler $Δt$ block is similar to [ref] as a layer of the neural network to advance variables based on equations in time.
PDE-Net: Learning PDEs from Data · mPDE-Net · 0.93
Cites as background 2 papers
-
For electromagnetic problems, Xiong et al. [ref] and Fu et al. [ref] combined the sparse regression with the PDE-FIND to build a time network for learning Maxwell's equations and electromagnetic wave equations, respectively.
Data-driven Discovery of Partial Differential Equations for Multiple-Physics Electromagnetic Problem · Introduction · 0.87
-
Long et al. [ref] proposed the PDE-NET method, which approximates the spatial differentiation through the convolutional neural network, and can realize long-time prediction even in noisy data.
PDE-Net: Learning PDEs from Data · Introduction · 0.87
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.