Data-driven, multi-moment fluid modeling of Landau damping

被引：11

作者：

Cheng, Wenjie ^{[1
,2
]}

Fu, Haiyang ^{[1
,2
]}

Wang, Liang ^{[3
,4
]}

Dong, Chuanfei ^{[3
,4
]}

Jin, Yaqiu ^{[1
,2
]}

Jiang, Mingle ^{[1
,2
]}

Ma, Jiayu ^{[1
,2
]}

Qin, Yilan ^{[1
,2
]}

Liu, Kexin ^{[1
,2
]}

机构：

[1] Fudan Univ, Sch Informat Sci & Engn, Shanghai 200433, Peoples R China

[2] Fudan Univ, Key Lab Informat Sci Electromagnet Waves, MoE, Shanghai 200433, Peoples R China

[3] Princeton Univ, Dept Astrophys Sci, Princeton, NJ 08544 USA

[4] Princeton Univ, Princeton Plasma Phys Lab, Princeton, NJ 08540 USA

来源：

COMPUTER PHYSICS COMMUNICATIONS | 2023年 / 282卷

基金：

美国国家科学基金会;

关键词：

Data-driven modeling; Multi -moment fluid closure; Machine learning; Kinetic model data; Landau damping; PHYSICS;

D O I：

10.1016/j.cpc.2022.108538

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

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 effect 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 the fluid closure and reduce the computational cost of multi-scale modeling of global systems. (C) 2022 Elsevier B.V. All rights reserved.

引用

页数：9

共 32 条

[11]

Juno J., 2017, J COMPUT PHYS

[12]

Kim S., 2020, IEEE T NEURAL NETW L, V99, P1

[13]

Long ZC, 2018, Arxiv, DOI [arXiv:1710.09668, DOI 10.48550/ARXIV.1710.09668]

[14] PDE-Net 2.0: Learning PDEs from data with a numeric-symbolic hybrid deep network [J].

Long, Zichao ;

Lu, Yiping ;

Dong, Bin .

JOURNAL OF COMPUTATIONAL PHYSICS, 2019, 399

[15] Machine learning surrogate models for Landau fluid closure [J].

Ma, Chenhao ;

Zhu, Ben ;

Xu, Xue-Qiao ;

Wang, Weixing .

PHYSICS OF PLASMAS, 2020, 27 (04)

[16] Neural network representability of fully ionized plasma fluid model closures [J].

Maulik, Romit ;

Garland, Nathan A. ;

Burby, Joshua W. ;

Tang, Xian-Zhu ;

Balaprakash, Prasanna .

PHYSICS OF PLASMAS, 2020, 27 (07)

[17]

Maziar R., 2020, SCIENCE, V367, P1026

[18] An improved ten-moment closure for reconnection and instabilities [J].

Ng, Jonathan ;

Hakim, A. ;

Wang, L. ;

Bhattacharjee, A. .

PHYSICS OF PLASMAS, 2020, 27 (08)

[19]

Raissi M., 2017, Physics informed deep learning (part ii): Data-driven discovery of nonlinear partial differential equations, DOI [10.48550/arXiv.1711.10561, DOI 10.48550/ARXIV.1711.10561]

[20] Hidden physics models: Machine learning of nonlinear partial differential equations [J].

Raissi, Maziar ;

Karniadakis, George Em .

JOURNAL OF COMPUTATIONAL PHYSICS, 2018, 357 :125-141

← 1 2 3 4 →