Machine-learning-based models in particle-in-cell codes for advanced physics extensions

被引:6
作者
Badiali, Chiara [1 ]
Bilbao, Pablo J. J. [1 ]
Cruz, Fabio [1 ,2 ]
Silva, Luis O. [1 ]
机构
[1] Univ Lisbon, GoLP Inst Plasmas & Fusao Nucl, Inst Super Tecn, P-1049001 Lisbon, Portugal
[2] Induct Res Labs, Rua Prata 80, P-1100420 Lisbon, Portugal
基金
欧洲研究理事会; 欧盟地平线“2020”;
关键词
plasma simulation; SCATTERING; COLLISIONS;
D O I
10.1017/S0022377822001180
中图分类号
O35 [流体力学]; O53 [等离子体物理学];
学科分类号
070204 ; 080103 ; 080704 ;
摘要
In this paper we propose a methodology for the efficient implementation of machine learning (ML)-based methods in particle-in-cell (PIC) codes, with a focus on Monte Carlo or statistical extensions to the PIC algorithm. The presented approach allows for neural networks to be developed in a Python environment, where advanced ML tools are readily available to proficiently train and test them. Those models are then efficiently deployed within highly scalable and fully parallelized PIC simulations during runtime. We demonstrate this methodology with a proof-of-concept implementation within the PIC code OSIRIS, where a fully connected neural network is used to replace a section of a Compton scattering module. We demonstrate that the ML-based method reproduces the results obtained with the conventional method and achieves better computational performance. These results offer a promising avenue for future applications of ML-based methods in PIC, particularly for physics extensions where a ML-based approach can provide a higher performance increase.
引用
收藏
页数:12
相关论文
共 36 条
[1]   A Deep Learning-Based Particle-in-Cell Method for Plasma Simulations [J].
Aguilar, Xavier ;
Markidis, Stefano .
2021 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING (CLUSTER 2021), 2021, :692-697
[2]   Contemporary particle-in-cell approach to laser-plasma modelling [J].
Arber, T. D. ;
Bennett, K. ;
Brady, C. S. ;
Lawrence-Douglas, A. ;
Ramsay, M. G. ;
Sircombe, N. J. ;
Gillies, P. ;
Evans, R. G. ;
Schmitz, H. ;
Bell, A. R. ;
Ridgers, C. P. .
PLASMA PHYSICS AND CONTROLLED FUSION, 2015, 57 (11)
[3]   Generating ultradense pair beams using 400 GeV/c protons [J].
Arrowsmith, C. D. ;
Shukla, N. ;
Charitonidis, N. ;
Boni, R. ;
Chen, H. ;
Davenne, T. ;
Dyson, A. ;
Froula, D. H. ;
Gudmundsson, J. T. ;
Huffman, B. T. ;
Kadi, Y. ;
Reville, B. ;
Richardson, S. ;
Sarkar, S. ;
Shaw, J. L. ;
Silva, L. O. ;
Simon, P. ;
Trines, R. M. G. M. ;
Bingham, R. ;
Gregori, G. .
PHYSICAL REVIEW RESEARCH, 2021, 3 (02)
[4]   Generalized, Energy-conserving Numerical Simulations of Particles in General Relativity. I. Time-like and Null Geodesics [J].
Bacchini, F. ;
Ripperda, B. ;
Chen, A. Y. ;
Sironi, L. .
ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES, 2018, 237 (01)
[5]  
BELLO F.A.D., 2021, COMPUT SOFTW BIG SCI, V5, P1
[6]  
Bird G.A., 1989, Rarefied Gas Dynamics: Theoretical and Computational Techniques, V117, P211, DOI DOI 10.2514/5.9781600865923.0211.0226
[7]   BREMSSTRAHLUNG, SYNCHROTRON RADIATION, AND COMPTON SCATTERING OF HIGH-ENERGY ELECTRONS TRAVERSING DILUTE GASES [J].
BLUMENTHAL, GR ;
GOULD, RJ .
REVIEWS OF MODERN PHYSICS, 1970, 42 (02) :237-+
[8]  
Buneman O., 1993, TRISTAN COMPUTER SPA
[9]  
Chollet F., 2018, Deep learning with R
[10]  
Chollet F., 2017, Deep Learning with Python