Data-driven localized waves and parameter discovery in the massive Thirring model via extended physics-informed neural networks with interface zones

被引:7
|
作者
Chen, Junchao [1 ]
Song, Jin [2 ,3 ]
Zhou, Zijian [2 ,3 ]
Yan, Zhenya [2 ,3 ]
机构
[1] Lishui Univ, Dept Math, Lishui 323000, Peoples R China
[2] Chinese Acad Sci, Key Lab Math Mechanizat, Acad Math & Syst Sci, Beijing 100190, Peoples R China
[3] Univ Chinese Acad Sci, Sch Math Sci, Beijing 100049, Peoples R China
关键词
Deep learning; XPINNs algorithm with interface zones; Massive Thirring model; Data-driven localized waves; Parameter discovery; DEEP LEARNING FRAMEWORK; SOLITON-SOLUTIONS; BRAGG SOLITONS; EQUATION; INTEGRABILITY; XPINNS;
D O I
10.1016/j.chaos.2023.114090
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
In this paper, we study data-driven localized wave solutions and parameter discovery in the massive Thirring (MT) model via the deep learning in the framework of physics-informed neural networks (PINNs) algorithm. Abundant data-driven solutions including soliton of bright/dark type, breather and rogue wave are simulated accurately and analyzed contrastively with relative and absolute errors. For higher-order localized wave solutions, we employ the extended PINNs (XPINNs) with domain decomposition to capture the complete pictures of dynamic behaviors such as soliton collisions, breather oscillations and rogue-wave superposition. In particular, we modify the interface line in domain decomposition of XPINNs into a small interface zone and introduce the pseudo initial, residual and gradient conditions as interface conditions linked adjacently with individual neural networks. Then this modified approach is applied successfully to various solutions ranging from bright-bright soliton, dark-dark soliton, dark-antidark soliton, general breather, Kuznetsov-Ma breather and second-order rogue wave. Experimental results show that this improved version of XPINNs reduce the complexity of computation with faster convergence rate and keep the quality of learned solutions with smoother stitching performance as well. For the inverse problems, the unknown coefficient parameters of linear and nonlinear terms in the MT model are identified accurately with and without noise by using the classical PINNs algorithm.
引用
收藏
页数:16
相关论文
共 50 条
  • [41] A physics-informed data-driven model for landslide susceptibility assessment in the Three Gorges Reservoir area
    Liu, Songlin
    Wang, Luqi
    Zhang, Wengang
    Sun, Weixin
    Fu, Jie
    Xiao, Ting
    Dai, Zhenwei
    GEOSCIENCE FRONTIERS, 2023, 14 (05)
  • [42] Data-driven guided physics-informed segmented neural network for liquid-vapor flash calculation
    Hua, Jinyu
    Du, Xin
    Yang, Feng
    Lu, Detang
    PHYSICS OF FLUIDS, 2024, 36 (10)
  • [43] Data-driven physics-informed constitutive metamodeling of complex fluids: A multifidelity neural network (MFNN) framework
    Mahmoudabadbozchelou, Mohammadamin
    Caggioni, Marco
    Shahsavari, Setareh
    Hartt, William H.
    Em Karniadakis, George
    Jamali, Safa
    JOURNAL OF RHEOLOGY, 2021, 65 (02) : 179 - 198
  • [44] Extended Physics-Informed Neural Networks for Parameter Identification of Switched Mode Power Converters With Undetermined Topological Durations
    Xiang, Yangxiao
    Lin, Hongjian
    Chung, Henry Shu-Hung
    IEEE TRANSACTIONS ON POWER ELECTRONICS, 2025, 40 (01) : 2235 - 2247
  • [45] Physics-informed data-driven discovery of constitutive models with application to strain-rate-sensitive soft materials
    Upadhyay, Kshitiz
    Fuhg, Jan N.
    Bouklas, Nikolaos
    Ramesh, K. T.
    COMPUTATIONAL MECHANICS, 2024,
  • [46] Data-driven thermal state estimation for in-orbit systems via physics-informed machine learning
    Tanaka, Hiroto
    Nagai, Hiroki
    ACTA ASTRONAUTICA, 2023, 212 : 316 - 328
  • [47] Data-Driven Ai-and Bi-Soliton of the Cylindrical Korteweg–de Vries Equation via Prior-Information Physics-Informed Neural Networks
    田十方
    李彪
    张钊
    Chinese Physics Letters, 2024, (03) : 6 - 11
  • [48] A comparative study of dimensional and non-dimensional inputs in physics-informed and data-driven neural networks for single-droplet evaporation
    Malekjani, Narjes
    Kharaghani, Abdolreza
    Tsotsas, Evangelos
    CHEMICAL ENGINEERING SCIENCE, 2025, 306
  • [49] Data-driven nonparametric identification of material behavior based on physics-informed neural network with full-field data
    Jeong, Iksu
    Cho, Maenghyo
    Chung, Hayoung
    Kim, Do-Nyun
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 418
  • [50] Data-driven solutions and parameter estimations of a family of higher-order KdV equations based on physics informed neural networks
    Chen, Jiajun
    Shi, Jianping
    He, Ao
    Fang, Hui
    SCIENTIFIC REPORTS, 2024, 14 (01):