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

被引:5
|
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
  • [21] Data-driven machine learning approach based on physics-informed neural network for population balance model
    Ishtiaq Ali
    Advances in Continuous and Discrete Models, 2025 (1):
  • [22] A Regularized Physics-Informed Neural Network to Support Data-Driven Nonlinear Constrained Optimization
    Perez-Rosero, Diego Armando
    Alvarez-Meza, Andres Marino
    Castellanos-Dominguez, Cesar German
    COMPUTERS, 2024, 13 (07)
  • [23] A Hybrid Mechanism and Data-Driven Approach for Predicting Fatigue Life of MEMS Devices by Physics-Informed Neural Networks
    Cheng, Jiaxing
    Lu, Junxi
    Liu, Bangjian
    An, Jing
    Shen, Anping
    Fatigue and Fracture of Engineering Materials and Structures, 2025, 48 (01): : 3 - 15
  • [24] Learning scattering waves via coupling physics-informed neural networks and their convergence analysis
    Zhang, Rui
    Gao, Yu
    JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2024, 446
  • [25] The improved backward compatible physics-informed neural networks for reducing error accumulation and applications in data-driven higher-order rogue waves
    Lin, Shuning
    Chen, Yong
    CHAOS, 2024, 34 (03)
  • [26] Data-driven multi-valley dark solitons of multi-component Manakov Model using Physics-Informed Neural Networks
    Jaganathan, Meiyazhagan
    Bakthavatchalam, Tamil Arasan
    Vadivel, Murugesan
    Murugan, Selvakumar
    Balu, Gopinath
    Sankarasubbu, Malaikannan
    Ramaswamy, Radha
    Sethuraman, Vijayalakshmi
    Malomed, Boris A.
    CHAOS SOLITONS & FRACTALS, 2023, 172
  • [27] A data-driven tracking control framework using physics-informed neural networks and deep reinforcement learning for dynamical systems
    Faria, R. R.
    Capron, B. D. O.
    Secchi, A. R.
    De Souza, M. B.
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 127
  • [28] Physics-informed neural networks for parameter estimation and simulation of a two-group epidemiological model
    Ouyoussef, Kawtar Idhammou
    El Karkri, Jaafar
    Tine, Leon Matar
    Aboulaich, Rajae
    INTERNATIONAL JOURNAL OF MODELING SIMULATION AND SCIENTIFIC COMPUTING, 2024, 15 (03)
  • [29] A physics-informed GAN framework based on model-free data-driven computational mechanics
    Ciftcei, Kerem
    Hackl, Klaus
    COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 424
  • [30] Development of a physics-informed data-driven model for gaining insights into hydrological processes in irrigated watersheds
    Li, Kailong
    Huang, Guohe
    Wang, Shuo
    Razavi, Saman
    JOURNAL OF HYDROLOGY, 2022, 613