Wei Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wei Hu has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Chao Dong
3 shared publicationsHongyu Wu
3 shared publicationsJinxi Fei
College of Engineering, Lishui University, Lishui, China
2 shared publicationsRuozhou Gao
College of Engineering, Lishui University, Lishui, China
2 shared publicationsYi Cheng
2 shared publications- Ding Li
Beijing National Laboratory for Condensed Matter Physics and Laboratory of Soft Matter Physics, Institute of Physics, Chinese Academy of Sciences 1 , Beijing 100190
1 shared publication
Latest Publications
- 27 October 2026
- Published by Springer Nature in The European Physical Journal B
- Vol. 99 (10) , 175
Physics-informed neural networks for computing soliton solutions of high-order Sawada–Kotera and derivative Schrödinger equations
- 27 October 2026
- Published by Springer Nature in The European Physical Journal B
- Vol. 99 (10) , 175
Physics-informed neural networks for computing soliton solutions of high-order Sawada–Kotera and derivative Schrödinger equations
- 8 June 2023
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 111 (16) , 15279-15291
Boussinesq equation solved by the physics-informed neural networks
- 8 June 2023
- Published by Springer Nature in Nonlinear Dynamics
- Vol. 111 (16) , 15279-15291
Boussinesq equation solved by the physics-informed neural networks
- Open Access
- 27 April 2023
- Published by Springer Nature in Research Square
Boussinesq equation solved by the physics informed neural networks
Physics informed neural networks(PINNs) model is utilized to achieve the first and second order rogue wave solvers of the Boussinesq equation with different initial and boundary conditions. A new generalized loss term handling the initial first order derivate is included in the simulations to guarantee the high prediction accuracies in the adaptive PINNs(APINNs) and the gradient optimized PINNs(GPINNs) models, with a new regularization parameter being considered in the later case. Learned results with high precision are fulfilled in the large domain simulations by applying more collocation points and more weight parameters in the neural network architecture. The APINNs model currently can be made use of in more situations with high prediction accuracies, while the GPINNs model is more robust in the current research where the initial condition is distributed in the localized sharp areas. Parallel computing is carried out to get the mean relative L2-norm errors efficiently with the GPINNs model due to the random choosing of the simulation points during the training iterations.
- 27 April 2023
- Published by Springer Nature in Research Square
Open AccessBoussinesq equation solved by the physics informed neural networks
Physics informed neural networks(PINNs) model is utilized to achieve the first and second order rogue wave solvers of the Boussinesq equation with different initial and boundary conditions. A new generalized loss term handling the initial first order derivate is included in the simulations to guarantee the high prediction accuracies in the adaptive PINNs(APINNs) and the gradient optimized PINNs(GPINNs) models, with a new regularization parameter being considered in the later case. Learned results with high precision are fulfilled in the large domain simulations by applying more collocation points and more weight parameters in the neural network architecture. The APINNs model currently can be made use of in more situations with high prediction accuracies, while the GPINNs model is more robust in the current research where the initial condition is distributed in the localized sharp areas. Parallel computing is carried out to get the mean relative L2-norm errors efficiently with the GPINNs model due to the random choosing of the simulation points during the training iterations.
- 10 May 2022
- Published by American Physical Society (APS) in Physical Review E
- Vol. 105 (5) , 055204
Impact of magnetic field on the parallel resistivity
The impact of magnetic field (MF) on the parallel resistivity is studied for strongly magnetized plasmas with the electron thermal gyroradius smaller than the Debye length but much larger than the Landau length . Two previous papers [P. Ghendrih et al., Phys. Lett. A 119, 354 (1987); S. D. Baalrud and T. Lafleur, Phys. Plasmas 28, 102107 (2021)] found to increase monotonically with MF. Unfortunately, both works used predetermined electron distribution functions and are thus not self-consistent. In this paper, we analyze the MF dependence of self-consistently by solving the electron magnetized kinetic equation in a Lorentz gaslike approximation. It is found decreases monotonically with MF, with in the usual Coulomb logarithm being replaced by . The underlying physics is that the electrons affected only by the collisions with impact parameters between and carry almost all the parallel current.- 10 May 2022
- Published by American Physical Society (APS) in Physical Review E
- Vol. 105 (5) , 055204
Impact of magnetic field on the parallel resistivity
The impact of magnetic field (MF) on the parallel resistivity is studied for strongly magnetized plasmas with the electron thermal gyroradius smaller than the Debye length but much larger than the Landau length . Two previous papers [P. Ghendrih et al., Phys. Lett. A 119, 354 (1987); S. D. Baalrud and T. Lafleur, Phys. Plasmas 28, 102107 (2021)] found to increase monotonically with MF. Unfortunately, both works used predetermined electron distribution functions and are thus not self-consistent. In this paper, we analyze the MF dependence of self-consistently by solving the electron magnetized kinetic equation in a Lorentz gaslike approximation. It is found decreases monotonically with MF, with in the usual Coulomb logarithm being replaced by . The underlying physics is that the electrons affected only by the collisions with impact parameters between and carry almost all the parallel current.