Data-driven rogue waves and parameters discovery in nearly integrable \(\mathcal{PT}\)-symmetric Gross-Pitaevskii equations via PINNs deep learning

DOI10.1016/j.physd.2022.133430zbMath1496.35373WikidataQ113866764 ScholiaQ113866764MaRDI QIDQ2167994

Zhenya Yan, Ming Zhong, Shou-Fu Tian, Shibo Gong

Publication date: 1 September 2022

Published in: Physica D (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.physd.2022.133430

zbMATH Keywords

generalized Gross-Pitaevskii equation; complex \(\mathcal{PT}\)-symmetric potentials; data-driven rogue waves and parameters discovery; physics-informed deep neural networks

Mathematics Subject Classification ID

68T07: Artificial neural networks and deep learning

35Q35: PDEs in connection with fluid mechanics

76B15: Water waves, gravity waves; dispersion and scattering, nonlinear interaction

35R30: Inverse problems for PDEs

35Q55: NLS equations (nonlinear Schrödinger equations)

Uses Software

• Julia
• TensorFlow
• PyTorch
• ImageNet
• Tensor2Tensor
• DeepXDE
• AlexNet
• FPINNs
• PPINN
• Wasserstein GAN
• DeepONet
• PINNsNTK
• hp-VPINNs