Data-driven vector soliton solutions of coupled nonlinear Schrödinger equation using a deep learning algorithm

•We explore a deep learning method for solving coupled nonlinear Schrödinger equation.•We propose an improved PINN algorithm by error measurement, multistage training and adaptive weights techniques.•The data-driven vector soliton and two-soliton solutions are derived by the proposed method. In this...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Physics letters. A Ročník 421; s. 127739
Hlavní autoři:	Mo, Yifan, Ling, Liming, Zeng, Delu
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier B.V 06.01.2022
Témata:	Coupled nonlinear Schrödinger equation Data-driven solutions Deep learning Nondegenerate vector soliton Two-soliton solutions Deep learning Two-soliton solutions Nondegenerate vector soliton Data-driven solutions Coupled nonlinear Schrödinger equation
ISSN:	0375-9601, 1873-2429
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•We explore a deep learning method for solving coupled nonlinear Schrödinger equation.•We propose an improved PINN algorithm by error measurement, multistage training and adaptive weights techniques.•The data-driven vector soliton and two-soliton solutions are derived by the proposed method. In this work, we explore a deep learning algorithm for vector solitons of the coupled nonlinear Schrödinger equation (CNLSE). Based on the original physics-informed neural networks (PINN), we propose a pre-fixed multi-stage training algorithm by combining the ideas of error measurement, multi-stage training and adaptive weights. The result of numerical simulation demonstrates that the improved algorithm not only can recover different dynamical behaviors of solitons in the coupled equation but also has better approximation ability and faster convergence rate.
ISSN:	0375-9601 1873-2429
DOI:	10.1016/j.physleta.2021.127739