Data-Driven Solutions and Parameters Discovery of the Chiral Nonlinear Schrödinger Equation via Deep Learning

The chiral nonlinear Schrödinger equation (CNLSE) serves as a simplified model for characterizing edge states in the fractional quantum Hall effect. In this paper, we leverage the generalization and parameter inversion capabilities of physics-informed neural networks (PINNs) to investigate both forw...

Full description

Saved in:
Bibliographic Details
Main Authors: Zekang Wu, Lijun Zhang, Xuwen Huo, Chaudry Masood Khalique
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/15/2344
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849405418138238976
author Zekang Wu
Lijun Zhang
Xuwen Huo
Chaudry Masood Khalique
author_facet Zekang Wu
Lijun Zhang
Xuwen Huo
Chaudry Masood Khalique
author_sort Zekang Wu
collection DOAJ
description The chiral nonlinear Schrödinger equation (CNLSE) serves as a simplified model for characterizing edge states in the fractional quantum Hall effect. In this paper, we leverage the generalization and parameter inversion capabilities of physics-informed neural networks (PINNs) to investigate both forward and inverse problems of 1D and 2D CNLSEs. Specifically, a hybrid optimization strategy incorporating exponential learning rate decay is proposed to reconstruct data-driven solutions, including bright soliton for the 1D case and bright, dark soliton as well as periodic solutions for the 2D case. Moreover, we conduct a comprehensive discussion on varying parameter configurations derived from the equations and their corresponding solutions to evaluate the adaptability of the PINNs framework. The effects of residual points, network architectures, and weight settings are additionally examined. For the inverse problems, the coefficients of 1D and 2D CNLSEs are successfully identified using soliton solution data, and several factors that can impact the robustness of the proposed model, such as noise interference, time range, and observation moment are explored as well. Numerical experiments highlight the remarkable efficacy of PINNs in solution reconstruction and coefficient identification while revealing that observational noise exerts a more pronounced influence on accuracy compared to boundary perturbations. Our research offers new insights into simulating dynamics and discovering parameters of nonlinear chiral systems with deep learning.
format Article
id doaj-art-746b8a10cb4541e992ab5739bb923697
institution Kabale University
issn 2227-7390
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-746b8a10cb4541e992ab5739bb9236972025-08-20T03:36:41ZengMDPI AGMathematics2227-73902025-07-011315234410.3390/math13152344Data-Driven Solutions and Parameters Discovery of the Chiral Nonlinear Schrödinger Equation via Deep LearningZekang Wu0Lijun Zhang1Xuwen Huo2Chaudry Masood Khalique3College of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao 266590, ChinaSchool of Science, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaCollege of Mathematics and Systems Science, Shandong University of Science and Technology, Qingdao 266590, ChinaThe chiral nonlinear Schrödinger equation (CNLSE) serves as a simplified model for characterizing edge states in the fractional quantum Hall effect. In this paper, we leverage the generalization and parameter inversion capabilities of physics-informed neural networks (PINNs) to investigate both forward and inverse problems of 1D and 2D CNLSEs. Specifically, a hybrid optimization strategy incorporating exponential learning rate decay is proposed to reconstruct data-driven solutions, including bright soliton for the 1D case and bright, dark soliton as well as periodic solutions for the 2D case. Moreover, we conduct a comprehensive discussion on varying parameter configurations derived from the equations and their corresponding solutions to evaluate the adaptability of the PINNs framework. The effects of residual points, network architectures, and weight settings are additionally examined. For the inverse problems, the coefficients of 1D and 2D CNLSEs are successfully identified using soliton solution data, and several factors that can impact the robustness of the proposed model, such as noise interference, time range, and observation moment are explored as well. Numerical experiments highlight the remarkable efficacy of PINNs in solution reconstruction and coefficient identification while revealing that observational noise exerts a more pronounced influence on accuracy compared to boundary perturbations. Our research offers new insights into simulating dynamics and discovering parameters of nonlinear chiral systems with deep learning.https://www.mdpi.com/2227-7390/13/15/2344physics-informed neural networkschiral nonlinear Schrödinger equationsdata-driven solutionsparameters discovery
spellingShingle Zekang Wu
Lijun Zhang
Xuwen Huo
Chaudry Masood Khalique
Data-Driven Solutions and Parameters Discovery of the Chiral Nonlinear Schrödinger Equation via Deep Learning
Mathematics
physics-informed neural networks
chiral nonlinear Schrödinger equations
data-driven solutions
parameters discovery
title Data-Driven Solutions and Parameters Discovery of the Chiral Nonlinear Schrödinger Equation via Deep Learning
title_full Data-Driven Solutions and Parameters Discovery of the Chiral Nonlinear Schrödinger Equation via Deep Learning
title_fullStr Data-Driven Solutions and Parameters Discovery of the Chiral Nonlinear Schrödinger Equation via Deep Learning
title_full_unstemmed Data-Driven Solutions and Parameters Discovery of the Chiral Nonlinear Schrödinger Equation via Deep Learning
title_short Data-Driven Solutions and Parameters Discovery of the Chiral Nonlinear Schrödinger Equation via Deep Learning
title_sort data driven solutions and parameters discovery of the chiral nonlinear schrodinger equation via deep learning
topic physics-informed neural networks
chiral nonlinear Schrödinger equations
data-driven solutions
parameters discovery
url https://www.mdpi.com/2227-7390/13/15/2344
work_keys_str_mv AT zekangwu datadrivensolutionsandparametersdiscoveryofthechiralnonlinearschrodingerequationviadeeplearning
AT lijunzhang datadrivensolutionsandparametersdiscoveryofthechiralnonlinearschrodingerequationviadeeplearning
AT xuwenhuo datadrivensolutionsandparametersdiscoveryofthechiralnonlinearschrodingerequationviadeeplearning
AT chaudrymasoodkhalique datadrivensolutionsandparametersdiscoveryofthechiralnonlinearschrodingerequationviadeeplearning