Physics-informed Neural Network method for the Modified Nonlinear Schrödinger equation

In this paper, we apply the Physics-informed Neural Network (PINN) method to investigate some nonlinear wave solutions of the Modified Nonlinear Schrödinger (MNLS) equation, which characterizes the ultrashort pulse propagation well in optical fibers. We generate the training dataset by the Latin Hyp...

Full description

Saved in:
Bibliographic Details
Published in:Optik (Stuttgart) 2023-05, Vol.279, p.170739, Article 170739
Main Authors: Yuan, Wen-Xuan, Guo, Rui, Gao, Yi-Ning
Format: Article
Language:English
Subjects:
Neural network
The modified nonlinear Schrödinger equation
The PINN method
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c218t-6d9f2321b12daa22edddac1486ab693c1d523e6e84f08743c53fbef7330222f53
cites cdi_FETCH-LOGICAL-c218t-6d9f2321b12daa22edddac1486ab693c1d523e6e84f08743c53fbef7330222f53
container_end_page
container_issue
container_start_page 170739
container_title Optik (Stuttgart)
container_volume 279
creator Yuan, Wen-Xuan
Guo, Rui
Gao, Yi-Ning
description In this paper, we apply the Physics-informed Neural Network (PINN) method to investigate some nonlinear wave solutions of the Modified Nonlinear Schrödinger (MNLS) equation, which characterizes the ultrashort pulse propagation well in optical fibers. We generate the training dataset by the Latin Hypercube Sampling (LHS) method under Dirichlet boundary conditions. We use the Xavier initialization method to generate the parameters of the neural network, and then use the Adam algorithm to optimize them. Finally, we derive the data-driven solutions of single soliton solution, double solitons solution, single breather solution, double breather solution, first-order rogue wave and second-order rogue wave solutions for the MNLS equation. Through loss and L2 error of the experimental results, the PINN method has been verified to have prominent stability and effectiveness.
doi_str_mv 10.1016/j.ijleo.2023.170739
format article
fullrecord <record><control><sourceid>elsevier_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1016_j_ijleo_2023_170739</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0030402623002358</els_id><sourcerecordid>S0030402623002358</sourcerecordid><originalsourceid>FETCH-LOGICAL-c218t-6d9f2321b12daa22edddac1486ab693c1d523e6e84f08743c53fbef7330222f53</originalsourceid><addsrcrecordid>eNp9kEtOwzAURS0EEqWwAibeQMKznTrpgAGq-EnlIwFiaLn2M3FIY7BTUDfGBtgYKWXM6A7ePVdPh5BjBjkDJk-a3DcthpwDFzkroRTTHTJiklUZE0LukhGAgKwALvfJQUoNAJRDbUSe7-t18iZlvnMhLtHSW1xF3Q7Rf4b4SpfY18HS4Uj7GulNsN75TS10re9QR_pg6vj9ZX33gpHi-0r3PnSHZM_pNuHRX47J08X54-wqm99dXs_O5pnhrOozaaeOC84WjFutOUdrrTasqKReyKkwzE64QIlV4aAqC2Emwi3QlUIA59xNxJiI7a6JIaWITr1Fv9RxrRiojRvVqF83auNGbd0M1OmWwuG1D49RJeOxM2h9RNMrG_y__A8VDnAg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Physics-informed Neural Network method for the Modified Nonlinear Schrödinger equation</title><source>ScienceDirect Freedom Collection 2022-2024</source><creator>Yuan, Wen-Xuan ; Guo, Rui ; Gao, Yi-Ning</creator><creatorcontrib>Yuan, Wen-Xuan ; Guo, Rui ; Gao, Yi-Ning</creatorcontrib><description>In this paper, we apply the Physics-informed Neural Network (PINN) method to investigate some nonlinear wave solutions of the Modified Nonlinear Schrödinger (MNLS) equation, which characterizes the ultrashort pulse propagation well in optical fibers. We generate the training dataset by the Latin Hypercube Sampling (LHS) method under Dirichlet boundary conditions. We use the Xavier initialization method to generate the parameters of the neural network, and then use the Adam algorithm to optimize them. Finally, we derive the data-driven solutions of single soliton solution, double solitons solution, single breather solution, double breather solution, first-order rogue wave and second-order rogue wave solutions for the MNLS equation. Through loss and L2 error of the experimental results, the PINN method has been verified to have prominent stability and effectiveness.</description><identifier>ISSN: 0030-4026</identifier><identifier>EISSN: 1618-1336</identifier><identifier>DOI: 10.1016/j.ijleo.2023.170739</identifier><language>eng</language><publisher>Elsevier GmbH</publisher><subject>Neural network ; The modified nonlinear Schrödinger equation ; The PINN method</subject><ispartof>Optik (Stuttgart), 2023-05, Vol.279, p.170739, Article 170739</ispartof><rights>2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c218t-6d9f2321b12daa22edddac1486ab693c1d523e6e84f08743c53fbef7330222f53</citedby><cites>FETCH-LOGICAL-c218t-6d9f2321b12daa22edddac1486ab693c1d523e6e84f08743c53fbef7330222f53</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27903,27904</link.rule.ids></links><search><creatorcontrib>Yuan, Wen-Xuan</creatorcontrib><creatorcontrib>Guo, Rui</creatorcontrib><creatorcontrib>Gao, Yi-Ning</creatorcontrib><title>Physics-informed Neural Network method for the Modified Nonlinear Schrödinger equation</title><title>Optik (Stuttgart)</title><description>In this paper, we apply the Physics-informed Neural Network (PINN) method to investigate some nonlinear wave solutions of the Modified Nonlinear Schrödinger (MNLS) equation, which characterizes the ultrashort pulse propagation well in optical fibers. We generate the training dataset by the Latin Hypercube Sampling (LHS) method under Dirichlet boundary conditions. We use the Xavier initialization method to generate the parameters of the neural network, and then use the Adam algorithm to optimize them. Finally, we derive the data-driven solutions of single soliton solution, double solitons solution, single breather solution, double breather solution, first-order rogue wave and second-order rogue wave solutions for the MNLS equation. Through loss and L2 error of the experimental results, the PINN method has been verified to have prominent stability and effectiveness.</description><subject>Neural network</subject><subject>The modified nonlinear Schrödinger equation</subject><subject>The PINN method</subject><issn>0030-4026</issn><issn>1618-1336</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNp9kEtOwzAURS0EEqWwAibeQMKznTrpgAGq-EnlIwFiaLn2M3FIY7BTUDfGBtgYKWXM6A7ePVdPh5BjBjkDJk-a3DcthpwDFzkroRTTHTJiklUZE0LukhGAgKwALvfJQUoNAJRDbUSe7-t18iZlvnMhLtHSW1xF3Q7Rf4b4SpfY18HS4Uj7GulNsN75TS10re9QR_pg6vj9ZX33gpHi-0r3PnSHZM_pNuHRX47J08X54-wqm99dXs_O5pnhrOozaaeOC84WjFutOUdrrTasqKReyKkwzE64QIlV4aAqC2Emwi3QlUIA59xNxJiI7a6JIaWITr1Fv9RxrRiojRvVqF83auNGbd0M1OmWwuG1D49RJeOxM2h9RNMrG_y__A8VDnAg</recordid><startdate>202305</startdate><enddate>202305</enddate><creator>Yuan, Wen-Xuan</creator><creator>Guo, Rui</creator><creator>Gao, Yi-Ning</creator><general>Elsevier GmbH</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>202305</creationdate><title>Physics-informed Neural Network method for the Modified Nonlinear Schrödinger equation</title><author>Yuan, Wen-Xuan ; Guo, Rui ; Gao, Yi-Ning</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c218t-6d9f2321b12daa22edddac1486ab693c1d523e6e84f08743c53fbef7330222f53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Neural network</topic><topic>The modified nonlinear Schrödinger equation</topic><topic>The PINN method</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yuan, Wen-Xuan</creatorcontrib><creatorcontrib>Guo, Rui</creatorcontrib><creatorcontrib>Gao, Yi-Ning</creatorcontrib><collection>CrossRef</collection><jtitle>Optik (Stuttgart)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yuan, Wen-Xuan</au><au>Guo, Rui</au><au>Gao, Yi-Ning</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Physics-informed Neural Network method for the Modified Nonlinear Schrödinger equation</atitle><jtitle>Optik (Stuttgart)</jtitle><date>2023-05</date><risdate>2023</risdate><volume>279</volume><spage>170739</spage><pages>170739-</pages><artnum>170739</artnum><issn>0030-4026</issn><eissn>1618-1336</eissn><abstract>In this paper, we apply the Physics-informed Neural Network (PINN) method to investigate some nonlinear wave solutions of the Modified Nonlinear Schrödinger (MNLS) equation, which characterizes the ultrashort pulse propagation well in optical fibers. We generate the training dataset by the Latin Hypercube Sampling (LHS) method under Dirichlet boundary conditions. We use the Xavier initialization method to generate the parameters of the neural network, and then use the Adam algorithm to optimize them. Finally, we derive the data-driven solutions of single soliton solution, double solitons solution, single breather solution, double breather solution, first-order rogue wave and second-order rogue wave solutions for the MNLS equation. Through loss and L2 error of the experimental results, the PINN method has been verified to have prominent stability and effectiveness.</abstract><pub>Elsevier GmbH</pub><doi>10.1016/j.ijleo.2023.170739</doi></addata></record>
fulltext fulltext
identifier ISSN: 0030-4026
ispartof Optik (Stuttgart), 2023-05, Vol.279, p.170739, Article 170739
issn 0030-4026
1618-1336
language eng
recordid cdi_crossref_primary_10_1016_j_ijleo_2023_170739
source ScienceDirect Freedom Collection 2022-2024
subjects Neural network
The modified nonlinear Schrödinger equation
The PINN method
title Physics-informed Neural Network method for the Modified Nonlinear Schrödinger equation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T03%3A13%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Physics-informed%20Neural%20Network%20method%20for%20the%20Modified%20Nonlinear%20Schr%C3%B6dinger%20equation&rft.jtitle=Optik%20(Stuttgart)&rft.au=Yuan,%20Wen-Xuan&rft.date=2023-05&rft.volume=279&rft.spage=170739&rft.pages=170739-&rft.artnum=170739&rft.issn=0030-4026&rft.eissn=1618-1336&rft_id=info:doi/10.1016/j.ijleo.2023.170739&rft_dat=%3Celsevier_cross%3ES0030402623002358%3C/elsevier_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c218t-6d9f2321b12daa22edddac1486ab693c1d523e6e84f08743c53fbef7330222f53%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true