Thulasidharan K., Sinthuja N., Vishnu Priya N., Senthilvelan M
{"title":"论检验 PINN 两种变体在验证广义非线性薛定谔方程中局部波解的预测能力","authors":"Thulasidharan K., Sinthuja N., Vishnu Priya N., Senthilvelan M","doi":"arxiv-2407.07415","DOIUrl":null,"url":null,"abstract":"We introduce a novel neural network structure called Strongly Constrained\nTheory-Guided Neural Network (SCTgNN), to investigate the behaviours of the\nlocalized solutions of the generalized nonlinear Schr\\\"{o}dinger (NLS)\nequation. This equation comprises four physically significant nonlinear\nevolution equations, namely, (i) NLS equation, Hirota equation\nLakshmanan-Porsezian-Daniel (LPD) equation and fifth-order NLS equation. The\ngeneralized NLS equation demonstrates nonlinear effects up to quintic order,\nindicating rich and complex dynamics in various fields of physics. By combining\nconcepts from the Physics-Informed Neural Network (PINN) and Theory-Guided\nNeural Network (TgNN) models, SCTgNN aims to enhance our understanding of\ncomplex phenomena, particularly within nonlinear systems that defy conventional\npatterns. To begin, we employ the TgNN method to predict the behaviours of\nlocalized waves, including solitons, rogue waves, and breathers, within the\ngeneralized NLS equation. We then use SCTgNN to predict the aforementioned\nlocalized solutions and calculate the mean square errors in both SCTgNN and\nTgNN in predicting these three localized solutions. Our findings reveal that\nboth models excel in understanding complex behaviours and provide predictions\nacross a wide variety of situations.","PeriodicalId":501370,"journal":{"name":"arXiv - PHYS - Pattern Formation and Solitons","volume":"52 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"On examining the predictive capabilities of two variants of PINN in validating localised wave solutions in the generalized nonlinear Schrödinger equation\",\"authors\":\"Thulasidharan K., Sinthuja N., Vishnu Priya N., Senthilvelan M\",\"doi\":\"arxiv-2407.07415\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We introduce a novel neural network structure called Strongly Constrained\\nTheory-Guided Neural Network (SCTgNN), to investigate the behaviours of the\\nlocalized solutions of the generalized nonlinear Schr\\\\\\\"{o}dinger (NLS)\\nequation. This equation comprises four physically significant nonlinear\\nevolution equations, namely, (i) NLS equation, Hirota equation\\nLakshmanan-Porsezian-Daniel (LPD) equation and fifth-order NLS equation. The\\ngeneralized NLS equation demonstrates nonlinear effects up to quintic order,\\nindicating rich and complex dynamics in various fields of physics. By combining\\nconcepts from the Physics-Informed Neural Network (PINN) and Theory-Guided\\nNeural Network (TgNN) models, SCTgNN aims to enhance our understanding of\\ncomplex phenomena, particularly within nonlinear systems that defy conventional\\npatterns. To begin, we employ the TgNN method to predict the behaviours of\\nlocalized waves, including solitons, rogue waves, and breathers, within the\\ngeneralized NLS equation. We then use SCTgNN to predict the aforementioned\\nlocalized solutions and calculate the mean square errors in both SCTgNN and\\nTgNN in predicting these three localized solutions. Our findings reveal that\\nboth models excel in understanding complex behaviours and provide predictions\\nacross a wide variety of situations.\",\"PeriodicalId\":501370,\"journal\":{\"name\":\"arXiv - PHYS - Pattern Formation and Solitons\",\"volume\":\"52 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Pattern Formation and Solitons\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.07415\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Pattern Formation and Solitons","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.07415","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
On examining the predictive capabilities of two variants of PINN in validating localised wave solutions in the generalized nonlinear Schrödinger equation
We introduce a novel neural network structure called Strongly Constrained
Theory-Guided Neural Network (SCTgNN), to investigate the behaviours of the
localized solutions of the generalized nonlinear Schr\"{o}dinger (NLS)
equation. This equation comprises four physically significant nonlinear
evolution equations, namely, (i) NLS equation, Hirota equation
Lakshmanan-Porsezian-Daniel (LPD) equation and fifth-order NLS equation. The
generalized NLS equation demonstrates nonlinear effects up to quintic order,
indicating rich and complex dynamics in various fields of physics. By combining
concepts from the Physics-Informed Neural Network (PINN) and Theory-Guided
Neural Network (TgNN) models, SCTgNN aims to enhance our understanding of
complex phenomena, particularly within nonlinear systems that defy conventional
patterns. To begin, we employ the TgNN method to predict the behaviours of
localized waves, including solitons, rogue waves, and breathers, within the
generalized NLS equation. We then use SCTgNN to predict the aforementioned
localized solutions and calculate the mean square errors in both SCTgNN and
TgNN in predicting these three localized solutions. Our findings reveal that
both models excel in understanding complex behaviours and provide predictions
across a wide variety of situations.