(1+1)维Ito积分-微分方程的数据驱动局域波解和参数发现

IF 1.3 4区 物理与天体物理 Q3 PHYSICS, MULTIDISCIPLINARY
Yufan Zou, Chuanjian Wang, Mengyao Zhang, Changzhao Li, Hui Fang
{"title":"(1+1)维Ito积分-微分方程的数据驱动局域波解和参数发现","authors":"Yufan Zou,&nbsp;Chuanjian Wang,&nbsp;Mengyao Zhang,&nbsp;Changzhao Li,&nbsp;Hui Fang","doi":"10.1007/s10773-025-06034-1","DOIUrl":null,"url":null,"abstract":"<div><p>In this paper, we investigate the data-driven localized wave solutions and parameters discovery of the (1+1)-dimensional Ito integro-differential equation by using the ​Potential-Function-Transformation PINNs (PFT-PINNs) method. Firstly, through the introduction of a potential function transformation, we convert the original integro-differential equation into the differential form and simultaneously also reduce the order of the differential equation, which provide convenience in solving the (1+1)-dimensional Ito integro-differential equation by using the PINNs method. Secondly, based on the neural networks, the data-driven localized wave solutions including soliton, breather, rogue wave, fusion and fission solutions are obtained with the aid of the potential function transformation. The results show that the PFT-PINNs method possesses the good performance of PFT-PINNs method in solving the forward problem of the (1+1)-dimensional Ito integro-differential equation and can acquire more accurate localized wave solutions than the standard PINNs method. Finally the PFT-PINNs method is used to solve the inverse problem of the (1+1)-dimensional Ito integro-differential equation and the results demonstrate that the unknown coefficient parameters can be satisfactorily identified even with heavily noisy data.</p></div>","PeriodicalId":597,"journal":{"name":"International Journal of Theoretical Physics","volume":"64 6","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2025-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Data-Driven Localized Wave Solutions and Parameters Discovery of the (1+1)-dimensional Ito Integro-Differential Equation\",\"authors\":\"Yufan Zou,&nbsp;Chuanjian Wang,&nbsp;Mengyao Zhang,&nbsp;Changzhao Li,&nbsp;Hui Fang\",\"doi\":\"10.1007/s10773-025-06034-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>In this paper, we investigate the data-driven localized wave solutions and parameters discovery of the (1+1)-dimensional Ito integro-differential equation by using the ​Potential-Function-Transformation PINNs (PFT-PINNs) method. Firstly, through the introduction of a potential function transformation, we convert the original integro-differential equation into the differential form and simultaneously also reduce the order of the differential equation, which provide convenience in solving the (1+1)-dimensional Ito integro-differential equation by using the PINNs method. Secondly, based on the neural networks, the data-driven localized wave solutions including soliton, breather, rogue wave, fusion and fission solutions are obtained with the aid of the potential function transformation. The results show that the PFT-PINNs method possesses the good performance of PFT-PINNs method in solving the forward problem of the (1+1)-dimensional Ito integro-differential equation and can acquire more accurate localized wave solutions than the standard PINNs method. Finally the PFT-PINNs method is used to solve the inverse problem of the (1+1)-dimensional Ito integro-differential equation and the results demonstrate that the unknown coefficient parameters can be satisfactorily identified even with heavily noisy data.</p></div>\",\"PeriodicalId\":597,\"journal\":{\"name\":\"International Journal of Theoretical Physics\",\"volume\":\"64 6\",\"pages\":\"\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2025-05-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Theoretical Physics\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s10773-025-06034-1\",\"RegionNum\":4,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"PHYSICS, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Theoretical Physics","FirstCategoryId":"101","ListUrlMain":"https://link.springer.com/article/10.1007/s10773-025-06034-1","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PHYSICS, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

本文利用势函数变换PINNs (PFT-PINNs)方法研究了(1+1)维Ito积分微分方程的数据驱动局域波解和参数发现。首先,通过引入势函数变换,将原积分-微分方程转化为微分形式,同时对微分方程进行降阶,为利用PINNs方法求解(1+1)维伊藤积分-微分方程提供了方便。其次,在神经网络的基础上,借助势函数变换,得到了数据驱动的局部波解,包括孤子解、呼吸波解、异常波解、聚变解和裂变解;结果表明,PFT-PINNs方法在求解(1+1)维Ito积分-微分方程正演问题方面具有PFT-PINNs方法的良好性能,并且可以获得比标准PINNs方法更精确的局域波解。最后,利用PFT-PINNs方法求解了(1+1)维Ito积分微分方程的反问题,结果表明,即使在重噪声数据下,未知系数参数也能得到满意的识别。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Data-Driven Localized Wave Solutions and Parameters Discovery of the (1+1)-dimensional Ito Integro-Differential Equation

In this paper, we investigate the data-driven localized wave solutions and parameters discovery of the (1+1)-dimensional Ito integro-differential equation by using the ​Potential-Function-Transformation PINNs (PFT-PINNs) method. Firstly, through the introduction of a potential function transformation, we convert the original integro-differential equation into the differential form and simultaneously also reduce the order of the differential equation, which provide convenience in solving the (1+1)-dimensional Ito integro-differential equation by using the PINNs method. Secondly, based on the neural networks, the data-driven localized wave solutions including soliton, breather, rogue wave, fusion and fission solutions are obtained with the aid of the potential function transformation. The results show that the PFT-PINNs method possesses the good performance of PFT-PINNs method in solving the forward problem of the (1+1)-dimensional Ito integro-differential equation and can acquire more accurate localized wave solutions than the standard PINNs method. Finally the PFT-PINNs method is used to solve the inverse problem of the (1+1)-dimensional Ito integro-differential equation and the results demonstrate that the unknown coefficient parameters can be satisfactorily identified even with heavily noisy data.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
2.50
自引率
21.40%
发文量
258
审稿时长
3.3 months
期刊介绍: International Journal of Theoretical Physics publishes original research and reviews in theoretical physics and neighboring fields. Dedicated to the unification of the latest physics research, this journal seeks to map the direction of future research by original work in traditional physics like general relativity, quantum theory with relativistic quantum field theory,as used in particle physics, and by fresh inquiry into quantum measurement theory, and other similarly fundamental areas, e.g. quantum geometry and quantum logic, etc.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信