{"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, Chuanjian Wang, Mengyao Zhang, Changzhao Li, 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, Chuanjian Wang, Mengyao Zhang, Changzhao Li, 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}
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.
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.