Ziwei Huang, Liang An, Yang Ye, Xiaoyan Wang, Hongli Cao, Yuchong Du, Meng Zhang
{"title":"A broadband modeling method for range-independent underwater acoustic channels using physics-informed neural networks.","authors":"Ziwei Huang, Liang An, Yang Ye, Xiaoyan Wang, Hongli Cao, Yuchong Du, Meng Zhang","doi":"10.1121/10.0034458","DOIUrl":null,"url":null,"abstract":"<p><p>Accurate broadband modeling of underwater acoustic channels is vital for underwater acoustic detection, localization, and communication. Conventional modeling methodologies, based on methods such as the finite element method, finite difference method, and boundary element method, generally facilitate computation for only a single frequency at a time. However, in broadband modeling, this characteristic presents limitations, requiring multiple computations across frequencies, thereby leading to significant time challenges. To solve this problem, we propose a rapid broadband modeling approach using physics-informed neural networks. By integrating the modal equation of normal modes as a regularization term within the neural network's loss function, the method can achieve rapid broadband modeling of underwater acoustic channel with a sparse set of frequency sampling points. Operating in range-independent underwater environments with a liquid semi-infinite seabed, the method proficiently predicts the channel response across the frequency band from 100 to 300 Hz. Compared to the results obtained from KRAKEN, our method improves computational speed by a factor of 25 at a propagation distance of 20 km, while maintaining a mean absolute error of 0.15 dB for the acoustic channel response.</p>","PeriodicalId":17168,"journal":{"name":"Journal of the Acoustical Society of America","volume":"156 5","pages":"3523-3533"},"PeriodicalIF":2.1000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Acoustical Society of America","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1121/10.0034458","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ACOUSTICS","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate broadband modeling of underwater acoustic channels is vital for underwater acoustic detection, localization, and communication. Conventional modeling methodologies, based on methods such as the finite element method, finite difference method, and boundary element method, generally facilitate computation for only a single frequency at a time. However, in broadband modeling, this characteristic presents limitations, requiring multiple computations across frequencies, thereby leading to significant time challenges. To solve this problem, we propose a rapid broadband modeling approach using physics-informed neural networks. By integrating the modal equation of normal modes as a regularization term within the neural network's loss function, the method can achieve rapid broadband modeling of underwater acoustic channel with a sparse set of frequency sampling points. Operating in range-independent underwater environments with a liquid semi-infinite seabed, the method proficiently predicts the channel response across the frequency band from 100 to 300 Hz. Compared to the results obtained from KRAKEN, our method improves computational speed by a factor of 25 at a propagation distance of 20 km, while maintaining a mean absolute error of 0.15 dB for the acoustic channel response.
期刊介绍:
Since 1929 The Journal of the Acoustical Society of America has been the leading source of theoretical and experimental research results in the broad interdisciplinary study of sound. Subject coverage includes: linear and nonlinear acoustics; aeroacoustics, underwater sound and acoustical oceanography; ultrasonics and quantum acoustics; architectural and structural acoustics and vibration; speech, music and noise; psychology and physiology of hearing; engineering acoustics, transduction; bioacoustics, animal bioacoustics.