A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep Learning

As sound speed is a fundamental parameter of ocean acoustic characteristics, its prediction is a central focus of underwater acoustics research. Traditional numerical and statistical forecasting methods often exhibit suboptimal performance under complex conditions, whereas deep learning approaches d...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Liu, Benjun Ma, Zhiliang Qin, Cheng Wang, Chao Guo, Siyu Yang, Jixiang Zhao, Yimeng Cai, Mingzhe Li
Format: Article
Language:English
Published: MDPI AG 2024-10-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/12/11/1943
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846153280730693632
author Yu Liu
Benjun Ma
Zhiliang Qin
Cheng Wang
Chao Guo
Siyu Yang
Jixiang Zhao
Yimeng Cai
Mingzhe Li
author_facet Yu Liu
Benjun Ma
Zhiliang Qin
Cheng Wang
Chao Guo
Siyu Yang
Jixiang Zhao
Yimeng Cai
Mingzhe Li
author_sort Yu Liu
collection DOAJ
description As sound speed is a fundamental parameter of ocean acoustic characteristics, its prediction is a central focus of underwater acoustics research. Traditional numerical and statistical forecasting methods often exhibit suboptimal performance under complex conditions, whereas deep learning approaches demonstrate promising results. However, these methodologies fall short in adequately addressing multi-spatial coupling effects and spatiotemporal weighting, particularly in scenarios characterized by limited data availability. To investigate the interactions across multiple spatial scales and to achieve accurate predictions, we propose the STA-ConvLSTM framework that integrates spatiotemporal attention mechanisms with convolutional long short-term memory neural networks (ConvLSTM). The core concept involves accounting for the coupling effects among various spatial scales while extracting temporal and spatial information from the data and assigning appropriate weights to different spatiotemporal entities. Furthermore, we introduce an interpolation method for ocean temperature and salinity data based on the KNN algorithm to enhance dataset resolution. Experimental results indicate that STA-ConvLSTM provides precise predictions of sound speed. Specifically, relative to the measured data, it achieved a root mean square error (RMSE) of approximately 0.57 m/s and a mean absolute error (MAE) of about 0.29 m/s. Additionally, when compared to single-dimensional spatial analysis, incorporating multi-spatial scale considerations yielded superior predictive performance.
format Article
id doaj-art-450705aec81a412abdc35d25b54a0749
institution Kabale University
issn 2077-1312
language English
publishDate 2024-10-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-450705aec81a412abdc35d25b54a07492024-11-26T18:08:01ZengMDPI AGJournal of Marine Science and Engineering2077-13122024-10-011211194310.3390/jmse12111943A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep LearningYu Liu0Benjun Ma1Zhiliang Qin2Cheng Wang3Chao Guo4Siyu Yang5Jixiang Zhao6Yimeng Cai7Mingzhe Li8College of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaCollege of Underwater Acoustic Engineering, Harbin Engineering University, Harbin 150001, ChinaAs sound speed is a fundamental parameter of ocean acoustic characteristics, its prediction is a central focus of underwater acoustics research. Traditional numerical and statistical forecasting methods often exhibit suboptimal performance under complex conditions, whereas deep learning approaches demonstrate promising results. However, these methodologies fall short in adequately addressing multi-spatial coupling effects and spatiotemporal weighting, particularly in scenarios characterized by limited data availability. To investigate the interactions across multiple spatial scales and to achieve accurate predictions, we propose the STA-ConvLSTM framework that integrates spatiotemporal attention mechanisms with convolutional long short-term memory neural networks (ConvLSTM). The core concept involves accounting for the coupling effects among various spatial scales while extracting temporal and spatial information from the data and assigning appropriate weights to different spatiotemporal entities. Furthermore, we introduce an interpolation method for ocean temperature and salinity data based on the KNN algorithm to enhance dataset resolution. Experimental results indicate that STA-ConvLSTM provides precise predictions of sound speed. Specifically, relative to the measured data, it achieved a root mean square error (RMSE) of approximately 0.57 m/s and a mean absolute error (MAE) of about 0.29 m/s. Additionally, when compared to single-dimensional spatial analysis, incorporating multi-spatial scale considerations yielded superior predictive performance.https://www.mdpi.com/2077-1312/12/11/1943sound speed predictiondeep learninglong short-term memory neural networksspatiotemporal attention mechanisms
spellingShingle Yu Liu
Benjun Ma
Zhiliang Qin
Cheng Wang
Chao Guo
Siyu Yang
Jixiang Zhao
Yimeng Cai
Mingzhe Li
A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep Learning
Journal of Marine Science and Engineering
sound speed prediction
deep learning
long short-term memory neural networks
spatiotemporal attention mechanisms
title A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep Learning
title_full A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep Learning
title_fullStr A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep Learning
title_full_unstemmed A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep Learning
title_short A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep Learning
title_sort multi spatial scale ocean sound speed prediction method based on deep learning
topic sound speed prediction
deep learning
long short-term memory neural networks
spatiotemporal attention mechanisms
url https://www.mdpi.com/2077-1312/12/11/1943
work_keys_str_mv AT yuliu amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT benjunma amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT zhiliangqin amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT chengwang amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT chaoguo amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT siyuyang amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT jixiangzhao amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT yimengcai amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT mingzheli amultispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT yuliu multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT benjunma multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT zhiliangqin multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT chengwang multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT chaoguo multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT siyuyang multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT jixiangzhao multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT yimengcai multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning
AT mingzheli multispatialscaleoceansoundspeedpredictionmethodbasedondeeplearning