Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement
Warm current has a strong impact on the melting of sea ice, so clarifying the current features plays a very important role in the Arctic sea ice coverage forecasting study field. Currently, Arctic acoustic tomography is the only feasible method for the large-range current measurement under the Arcti...
Published in: | Journal of Marine Science and Engineering |
---|---|
Main Authors: | , , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/jmse9070755 |
id |
ftmdpi:oai:mdpi.com:/2077-1312/9/7/755/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2077-1312/9/7/755/ 2023-08-20T04:03:22+02:00 Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement Kangkang Jin Jian Xu Zichen Wang Can Lu Long Fan Zhongzheng Li Jiaxin Zhou agris 2021-07-08 application/pdf https://doi.org/10.3390/jmse9070755 EN eng Multidisciplinary Digital Publishing Institute Physical Oceanography https://dx.doi.org/10.3390/jmse9070755 https://creativecommons.org/licenses/by/4.0/ Journal of Marine Science and Engineering; Volume 9; Issue 7; Pages: 755 ocean acoustic tomography velocity field RLS convolutional neural network acoustic inverse problem Text 2021 ftmdpi https://doi.org/10.3390/jmse9070755 2023-08-01T02:08:32Z Warm current has a strong impact on the melting of sea ice, so clarifying the current features plays a very important role in the Arctic sea ice coverage forecasting study field. Currently, Arctic acoustic tomography is the only feasible method for the large-range current measurement under the Arctic sea ice. Furthermore, affected by the high latitudes Coriolis force, small-scale variability greatly affects the accuracy of Arctic acoustic tomography. However, small-scale variability could not be measured by empirical parameters and resolved by Regularized Least Squares (RLS) in the inverse problem of Arctic acoustic tomography. In this paper, the convolutional neural network (CNN) is proposed to enhance the prediction accuracy in the Arctic, and especially, Gaussian noise is added to reflect the disturbance of the Arctic environment. First, we use the finite element method to build the background ocean model. Then, the deep learning CNN method constructs the non-linear mapping relationship between the acoustic data and the corresponding flow velocity. Finally, the simulation result shows that the deep learning convolutional neural network method being applied to Arctic acoustic tomography could achieve 45.87% accurate improvement than the common RLS method in the current inversion. Text Arctic Sea ice MDPI Open Access Publishing Arctic Journal of Marine Science and Engineering 9 7 755 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
ocean acoustic tomography velocity field RLS convolutional neural network acoustic inverse problem |
spellingShingle |
ocean acoustic tomography velocity field RLS convolutional neural network acoustic inverse problem Kangkang Jin Jian Xu Zichen Wang Can Lu Long Fan Zhongzheng Li Jiaxin Zhou Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement |
topic_facet |
ocean acoustic tomography velocity field RLS convolutional neural network acoustic inverse problem |
description |
Warm current has a strong impact on the melting of sea ice, so clarifying the current features plays a very important role in the Arctic sea ice coverage forecasting study field. Currently, Arctic acoustic tomography is the only feasible method for the large-range current measurement under the Arctic sea ice. Furthermore, affected by the high latitudes Coriolis force, small-scale variability greatly affects the accuracy of Arctic acoustic tomography. However, small-scale variability could not be measured by empirical parameters and resolved by Regularized Least Squares (RLS) in the inverse problem of Arctic acoustic tomography. In this paper, the convolutional neural network (CNN) is proposed to enhance the prediction accuracy in the Arctic, and especially, Gaussian noise is added to reflect the disturbance of the Arctic environment. First, we use the finite element method to build the background ocean model. Then, the deep learning CNN method constructs the non-linear mapping relationship between the acoustic data and the corresponding flow velocity. Finally, the simulation result shows that the deep learning convolutional neural network method being applied to Arctic acoustic tomography could achieve 45.87% accurate improvement than the common RLS method in the current inversion. |
format |
Text |
author |
Kangkang Jin Jian Xu Zichen Wang Can Lu Long Fan Zhongzheng Li Jiaxin Zhou |
author_facet |
Kangkang Jin Jian Xu Zichen Wang Can Lu Long Fan Zhongzheng Li Jiaxin Zhou |
author_sort |
Kangkang Jin |
title |
Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement |
title_short |
Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement |
title_full |
Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement |
title_fullStr |
Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement |
title_full_unstemmed |
Deep Learning Convolutional Neural Network Applying for the Arctic Acoustic Tomography Current Inversion Accuracy Improvement |
title_sort |
deep learning convolutional neural network applying for the arctic acoustic tomography current inversion accuracy improvement |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/jmse9070755 |
op_coverage |
agris |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_source |
Journal of Marine Science and Engineering; Volume 9; Issue 7; Pages: 755 |
op_relation |
Physical Oceanography https://dx.doi.org/10.3390/jmse9070755 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/jmse9070755 |
container_title |
Journal of Marine Science and Engineering |
container_volume |
9 |
container_issue |
7 |
container_start_page |
755 |
_version_ |
1774713741117489152 |