A Deep Learning Method for Inversing 3D Temperature Fields Using Sea Surface Data in Offshore China and the Northwest Pacific Ocean

Three-dimensional ocean temperature field data with high temporal-spatial resolution bears a significant impact on ocean dynamic processes such as mesoscale eddies. In recent years, with the rapid development of remote sensing data, deep learning methods have provided new ideas for the reconstructio...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiangyu Wu, Mengqi Zhang, Qingchang Wang, Xidong Wang, Jian Chen, Yinghao Qin
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/12/12/2337
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104055919673344
author Xiangyu Wu
Mengqi Zhang
Qingchang Wang
Xidong Wang
Jian Chen
Yinghao Qin
author_facet Xiangyu Wu
Mengqi Zhang
Qingchang Wang
Xidong Wang
Jian Chen
Yinghao Qin
author_sort Xiangyu Wu
collection DOAJ
description Three-dimensional ocean temperature field data with high temporal-spatial resolution bears a significant impact on ocean dynamic processes such as mesoscale eddies. In recent years, with the rapid development of remote sensing data, deep learning methods have provided new ideas for the reconstruction of ocean information. In the present study, based on sea surface data, a deep learning model is constructed using the U-net method to reconstruct the three-dimensional temperature structure of the Northwest Pacific and offshore China. Next, the correlation between surface data and underwater temperature structure is established, achieving the construction of a three-dimensional ocean temperature field based on sea surface height and sea surface temperature. A three-dimensional temperature field for the water layers within the depth of 1700 m in the Northwest Pacific and offshore China is reconstructed, featuring a spatial resolution of 0.25°. Control experiments are conducted to explore the impact of different input variables, labels, and loss functions on the reconstruction results. This study’s results show that the reconstruction accuracy of the model is higher when the input variables are anomalies of sea surface temperature and sea surface height. The reconstruction results using the mean square error (MSE) and mean absolute error (MAE) loss functions are highly similar, indicating that these two loss functions have no significant impact on the results, and only in the upper ocean does the MSE value slightly outperform MAE. Overall, the results show a rather good spatial distribution, with relatively large errors only occurring in areas where the temperature gradient is strong. The reconstruction error remains quite stable over time. Furthermore, an analysis is conducted on the temporal-spatial characteristics of some mesoscale eddies in the inversed temperature field. It is shown that the U-net network can effectively reconstruct the temporal-spatial distribution characteristics of eddies at different times and in different regions, providing a good fit for the eddy conditions in offshore China and the Northwest Pacific. The inversed eddy features are in high agreement with the eddies in the original data.
format Article
id doaj-art-20750c3caccc4c7f9b3c83f9a8d3809d
institution Kabale University
issn 2077-1312
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-20750c3caccc4c7f9b3c83f9a8d3809d2024-12-27T14:33:38ZengMDPI AGJournal of Marine Science and Engineering2077-13122024-12-011212233710.3390/jmse12122337A Deep Learning Method for Inversing 3D Temperature Fields Using Sea Surface Data in Offshore China and the Northwest Pacific OceanXiangyu Wu0Mengqi Zhang1Qingchang Wang2Xidong Wang3Jian Chen4Yinghao Qin5National Marine Environmental Forecasting Center, Ministry of Natural Resources, Beijing 100082, ChinaKey Laboratory of Marine Hazards Forecasting, Ministry of Natural Resources, Hohai University, Nanjing 210098, ChinaSchool of Marine Science and Technology, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Marine Hazards Forecasting, Ministry of Natural Resources, Hohai University, Nanjing 210098, ChinaBeijing Institute of Applied Meteorology, Beijing 100029, ChinaNational Marine Environmental Forecasting Center, Ministry of Natural Resources, Beijing 100082, ChinaThree-dimensional ocean temperature field data with high temporal-spatial resolution bears a significant impact on ocean dynamic processes such as mesoscale eddies. In recent years, with the rapid development of remote sensing data, deep learning methods have provided new ideas for the reconstruction of ocean information. In the present study, based on sea surface data, a deep learning model is constructed using the U-net method to reconstruct the three-dimensional temperature structure of the Northwest Pacific and offshore China. Next, the correlation between surface data and underwater temperature structure is established, achieving the construction of a three-dimensional ocean temperature field based on sea surface height and sea surface temperature. A three-dimensional temperature field for the water layers within the depth of 1700 m in the Northwest Pacific and offshore China is reconstructed, featuring a spatial resolution of 0.25°. Control experiments are conducted to explore the impact of different input variables, labels, and loss functions on the reconstruction results. This study’s results show that the reconstruction accuracy of the model is higher when the input variables are anomalies of sea surface temperature and sea surface height. The reconstruction results using the mean square error (MSE) and mean absolute error (MAE) loss functions are highly similar, indicating that these two loss functions have no significant impact on the results, and only in the upper ocean does the MSE value slightly outperform MAE. Overall, the results show a rather good spatial distribution, with relatively large errors only occurring in areas where the temperature gradient is strong. The reconstruction error remains quite stable over time. Furthermore, an analysis is conducted on the temporal-spatial characteristics of some mesoscale eddies in the inversed temperature field. It is shown that the U-net network can effectively reconstruct the temporal-spatial distribution characteristics of eddies at different times and in different regions, providing a good fit for the eddy conditions in offshore China and the Northwest Pacific. The inversed eddy features are in high agreement with the eddies in the original data.https://www.mdpi.com/2077-1312/12/12/2337deep learningNorthwest Pacificoffshore Chinasea surface temperaturesea surface heightthree-dimensional ocean temperature field
spellingShingle Xiangyu Wu
Mengqi Zhang
Qingchang Wang
Xidong Wang
Jian Chen
Yinghao Qin
A Deep Learning Method for Inversing 3D Temperature Fields Using Sea Surface Data in Offshore China and the Northwest Pacific Ocean
Journal of Marine Science and Engineering
deep learning
Northwest Pacific
offshore China
sea surface temperature
sea surface height
three-dimensional ocean temperature field
title A Deep Learning Method for Inversing 3D Temperature Fields Using Sea Surface Data in Offshore China and the Northwest Pacific Ocean
title_full A Deep Learning Method for Inversing 3D Temperature Fields Using Sea Surface Data in Offshore China and the Northwest Pacific Ocean
title_fullStr A Deep Learning Method for Inversing 3D Temperature Fields Using Sea Surface Data in Offshore China and the Northwest Pacific Ocean
title_full_unstemmed A Deep Learning Method for Inversing 3D Temperature Fields Using Sea Surface Data in Offshore China and the Northwest Pacific Ocean
title_short A Deep Learning Method for Inversing 3D Temperature Fields Using Sea Surface Data in Offshore China and the Northwest Pacific Ocean
title_sort deep learning method for inversing 3d temperature fields using sea surface data in offshore china and the northwest pacific ocean
topic deep learning
Northwest Pacific
offshore China
sea surface temperature
sea surface height
three-dimensional ocean temperature field
url https://www.mdpi.com/2077-1312/12/12/2337
work_keys_str_mv AT xiangyuwu adeeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT mengqizhang adeeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT qingchangwang adeeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT xidongwang adeeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT jianchen adeeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT yinghaoqin adeeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT xiangyuwu deeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT mengqizhang deeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT qingchangwang deeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT xidongwang deeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT jianchen deeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean
AT yinghaoqin deeplearningmethodforinversing3dtemperaturefieldsusingseasurfacedatainoffshorechinaandthenorthwestpacificocean