A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean
This paper proposes a convolutional neural network (CNN) method to estimate subsurface temperature (ST) in the Pacific Ocean from a suite of satellite remote sensing measurements. These include sea surface temperature(SST), sea surface height (SSH), and sea surface salinity (SSS). We propose using t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8913542/ |
| _version_ | 1818347864798003200 |
|---|---|
| author | Mingxu Han Yuan Feng Xueli Zhao Chunjian Sun Feng Hong Chao Liu |
| author_facet | Mingxu Han Yuan Feng Xueli Zhao Chunjian Sun Feng Hong Chao Liu |
| author_sort | Mingxu Han |
| collection | DOAJ |
| description | This paper proposes a convolutional neural network (CNN) method to estimate subsurface temperature (ST) in the Pacific Ocean from a suite of satellite remote sensing measurements. These include sea surface temperature(SST), sea surface height (SSH), and sea surface salinity (SSS). We propose using the multisource sea surface parameters to establish a monthly CNN model to reconstruct the ocean subsurface temperature (ST) and use Argo data for accurate validation. The results show that the CNN can accurately estimate the ST of the Pacific Ocean by using the model. We trained the model for 12 months. The most prominent months are January, April, July, and October with average mean square error (MSE) values of 0.2659, 0.3129, 0.5318, and 0.5160, and the average coefficients of determination (R<sup>2</sup>) were 0.968, 0.971, 0.949, and 0.967, respectively. This study improves the accuracy of ST estimation and the good results based on reanalysis indicate that the model is promising to be applied to satellite observations. |
| first_indexed | 2024-12-13T17:40:56Z |
| format | Article |
| id | doaj.art-b17fafbea30b4112bf0dfa40bbf50949 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T17:40:56Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-b17fafbea30b4112bf0dfa40bbf509492022-12-21T23:36:44ZengIEEEIEEE Access2169-35362019-01-01717281617282910.1109/ACCESS.2019.29559578913542A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific OceanMingxu Han0https://orcid.org/0000-0002-4988-3997Yuan Feng1https://orcid.org/0000-0002-0721-4488Xueli Zhao2https://orcid.org/0000-0001-9336-7378Chunjian Sun3https://orcid.org/0000-0002-2083-4809Feng Hong4https://orcid.org/0000-0002-4167-6037Chao Liu5https://orcid.org/0000-0001-7363-1987College of Information Science and Engineering, Ocean University of China, Qingdao, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao, ChinaNational Marine Data Information Center, Tianjin, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao, ChinaCollege of Information Science and Engineering, Ocean University of China, Qingdao, ChinaThis paper proposes a convolutional neural network (CNN) method to estimate subsurface temperature (ST) in the Pacific Ocean from a suite of satellite remote sensing measurements. These include sea surface temperature(SST), sea surface height (SSH), and sea surface salinity (SSS). We propose using the multisource sea surface parameters to establish a monthly CNN model to reconstruct the ocean subsurface temperature (ST) and use Argo data for accurate validation. The results show that the CNN can accurately estimate the ST of the Pacific Ocean by using the model. We trained the model for 12 months. The most prominent months are January, April, July, and October with average mean square error (MSE) values of 0.2659, 0.3129, 0.5318, and 0.5160, and the average coefficients of determination (R<sup>2</sup>) were 0.968, 0.971, 0.949, and 0.967, respectively. This study improves the accuracy of ST estimation and the good results based on reanalysis indicate that the model is promising to be applied to satellite observations.https://ieeexplore.ieee.org/document/8913542/Convolutional neural networkocean datasatellite measurementssubsurface temperature |
| spellingShingle | Mingxu Han Yuan Feng Xueli Zhao Chunjian Sun Feng Hong Chao Liu A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean IEEE Access Convolutional neural network ocean data satellite measurements subsurface temperature |
| title | A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean |
| title_full | A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean |
| title_fullStr | A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean |
| title_full_unstemmed | A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean |
| title_short | A Convolutional Neural Network Using Surface Data to Predict Subsurface Temperatures in the Pacific Ocean |
| title_sort | convolutional neural network using surface data to predict subsurface temperatures in the pacific ocean |
| topic | Convolutional neural network ocean data satellite measurements subsurface temperature |
| url | https://ieeexplore.ieee.org/document/8913542/ |
| work_keys_str_mv | AT mingxuhan aconvolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT yuanfeng aconvolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT xuelizhao aconvolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT chunjiansun aconvolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT fenghong aconvolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT chaoliu aconvolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT mingxuhan convolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT yuanfeng convolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT xuelizhao convolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT chunjiansun convolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT fenghong convolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean AT chaoliu convolutionalneuralnetworkusingsurfacedatatopredictsubsurfacetemperaturesinthepacificocean |