OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing Data
Retrieving information concerning the interior of the ocean using satellite remote sensing data has a major impact on studies of ocean dynamic and climate changes; however, the lack of information within the ocean limits such studies about the global ocean. In this paper, an artificial neural networ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/14/2294 |
| _version_ | 1797562204869885952 |
|---|---|
| author | Hua Su Haojie Zhang Xupu Geng Tian Qin Wenfang Lu Xiao-Hai Yan |
| author_facet | Hua Su Haojie Zhang Xupu Geng Tian Qin Wenfang Lu Xiao-Hai Yan |
| author_sort | Hua Su |
| collection | DOAJ |
| description | Retrieving information concerning the interior of the ocean using satellite remote sensing data has a major impact on studies of ocean dynamic and climate changes; however, the lack of information within the ocean limits such studies about the global ocean. In this paper, an artificial neural network, combined with satellite data and gridded Argo product, is used to estimate the ocean heat content (OHC) anomalies over four different depths down to 2000 m covering the near-global ocean, excluding the polar regions. Our method allows for the temporal hindcast of the OHC to other periods beyond the 2005–2018 training period. By applying an ensemble technique, the hindcasting uncertainty could also be estimated by using different 9-year periods for training and then calculating the standard deviation across six ensemble members. This new OHC product is called the Ocean Projection and Extension neural Network (OPEN) product. The accuracy of the product is accessed using the coefficient of determination (R<sup>2</sup>) and the relative root-mean-square error (RRMSE). The feature combinations and network architecture are optimized via a series of experiments. Overall, intercomparison with several routinely analyzed OHC products shows that the OPEN OHC has an R<sup>2</sup> larger than 0.95 and an RRMSE of <0.20 and presents notably accurate trends and variabilities. The OPEN product can therefore provide a valuable complement for studies of global climate changes. |
| first_indexed | 2024-03-10T18:25:00Z |
| format | Article |
| id | doaj.art-b8ac1c4b107a482392a2e217841eb04c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T18:25:00Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b8ac1c4b107a482392a2e217841eb04c2023-11-20T07:05:19ZengMDPI AGRemote Sensing2072-42922020-07-011214229410.3390/rs12142294OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing DataHua Su0Haojie Zhang1Xupu Geng2Tian Qin3Wenfang Lu4Xiao-Hai Yan5Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education, National & Local Joint Engineering Research Centre of Satellite Geospatial Information Technology, Fuzhou University, Fuzhou 350108, ChinaKey Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education, National & Local Joint Engineering Research Centre of Satellite Geospatial Information Technology, Fuzhou University, Fuzhou 350108, ChinaJoint Institute for Coastal Research and Management, University of Delaware, Newark, DE 19716, USAKey Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education, National & Local Joint Engineering Research Centre of Satellite Geospatial Information Technology, Fuzhou University, Fuzhou 350108, ChinaKey Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education, National & Local Joint Engineering Research Centre of Satellite Geospatial Information Technology, Fuzhou University, Fuzhou 350108, ChinaJoint Institute for Coastal Research and Management, University of Delaware, Newark, DE 19716, USARetrieving information concerning the interior of the ocean using satellite remote sensing data has a major impact on studies of ocean dynamic and climate changes; however, the lack of information within the ocean limits such studies about the global ocean. In this paper, an artificial neural network, combined with satellite data and gridded Argo product, is used to estimate the ocean heat content (OHC) anomalies over four different depths down to 2000 m covering the near-global ocean, excluding the polar regions. Our method allows for the temporal hindcast of the OHC to other periods beyond the 2005–2018 training period. By applying an ensemble technique, the hindcasting uncertainty could also be estimated by using different 9-year periods for training and then calculating the standard deviation across six ensemble members. This new OHC product is called the Ocean Projection and Extension neural Network (OPEN) product. The accuracy of the product is accessed using the coefficient of determination (R<sup>2</sup>) and the relative root-mean-square error (RRMSE). The feature combinations and network architecture are optimized via a series of experiments. Overall, intercomparison with several routinely analyzed OHC products shows that the OPEN OHC has an R<sup>2</sup> larger than 0.95 and an RRMSE of <0.20 and presents notably accurate trends and variabilities. The OPEN product can therefore provide a valuable complement for studies of global climate changes.https://www.mdpi.com/2072-4292/12/14/2294remote sensing retrievalartificial neural networkocean heat contentdeep ocean remote sensing |
| spellingShingle | Hua Su Haojie Zhang Xupu Geng Tian Qin Wenfang Lu Xiao-Hai Yan OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing Data Remote Sensing remote sensing retrieval artificial neural network ocean heat content deep ocean remote sensing |
| title | OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing Data |
| title_full | OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing Data |
| title_fullStr | OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing Data |
| title_full_unstemmed | OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing Data |
| title_short | OPEN: A New Estimation of Global Ocean Heat Content for Upper 2000 Meters from Remote Sensing Data |
| title_sort | open a new estimation of global ocean heat content for upper 2000 meters from remote sensing data |
| topic | remote sensing retrieval artificial neural network ocean heat content deep ocean remote sensing |
| url | https://www.mdpi.com/2072-4292/12/14/2294 |
| work_keys_str_mv | AT huasu openanewestimationofglobaloceanheatcontentforupper2000metersfromremotesensingdata AT haojiezhang openanewestimationofglobaloceanheatcontentforupper2000metersfromremotesensingdata AT xupugeng openanewestimationofglobaloceanheatcontentforupper2000metersfromremotesensingdata AT tianqin openanewestimationofglobaloceanheatcontentforupper2000metersfromremotesensingdata AT wenfanglu openanewestimationofglobaloceanheatcontentforupper2000metersfromremotesensingdata AT xiaohaiyan openanewestimationofglobaloceanheatcontentforupper2000metersfromremotesensingdata |