Restoration of missing ocean color data in high-latitude oceans using neural network model
Satellite ocean color remote sensing plays a crucial role in monitoring marine environment at both regional and global scales. However, due to the reduced accuracy of atmospheric correction models under large solar zenith angles (≥70°), publicly available satellite ocean color products lack valid da...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-04-01
|
| Series: | Big Earth Data |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/20964471.2025.2474655 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839647258350452736 |
|---|---|
| author | Hao Li Xianqiang He Yan Bai Difeng Wang Teng Li Fang Gong |
| author_facet | Hao Li Xianqiang He Yan Bai Difeng Wang Teng Li Fang Gong |
| author_sort | Hao Li |
| collection | DOAJ |
| description | Satellite ocean color remote sensing plays a crucial role in monitoring marine environment at both regional and global scales. However, due to the reduced accuracy of atmospheric correction models under large solar zenith angles (≥70°), publicly available satellite ocean color products lack valid datasets for high-latitude oceans (≥50°S or ≥50°N) during winter. Based on a neural network atmospheric correction model designed for high solar zenith angle observation environments (which used a Rayleigh scattering lookup table generated by PCOART-SA to compute Rayleigh scattering radiance and a neural network model to invert remote sensing reflectance from Rayleigh-corrected radiance), this study has established a monthly ocean color product dataset for high-latitude oceans, named NN-LAT50, covering the period from 2003 to 2020. We validated the accuracy of the ocean color products in NN-LAT50 dataset using multiple in situ datasets, and the results indicated that NN-LAT50 had more reliable and accurate retrievals compared to the NASA released ocean color products in high latitude oceans. Furthermore, during autumn and winter, coverage of the NN-LAT50 dataset far exceeds that of products released by NASA. For instance, during the winter in the Southern Hemisphere, the coverage rates are 3.02% for MODIS/Aqua, 21.59% for VIIRS, and 1.74% for OLCI, while the NN-LAT50 dataset maintains a coverage rate of 38.64%. This study is the first to establish a long-term (2003–2020) ocean color product dataset covering high-latitude oceans during winter, which can significantly enhance the observation of ecological changes in polar and subpolar oceans. |
| format | Article |
| id | doaj-art-d82c4032b3eb41f683e5c8fc51457581 |
| institution | Matheson Library |
| issn | 2096-4471 2574-5417 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Big Earth Data |
| spelling | doaj-art-d82c4032b3eb41f683e5c8fc514575812025-06-30T08:43:22ZengTaylor & Francis GroupBig Earth Data2096-44712574-54172025-04-019233635510.1080/20964471.2025.2474655Restoration of missing ocean color data in high-latitude oceans using neural network modelHao Li0Xianqiang He1Yan Bai2Difeng Wang3Teng Li4Fang Gong5Ocean Remote Sensing Detection Technology Center, Donghai Laboratory, Zhoushan, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaState Key Laboratory of Satellite Ocean Environment Dynamics, Second Institute of Oceanography, Ministry of Natural Resources, Hangzhou, ChinaSatellite ocean color remote sensing plays a crucial role in monitoring marine environment at both regional and global scales. However, due to the reduced accuracy of atmospheric correction models under large solar zenith angles (≥70°), publicly available satellite ocean color products lack valid datasets for high-latitude oceans (≥50°S or ≥50°N) during winter. Based on a neural network atmospheric correction model designed for high solar zenith angle observation environments (which used a Rayleigh scattering lookup table generated by PCOART-SA to compute Rayleigh scattering radiance and a neural network model to invert remote sensing reflectance from Rayleigh-corrected radiance), this study has established a monthly ocean color product dataset for high-latitude oceans, named NN-LAT50, covering the period from 2003 to 2020. We validated the accuracy of the ocean color products in NN-LAT50 dataset using multiple in situ datasets, and the results indicated that NN-LAT50 had more reliable and accurate retrievals compared to the NASA released ocean color products in high latitude oceans. Furthermore, during autumn and winter, coverage of the NN-LAT50 dataset far exceeds that of products released by NASA. For instance, during the winter in the Southern Hemisphere, the coverage rates are 3.02% for MODIS/Aqua, 21.59% for VIIRS, and 1.74% for OLCI, while the NN-LAT50 dataset maintains a coverage rate of 38.64%. This study is the first to establish a long-term (2003–2020) ocean color product dataset covering high-latitude oceans during winter, which can significantly enhance the observation of ecological changes in polar and subpolar oceans.https://www.tandfonline.com/doi/10.1080/20964471.2025.2474655Ocean color datasethigh-latitude oceansremote sensingneural networklong-term time series |
| spellingShingle | Hao Li Xianqiang He Yan Bai Difeng Wang Teng Li Fang Gong Restoration of missing ocean color data in high-latitude oceans using neural network model Big Earth Data Ocean color dataset high-latitude oceans remote sensing neural network long-term time series |
| title | Restoration of missing ocean color data in high-latitude oceans using neural network model |
| title_full | Restoration of missing ocean color data in high-latitude oceans using neural network model |
| title_fullStr | Restoration of missing ocean color data in high-latitude oceans using neural network model |
| title_full_unstemmed | Restoration of missing ocean color data in high-latitude oceans using neural network model |
| title_short | Restoration of missing ocean color data in high-latitude oceans using neural network model |
| title_sort | restoration of missing ocean color data in high latitude oceans using neural network model |
| topic | Ocean color dataset high-latitude oceans remote sensing neural network long-term time series |
| url | https://www.tandfonline.com/doi/10.1080/20964471.2025.2474655 |
| work_keys_str_mv | AT haoli restorationofmissingoceancolordatainhighlatitudeoceansusingneuralnetworkmodel AT xianqianghe restorationofmissingoceancolordatainhighlatitudeoceansusingneuralnetworkmodel AT yanbai restorationofmissingoceancolordatainhighlatitudeoceansusingneuralnetworkmodel AT difengwang restorationofmissingoceancolordatainhighlatitudeoceansusingneuralnetworkmodel AT tengli restorationofmissingoceancolordatainhighlatitudeoceansusingneuralnetworkmodel AT fanggong restorationofmissingoceancolordatainhighlatitudeoceansusingneuralnetworkmodel |