Improving GOCI ocean color data under high solar-zenith angle over open oceans using neural networks
With hourly measurements available during daytime between local times of 09:00–16:00, ocean color data derived from the Geostationary Ocean Color Imager (GOCI) onboard the Korean Communication, Ocean, and Meteorological (COMS) satellite have been useful for research and surveillance of diurnal proce...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/15481603.2024.2353426 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850176582456442880 |
|---|---|
| author | Xiaoming Liu Menghua Wang |
| author_facet | Xiaoming Liu Menghua Wang |
| author_sort | Xiaoming Liu |
| collection | DOAJ |
| description | With hourly measurements available during daytime between local times of 09:00–16:00, ocean color data derived from the Geostationary Ocean Color Imager (GOCI) onboard the Korean Communication, Ocean, and Meteorological (COMS) satellite have been useful for research and surveillance of diurnal processes in the western Pacific Ocean region. However, in early morning and late afternoon measurements, there are significant errors in GOCI-derived ocean color products as the solar-zenith angle (θ0) goes beyond 70°, especially in autumn and winter seasons. In this study, we employ a neural network (NN) model to make corrections on the GOCI-measured normalize water-leaving radiance spectra, nLw(λ), with high θ0 (>70°) in open oceans. Results show that NN-corrected nLw(λ) are consistent with the previous-hour nLw(λ) and make the diurnal variations in the region much more stable and reasonable. Specifically, the GOCI-measured nLw(λ) with θ0 ≤65° in earlier hours of the day (including some nLw(λ) diurnal variation) are considered accurate and used as the ground truth to train NN models for nLw(λ) correction with high θ0. Further analysis of the relationship of ratios (between the NN-corrected and original nLw(λ)) with θ0 shows that the nLw(λ) ratios increase as θ0 increase, which indicates that there are more significant corrections with larger θ0 (>70°). The performance evaluation of the NN models is based on the comparison of NN-corrected nLw(λ) with the original previous hour nLw(λ) data. The ratios of NN-corrected nLw(λ) to the original previous hour nLw(λ) are 0.968–1.045 for the short blue/blue and green bands, and the performance of nLw(λ) correction at 14:00 and 15:00 is slightly better than that at 16:00, due to significantly large θ0 at late afternoon hours. The NN-corrected nLw(λ) data are also used to derive chlorophyll-a (Chl-a) concentration, showing significantly improved Chl-a in GOCI’s late afternoon measurements with θ0 >70°. |
| format | Article |
| id | doaj-art-7973273d454f47a2b46a1df5e4c2f40e |
| institution | OA Journals |
| issn | 1548-1603 1943-7226 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj-art-7973273d454f47a2b46a1df5e4c2f40e2025-08-20T02:19:14ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262024-12-0161110.1080/15481603.2024.2353426Improving GOCI ocean color data under high solar-zenith angle over open oceans using neural networksXiaoming Liu0Menghua Wang1NOAA National Environmental Satellite, Data, and Information Service, Center for Satellite Applications and Research, College Park, MD, USANOAA National Environmental Satellite, Data, and Information Service, Center for Satellite Applications and Research, College Park, MD, USAWith hourly measurements available during daytime between local times of 09:00–16:00, ocean color data derived from the Geostationary Ocean Color Imager (GOCI) onboard the Korean Communication, Ocean, and Meteorological (COMS) satellite have been useful for research and surveillance of diurnal processes in the western Pacific Ocean region. However, in early morning and late afternoon measurements, there are significant errors in GOCI-derived ocean color products as the solar-zenith angle (θ0) goes beyond 70°, especially in autumn and winter seasons. In this study, we employ a neural network (NN) model to make corrections on the GOCI-measured normalize water-leaving radiance spectra, nLw(λ), with high θ0 (>70°) in open oceans. Results show that NN-corrected nLw(λ) are consistent with the previous-hour nLw(λ) and make the diurnal variations in the region much more stable and reasonable. Specifically, the GOCI-measured nLw(λ) with θ0 ≤65° in earlier hours of the day (including some nLw(λ) diurnal variation) are considered accurate and used as the ground truth to train NN models for nLw(λ) correction with high θ0. Further analysis of the relationship of ratios (between the NN-corrected and original nLw(λ)) with θ0 shows that the nLw(λ) ratios increase as θ0 increase, which indicates that there are more significant corrections with larger θ0 (>70°). The performance evaluation of the NN models is based on the comparison of NN-corrected nLw(λ) with the original previous hour nLw(λ) data. The ratios of NN-corrected nLw(λ) to the original previous hour nLw(λ) are 0.968–1.045 for the short blue/blue and green bands, and the performance of nLw(λ) correction at 14:00 and 15:00 is slightly better than that at 16:00, due to significantly large θ0 at late afternoon hours. The NN-corrected nLw(λ) data are also used to derive chlorophyll-a (Chl-a) concentration, showing significantly improved Chl-a in GOCI’s late afternoon measurements with θ0 >70°.https://www.tandfonline.com/doi/10.1080/15481603.2024.2353426Satellite remote sensingocean colorgeostationarynormalized water-leaving radiance |
| spellingShingle | Xiaoming Liu Menghua Wang Improving GOCI ocean color data under high solar-zenith angle over open oceans using neural networks GIScience & Remote Sensing Satellite remote sensing ocean color geostationary normalized water-leaving radiance |
| title | Improving GOCI ocean color data under high solar-zenith angle over open oceans using neural networks |
| title_full | Improving GOCI ocean color data under high solar-zenith angle over open oceans using neural networks |
| title_fullStr | Improving GOCI ocean color data under high solar-zenith angle over open oceans using neural networks |
| title_full_unstemmed | Improving GOCI ocean color data under high solar-zenith angle over open oceans using neural networks |
| title_short | Improving GOCI ocean color data under high solar-zenith angle over open oceans using neural networks |
| title_sort | improving goci ocean color data under high solar zenith angle over open oceans using neural networks |
| topic | Satellite remote sensing ocean color geostationary normalized water-leaving radiance |
| url | https://www.tandfonline.com/doi/10.1080/15481603.2024.2353426 |
| work_keys_str_mv | AT xiaomingliu improvinggocioceancolordataunderhighsolarzenithangleoveropenoceansusingneuralnetworks AT menghuawang improvinggocioceancolordataunderhighsolarzenithangleoveropenoceansusingneuralnetworks |