Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural Network
The Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-orbiting Partnership (SNPP) satellite has been a reliable source of ocean color data products, including five moderate (M) bands and one imagery (I) band normalized water-leaving radiance spectra <i>nL<su...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/10/1944 |
| _version_ | 1797533843095289856 |
|---|---|
| author | Xiaoming Liu Menghua Wang |
| author_facet | Xiaoming Liu Menghua Wang |
| author_sort | Xiaoming Liu |
| collection | DOAJ |
| description | The Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-orbiting Partnership (SNPP) satellite has been a reliable source of ocean color data products, including five moderate (M) bands and one imagery (I) band normalized water-leaving radiance spectra <i>nL<sub>w</sub></i>(<i>λ</i>). The spatial resolutions of the M-band and I-band <i>nL<sub>w</sub></i>(<i>λ</i>) are 750 m and 375 m, respectively. With the technique of convolutional neural network (CNN), the M-band <i>nL<sub>w</sub></i>(<i>λ</i>) imagery can be super-resolved from 750 m to 375 m spatial resolution by leveraging the high spatial resolution features of I1-band <i>nL<sub>w</sub></i>(<i>λ</i>) data. However, it is also important to enhance the spatial resolution of VIIRS-derived chlorophyll-a (Chl-a) concentration and the water diffuse attenuation coefficient at the wavelength of 490 nm (<i>K<sub>d</sub></i>(490)), as well as other biological and biogeochemical products. In this study, we describe our effort to derive high-resolution <i>K<sub>d</sub></i>(490) and Chl-a data based on super-resolved <i>nL<sub>w</sub></i>(<i>λ</i>) images at the VIIRS five M-bands. To improve the network performance over extremely turbid coastal oceans and inland waters, the networks are retrained with a training dataset including ocean color data from the Bohai Sea, Baltic Sea, and La Plata River Estuary, covering water types from clear open oceans to moderately turbid and highly turbid waters. The evaluation results show that the super-resolved <i>K<sub>d</sub></i>(490) image is much sharper than the original one, and has more detailed fine spatial structures. A similar enhancement of finer structures is also found in the super-resolved Chl-a images. Chl-a filaments are much sharper and thinner in the super-resolved image, and some of the very fine spatial features that are not shown in the original images appear in the super-resolved Chl-a imageries. The networks are also applied to four other coastal and inland water regions. The results show that super-resolution occurs mainly on pixels of Chl-a and <i>K<sub>d</sub></i>(490) features, especially on the feature edges and locations with a large spatial gradient. The biases between the original M-band images and super-resolved high-resolution images are small for both Chl-a and <i>K<sub>d</sub></i>(490) in moderately to extremely turbid coastal oceans and inland waters, indicating that the super-resolution process does not change the mean values of the original images. |
| first_indexed | 2024-03-10T11:21:24Z |
| format | Article |
| id | doaj.art-cc36f37962b84729abb5e0cce3633326 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T11:21:24Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-cc36f37962b84729abb5e0cce36333262023-11-21T20:01:20ZengMDPI AGRemote Sensing2072-42922021-05-011310194410.3390/rs13101944Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural NetworkXiaoming Liu0Menghua Wang1NOAA National Environmental Satellite, Data, and Information Service, Center for Satellite Applications and Research, 5830 University Research Court, College Park, MD 20746, USANOAA National Environmental Satellite, Data, and Information Service, Center for Satellite Applications and Research, 5830 University Research Court, College Park, MD 20746, USAThe Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-orbiting Partnership (SNPP) satellite has been a reliable source of ocean color data products, including five moderate (M) bands and one imagery (I) band normalized water-leaving radiance spectra <i>nL<sub>w</sub></i>(<i>λ</i>). The spatial resolutions of the M-band and I-band <i>nL<sub>w</sub></i>(<i>λ</i>) are 750 m and 375 m, respectively. With the technique of convolutional neural network (CNN), the M-band <i>nL<sub>w</sub></i>(<i>λ</i>) imagery can be super-resolved from 750 m to 375 m spatial resolution by leveraging the high spatial resolution features of I1-band <i>nL<sub>w</sub></i>(<i>λ</i>) data. However, it is also important to enhance the spatial resolution of VIIRS-derived chlorophyll-a (Chl-a) concentration and the water diffuse attenuation coefficient at the wavelength of 490 nm (<i>K<sub>d</sub></i>(490)), as well as other biological and biogeochemical products. In this study, we describe our effort to derive high-resolution <i>K<sub>d</sub></i>(490) and Chl-a data based on super-resolved <i>nL<sub>w</sub></i>(<i>λ</i>) images at the VIIRS five M-bands. To improve the network performance over extremely turbid coastal oceans and inland waters, the networks are retrained with a training dataset including ocean color data from the Bohai Sea, Baltic Sea, and La Plata River Estuary, covering water types from clear open oceans to moderately turbid and highly turbid waters. The evaluation results show that the super-resolved <i>K<sub>d</sub></i>(490) image is much sharper than the original one, and has more detailed fine spatial structures. A similar enhancement of finer structures is also found in the super-resolved Chl-a images. Chl-a filaments are much sharper and thinner in the super-resolved image, and some of the very fine spatial features that are not shown in the original images appear in the super-resolved Chl-a imageries. The networks are also applied to four other coastal and inland water regions. The results show that super-resolution occurs mainly on pixels of Chl-a and <i>K<sub>d</sub></i>(490) features, especially on the feature edges and locations with a large spatial gradient. The biases between the original M-band images and super-resolved high-resolution images are small for both Chl-a and <i>K<sub>d</sub></i>(490) in moderately to extremely turbid coastal oceans and inland waters, indicating that the super-resolution process does not change the mean values of the original images.https://www.mdpi.com/2072-4292/13/10/1944VIIRSocean colorchlorophyll-asuper-resolutionconvolutional neural network |
| spellingShingle | Xiaoming Liu Menghua Wang Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural Network Remote Sensing VIIRS ocean color chlorophyll-a super-resolution convolutional neural network |
| title | Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural Network |
| title_full | Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural Network |
| title_fullStr | Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural Network |
| title_full_unstemmed | Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural Network |
| title_short | Deriving VIIRS High-Spatial Resolution Water Property Data over Coastal and Inland Waters Using Deep Convolutional Neural Network |
| title_sort | deriving viirs high spatial resolution water property data over coastal and inland waters using deep convolutional neural network |
| topic | VIIRS ocean color chlorophyll-a super-resolution convolutional neural network |
| url | https://www.mdpi.com/2072-4292/13/10/1944 |
| work_keys_str_mv | AT xiaomingliu derivingviirshighspatialresolutionwaterpropertydataovercoastalandinlandwatersusingdeepconvolutionalneuralnetwork AT menghuawang derivingviirshighspatialresolutionwaterpropertydataovercoastalandinlandwatersusingdeepconvolutionalneuralnetwork |