Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal Waters
Remote sensing of global ocean color is a valuable tool for understanding the ecology and biogeochemistry of the worlds oceans, and provides critical input to our knowledge of the global carbon cycle and the impacts of climate change. Ocean polarized reflectance contains information about the consti...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/9/1421 |
| _version_ | 1797569172131020800 |
|---|---|
| author | Lipi Mukherjee Peng-Wang Zhai Meng Gao Yongxiang Hu Bryan A. Franz P. Jeremy Werdell |
| author_facet | Lipi Mukherjee Peng-Wang Zhai Meng Gao Yongxiang Hu Bryan A. Franz P. Jeremy Werdell |
| author_sort | Lipi Mukherjee |
| collection | DOAJ |
| description | Remote sensing of global ocean color is a valuable tool for understanding the ecology and biogeochemistry of the worlds oceans, and provides critical input to our knowledge of the global carbon cycle and the impacts of climate change. Ocean polarized reflectance contains information about the constituents of the upper ocean euphotic zone, such as colored dissolved organic matter (CDOM), sediments, phytoplankton, and pollutants. In order to retrieve the information on these constituents, remote sensing algorithms typically rely on radiative transfer models to interpret water color or remote-sensing reflectance; however, this can be resource-prohibitive for operational use due to the extensive CPU time involved in radiative transfer solutions. In this work, we report a fast model based on machine learning techniques, called Neural Network Reflectance Prediction Model (NNRPM), which can be used to predict ocean bidirectional polarized reflectance given inherent optical properties of ocean waters. This supervised model is trained using a large volume of data derived from radiative transfer simulations for coupled atmosphere and ocean systems using the successive order of scattering technique (SOS-CAOS). The performance of the model is validated against another large independent test dataset generated from SOS-CAOS. The model is able to predict both polarized and unpolarized reflectances with an absolute error (AE) less than 0.004 for 99% of test cases. We have also shown that the degree of linear polarization (DoLP) for unpolarized incident light can be predicted with an AE less than 0.002 for 99% of test cases. In general, the simulation time of SOS-CAOS depends on optical depth, and required accuracy. When comparing the average speeds of the NNRPM against the SOS-CAOS model for the same parameters, we see that the NNRPM is able to predict the Ocean BRDF 6000 times faster than SOS-CAOS. Both ultraviolet and visible wavelengths are included in the model to help differentiate between dissolved organic material and chlorophyll in the study of the open ocean and the coastal zone. The incorporation of this model into the retrieval algorithm will make the retrieval process more efficient, and thus applicable for operational use with global satellite observations. |
| first_indexed | 2024-03-10T20:07:09Z |
| format | Article |
| id | doaj.art-152d284965254888b1f4fee46be9bd5f |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T20:07:09Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-152d284965254888b1f4fee46be9bd5f2023-11-19T23:08:59ZengMDPI AGRemote Sensing2072-42922020-04-01129142110.3390/rs12091421Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal WatersLipi Mukherjee0Peng-Wang Zhai1Meng Gao2Yongxiang Hu3Bryan A. Franz4P. Jeremy Werdell5Joint Center for Earth Systems Technology, Department of Physics, University of Maryland, Baltimore County, 1000 Hilltop Circle Baltimore, Baltimore, MD 21250, USAJoint Center for Earth Systems Technology, Department of Physics, University of Maryland, Baltimore County, 1000 Hilltop Circle Baltimore, Baltimore, MD 21250, USASSAI, NASA Goddard Space Flight Center, Code 616, Greenbelt, MD 20771, USAMS 475 NASA Langley Research Center, Hampton, VA 23681-2199, USANASA Goddard Space Flight Center, Code 616, Greenbelt, MD 20771, USANASA Goddard Space Flight Center, Code 616, Greenbelt, MD 20771, USARemote sensing of global ocean color is a valuable tool for understanding the ecology and biogeochemistry of the worlds oceans, and provides critical input to our knowledge of the global carbon cycle and the impacts of climate change. Ocean polarized reflectance contains information about the constituents of the upper ocean euphotic zone, such as colored dissolved organic matter (CDOM), sediments, phytoplankton, and pollutants. In order to retrieve the information on these constituents, remote sensing algorithms typically rely on radiative transfer models to interpret water color or remote-sensing reflectance; however, this can be resource-prohibitive for operational use due to the extensive CPU time involved in radiative transfer solutions. In this work, we report a fast model based on machine learning techniques, called Neural Network Reflectance Prediction Model (NNRPM), which can be used to predict ocean bidirectional polarized reflectance given inherent optical properties of ocean waters. This supervised model is trained using a large volume of data derived from radiative transfer simulations for coupled atmosphere and ocean systems using the successive order of scattering technique (SOS-CAOS). The performance of the model is validated against another large independent test dataset generated from SOS-CAOS. The model is able to predict both polarized and unpolarized reflectances with an absolute error (AE) less than 0.004 for 99% of test cases. We have also shown that the degree of linear polarization (DoLP) for unpolarized incident light can be predicted with an AE less than 0.002 for 99% of test cases. In general, the simulation time of SOS-CAOS depends on optical depth, and required accuracy. When comparing the average speeds of the NNRPM against the SOS-CAOS model for the same parameters, we see that the NNRPM is able to predict the Ocean BRDF 6000 times faster than SOS-CAOS. Both ultraviolet and visible wavelengths are included in the model to help differentiate between dissolved organic material and chlorophyll in the study of the open ocean and the coastal zone. The incorporation of this model into the retrieval algorithm will make the retrieval process more efficient, and thus applicable for operational use with global satellite observations.https://www.mdpi.com/2072-4292/12/9/1421radiative transferretrievalreflectance modelpolarizationocean opticsneural network |
| spellingShingle | Lipi Mukherjee Peng-Wang Zhai Meng Gao Yongxiang Hu Bryan A. Franz P. Jeremy Werdell Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal Waters Remote Sensing radiative transfer retrieval reflectance model polarization ocean optics neural network |
| title | Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal Waters |
| title_full | Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal Waters |
| title_fullStr | Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal Waters |
| title_full_unstemmed | Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal Waters |
| title_short | Neural Network Reflectance Prediction Model for Both Open Ocean and Coastal Waters |
| title_sort | neural network reflectance prediction model for both open ocean and coastal waters |
| topic | radiative transfer retrieval reflectance model polarization ocean optics neural network |
| url | https://www.mdpi.com/2072-4292/12/9/1421 |
| work_keys_str_mv | AT lipimukherjee neuralnetworkreflectancepredictionmodelforbothopenoceanandcoastalwaters AT pengwangzhai neuralnetworkreflectancepredictionmodelforbothopenoceanandcoastalwaters AT menggao neuralnetworkreflectancepredictionmodelforbothopenoceanandcoastalwaters AT yongxianghu neuralnetworkreflectancepredictionmodelforbothopenoceanandcoastalwaters AT bryanafranz neuralnetworkreflectancepredictionmodelforbothopenoceanandcoastalwaters AT pjeremywerdell neuralnetworkreflectancepredictionmodelforbothopenoceanandcoastalwaters |