Use of Hyper-Spectral Visible and Near-Infrared Satellite Data for Timely Estimates of the Earth’s Surface Reflectance in Cloudy and Aerosol Loaded Conditions: Part 1–Application to RGB Image Restoration Over Land With GOME-2
Space-based quantitative passive optical remote sensing of the Earth’s surface typically involves the detection and elimination of cloud-contaminated pixels as an initial processing step. We explore a fundamentally different approach; we use machine learning with cloud contaminated satellite hyper-s...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Remote Sensing |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frsen.2021.716430/full |
| _version_ | 1797972923681603584 |
|---|---|
| author | J. Joiner Z. Fasnacht W. Qin Y. Yoshida A. P. Vasilkov C. Li L. Lamsal N. Krotkov |
| author_facet | J. Joiner Z. Fasnacht W. Qin Y. Yoshida A. P. Vasilkov C. Li L. Lamsal N. Krotkov |
| author_sort | J. Joiner |
| collection | DOAJ |
| description | Space-based quantitative passive optical remote sensing of the Earth’s surface typically involves the detection and elimination of cloud-contaminated pixels as an initial processing step. We explore a fundamentally different approach; we use machine learning with cloud contaminated satellite hyper-spectral data to estimate underlying terrestrial surface reflectances at red, green, and blue (RGB) wavelengths. An artificial neural network (NN) reproduces land RGB reflectances with high fidelity, even in scenes with moderate to high cloud optical thicknesses. This implies that spectral features of the Earth’s surface can be detected and distinguished in the presence of clouds, even when they are partially and visibly obscured by clouds; the NN is able to separate the spectral fingerprint of the Earth’s surface from that of the clouds, aerosols, gaseous absorption, and Rayleigh scattering, provided that there are adequately different spectral features and that the clouds are not completely opaque. Once trained, the NN enables rapid estimates of RGB reflectances with little computational cost. Aside from the training data, there is no requirement of prior information regarding the land surface spectral reflectance, nor is there need for radiative transfer calculations. We test different wavelength windows and instrument configurations for reconstruction of surface reflectances. This work provides an initial example of a general approach that has many potential applications in land and ocean remote sensing as well as other practical uses such as in search and rescue, precision agriculture, and change detection. |
| first_indexed | 2024-04-11T03:56:07Z |
| format | Article |
| id | doaj.art-49d9a55a8c6245b8be4f3126cb666a1c |
| institution | Directory Open Access Journal |
| issn | 2673-6187 |
| language | English |
| last_indexed | 2024-04-11T03:56:07Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Remote Sensing |
| spelling | doaj.art-49d9a55a8c6245b8be4f3126cb666a1c2023-01-02T00:23:10ZengFrontiers Media S.A.Frontiers in Remote Sensing2673-61872022-01-01210.3389/frsen.2021.716430716430Use of Hyper-Spectral Visible and Near-Infrared Satellite Data for Timely Estimates of the Earth’s Surface Reflectance in Cloudy and Aerosol Loaded Conditions: Part 1–Application to RGB Image Restoration Over Land With GOME-2J. Joiner0Z. Fasnacht1W. Qin2Y. Yoshida3A. P. Vasilkov4C. Li5L. Lamsal6N. Krotkov7Laboratory for Atmospheric Chemistry and Dynamics, NASA Goddard Space Flight Center, Greenbelt, MD, United StatesScience Systems and Applications, Inc. (SSAI), Lanham, MD, United StatesScience Systems and Applications, Inc. (SSAI), Lanham, MD, United StatesScience Systems and Applications, Inc. (SSAI), Lanham, MD, United StatesScience Systems and Applications, Inc. (SSAI), Lanham, MD, United StatesUniversity of Maryland, College Park, MD, United StatesUniversities Space Research Association, Columbia, MD, United StatesLaboratory for Atmospheric Chemistry and Dynamics, NASA Goddard Space Flight Center, Greenbelt, MD, United StatesSpace-based quantitative passive optical remote sensing of the Earth’s surface typically involves the detection and elimination of cloud-contaminated pixels as an initial processing step. We explore a fundamentally different approach; we use machine learning with cloud contaminated satellite hyper-spectral data to estimate underlying terrestrial surface reflectances at red, green, and blue (RGB) wavelengths. An artificial neural network (NN) reproduces land RGB reflectances with high fidelity, even in scenes with moderate to high cloud optical thicknesses. This implies that spectral features of the Earth’s surface can be detected and distinguished in the presence of clouds, even when they are partially and visibly obscured by clouds; the NN is able to separate the spectral fingerprint of the Earth’s surface from that of the clouds, aerosols, gaseous absorption, and Rayleigh scattering, provided that there are adequately different spectral features and that the clouds are not completely opaque. Once trained, the NN enables rapid estimates of RGB reflectances with little computational cost. Aside from the training data, there is no requirement of prior information regarding the land surface spectral reflectance, nor is there need for radiative transfer calculations. We test different wavelength windows and instrument configurations for reconstruction of surface reflectances. This work provides an initial example of a general approach that has many potential applications in land and ocean remote sensing as well as other practical uses such as in search and rescue, precision agriculture, and change detection.https://www.frontiersin.org/articles/10.3389/frsen.2021.716430/fullimage reconstructioncloudy remote sensingcloud removalcloud-clearingcloud-contamination |
| spellingShingle | J. Joiner Z. Fasnacht W. Qin Y. Yoshida A. P. Vasilkov C. Li L. Lamsal N. Krotkov Use of Hyper-Spectral Visible and Near-Infrared Satellite Data for Timely Estimates of the Earth’s Surface Reflectance in Cloudy and Aerosol Loaded Conditions: Part 1–Application to RGB Image Restoration Over Land With GOME-2 Frontiers in Remote Sensing image reconstruction cloudy remote sensing cloud removal cloud-clearing cloud-contamination |
| title | Use of Hyper-Spectral Visible and Near-Infrared Satellite Data for Timely Estimates of the Earth’s Surface Reflectance in Cloudy and Aerosol Loaded Conditions: Part 1–Application to RGB Image Restoration Over Land With GOME-2 |
| title_full | Use of Hyper-Spectral Visible and Near-Infrared Satellite Data for Timely Estimates of the Earth’s Surface Reflectance in Cloudy and Aerosol Loaded Conditions: Part 1–Application to RGB Image Restoration Over Land With GOME-2 |
| title_fullStr | Use of Hyper-Spectral Visible and Near-Infrared Satellite Data for Timely Estimates of the Earth’s Surface Reflectance in Cloudy and Aerosol Loaded Conditions: Part 1–Application to RGB Image Restoration Over Land With GOME-2 |
| title_full_unstemmed | Use of Hyper-Spectral Visible and Near-Infrared Satellite Data for Timely Estimates of the Earth’s Surface Reflectance in Cloudy and Aerosol Loaded Conditions: Part 1–Application to RGB Image Restoration Over Land With GOME-2 |
| title_short | Use of Hyper-Spectral Visible and Near-Infrared Satellite Data for Timely Estimates of the Earth’s Surface Reflectance in Cloudy and Aerosol Loaded Conditions: Part 1–Application to RGB Image Restoration Over Land With GOME-2 |
| title_sort | use of hyper spectral visible and near infrared satellite data for timely estimates of the earth s surface reflectance in cloudy and aerosol loaded conditions part 1 application to rgb image restoration over land with gome 2 |
| topic | image reconstruction cloudy remote sensing cloud removal cloud-clearing cloud-contamination |
| url | https://www.frontiersin.org/articles/10.3389/frsen.2021.716430/full |
| work_keys_str_mv | AT jjoiner useofhyperspectralvisibleandnearinfraredsatellitedatafortimelyestimatesoftheearthssurfacereflectanceincloudyandaerosolloadedconditionspart1applicationtorgbimagerestorationoverlandwithgome2 AT zfasnacht useofhyperspectralvisibleandnearinfraredsatellitedatafortimelyestimatesoftheearthssurfacereflectanceincloudyandaerosolloadedconditionspart1applicationtorgbimagerestorationoverlandwithgome2 AT wqin useofhyperspectralvisibleandnearinfraredsatellitedatafortimelyestimatesoftheearthssurfacereflectanceincloudyandaerosolloadedconditionspart1applicationtorgbimagerestorationoverlandwithgome2 AT yyoshida useofhyperspectralvisibleandnearinfraredsatellitedatafortimelyestimatesoftheearthssurfacereflectanceincloudyandaerosolloadedconditionspart1applicationtorgbimagerestorationoverlandwithgome2 AT apvasilkov useofhyperspectralvisibleandnearinfraredsatellitedatafortimelyestimatesoftheearthssurfacereflectanceincloudyandaerosolloadedconditionspart1applicationtorgbimagerestorationoverlandwithgome2 AT cli useofhyperspectralvisibleandnearinfraredsatellitedatafortimelyestimatesoftheearthssurfacereflectanceincloudyandaerosolloadedconditionspart1applicationtorgbimagerestorationoverlandwithgome2 AT llamsal useofhyperspectralvisibleandnearinfraredsatellitedatafortimelyestimatesoftheearthssurfacereflectanceincloudyandaerosolloadedconditionspart1applicationtorgbimagerestorationoverlandwithgome2 AT nkrotkov useofhyperspectralvisibleandnearinfraredsatellitedatafortimelyestimatesoftheearthssurfacereflectanceincloudyandaerosolloadedconditionspart1applicationtorgbimagerestorationoverlandwithgome2 |