Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning Models
Very-high-resolution (VHR) optical imaging satellites can offer precise, accurate, and direct measurements of snow-covered areas (SCA) with sub-meter to meter-scale resolution in regions of complex land cover and terrain. We explore the potential of Maxar WorldView-2 and WorldView-3 in-track stereo...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/17/4227 |
| _version_ | 1797493368984436736 |
|---|---|
| author | J. Michelle Hu David Shean |
| author_facet | J. Michelle Hu David Shean |
| author_sort | J. Michelle Hu |
| collection | DOAJ |
| description | Very-high-resolution (VHR) optical imaging satellites can offer precise, accurate, and direct measurements of snow-covered areas (SCA) with sub-meter to meter-scale resolution in regions of complex land cover and terrain. We explore the potential of Maxar WorldView-2 and WorldView-3 in-track stereo images (WV) for land and snow cover mapping at two sites in the Western U.S. with different snow regimes, topographies, vegetation, and underlying geology. We trained random forest models using combinations of multispectral bands and normalized difference indices (i.e., NDVI) to produce land cover maps for priority feature classes (snow, shaded snow, vegetation, water, and exposed ground). We then created snow-covered area products from these maps and compared them with coarser resolution satellite fractional snow-covered area (fSCA) products from Landsat (~30 m) and MODIS (~500 m). Our models generated accurate classifications, even with limited combinations of available multispectral bands. Models trained on a single image demonstrated limited model transfer, with best results found for in-region transfers. Coarser-resolution Landsat and MODSCAG fSCA products identified many more pixels as completely snow-covered (100% fSCA) than WV fSCA. However, while MODSCAG fSCA products also identified many more completely snow-free pixels (0% fSCA) than WV fSCA, Landsat fSCA products only slightly underestimated the number of completely snow-free pixels. Overall, our results demonstrate that strategic image observations with VHR satellites such as WorldView-2 and WorldView-3 can complement the existing operational snow data products to map the evolution of seasonal snow cover. |
| first_indexed | 2024-03-10T01:19:03Z |
| format | Article |
| id | doaj.art-73c4f36f574a4da9bf6404e6e61ca4c5 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T01:19:03Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-73c4f36f574a4da9bf6404e6e61ca4c52023-11-23T14:03:04ZengMDPI AGRemote Sensing2072-42922022-08-011417422710.3390/rs14174227Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning ModelsJ. Michelle Hu0David Shean1Department of Civil and Environmental Engineering, University of Washington, Seattle, WA 98195, USADepartment of Civil and Environmental Engineering, University of Washington, Seattle, WA 98195, USAVery-high-resolution (VHR) optical imaging satellites can offer precise, accurate, and direct measurements of snow-covered areas (SCA) with sub-meter to meter-scale resolution in regions of complex land cover and terrain. We explore the potential of Maxar WorldView-2 and WorldView-3 in-track stereo images (WV) for land and snow cover mapping at two sites in the Western U.S. with different snow regimes, topographies, vegetation, and underlying geology. We trained random forest models using combinations of multispectral bands and normalized difference indices (i.e., NDVI) to produce land cover maps for priority feature classes (snow, shaded snow, vegetation, water, and exposed ground). We then created snow-covered area products from these maps and compared them with coarser resolution satellite fractional snow-covered area (fSCA) products from Landsat (~30 m) and MODIS (~500 m). Our models generated accurate classifications, even with limited combinations of available multispectral bands. Models trained on a single image demonstrated limited model transfer, with best results found for in-region transfers. Coarser-resolution Landsat and MODSCAG fSCA products identified many more pixels as completely snow-covered (100% fSCA) than WV fSCA. However, while MODSCAG fSCA products also identified many more completely snow-free pixels (0% fSCA) than WV fSCA, Landsat fSCA products only slightly underestimated the number of completely snow-free pixels. Overall, our results demonstrate that strategic image observations with VHR satellites such as WorldView-2 and WorldView-3 can complement the existing operational snow data products to map the evolution of seasonal snow cover.https://www.mdpi.com/2072-4292/14/17/4227cryosphereseasonal snow coverfractional snow-covered area (fSCA)WorldView |
| spellingShingle | J. Michelle Hu David Shean Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning Models Remote Sensing cryosphere seasonal snow cover fractional snow-covered area (fSCA) WorldView |
| title | Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning Models |
| title_full | Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning Models |
| title_fullStr | Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning Models |
| title_full_unstemmed | Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning Models |
| title_short | Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning Models |
| title_sort | improving mountain snow and land cover mapping using very high resolution vhr optical satellite images and random forest machine learning models |
| topic | cryosphere seasonal snow cover fractional snow-covered area (fSCA) WorldView |
| url | https://www.mdpi.com/2072-4292/14/17/4227 |
| work_keys_str_mv | AT jmichellehu improvingmountainsnowandlandcovermappingusingveryhighresolutionvhropticalsatelliteimagesandrandomforestmachinelearningmodels AT davidshean improvingmountainsnowandlandcovermappingusingveryhighresolutionvhropticalsatelliteimagesandrandomforestmachinelearningmodels |