Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation Components
Characterizing compositional and structural aspects of vegetation is critical to effectively assessing land function. When priorities are placed on ecological integrity, remotely sensed estimates of fractional vegetation components (FVCs) are useful for measuring landscape-level habitat structure an...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/3/551 |
| _version_ | 1827659076758142976 |
|---|---|
| author | Andrea E. Gaughan Nicholas E. Kolarik Forrest R. Stevens Narcisa G. Pricope Lin Cassidy Jonathan Salerno Karen M. Bailey Michael Drake Kyle Woodward Joel Hartter |
| author_facet | Andrea E. Gaughan Nicholas E. Kolarik Forrest R. Stevens Narcisa G. Pricope Lin Cassidy Jonathan Salerno Karen M. Bailey Michael Drake Kyle Woodward Joel Hartter |
| author_sort | Andrea E. Gaughan |
| collection | DOAJ |
| description | Characterizing compositional and structural aspects of vegetation is critical to effectively assessing land function. When priorities are placed on ecological integrity, remotely sensed estimates of fractional vegetation components (FVCs) are useful for measuring landscape-level habitat structure and function. In this study, we address whether FVC estimates, stratified by dominant vegetation type, vary with different classification approaches applied to very-high-resolution small unoccupied aerial system (UAS)-derived imagery. Using Parrot Sequoia imagery, flown on a DJI Mavic Pro micro-quadcopter, we compare pixel- and segment-based random forest classifiers alongside a vegetation height-threshold model for characterizing the FVC in a southern African dryland savanna. Results show differences in agreement between each classification method, with the most disagreement in shrub-dominated sites. When compared to vegetation classes chosen by visual identification, the pixel-based random forest classifier had the highest overall agreement and was the only classifier not to differ significantly from the hand-delineated FVC estimation. However, when separating out woody biomass components of tree and shrub, the vegetation height-threshold performed better than both random-forest approaches. These findings underscore the utility and challenges represented by very-high-resolution multispectral UAS-derived data (~10 cm ground resolution) and their uses to estimate FVC. Semi-automated approaches statistically differ from by-hand estimation in most cases; however, we present insights for approaches that are applicable across varying vegetation types and structural conditions. Importantly, characterization of savanna land function cannot rely only on a “greenness” measure but also requires a structural vegetation component. Underscoring these insights is that the spatial heterogeneity of vegetation structure on the landscape broadly informs land management, from land allocation, wildlife habitat use, natural resource collection, and as an indicator of overall ecosystem function. |
| first_indexed | 2024-03-09T23:13:32Z |
| format | Article |
| id | doaj.art-43df7f4bff95474390cb729308d65f20 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T23:13:32Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-43df7f4bff95474390cb729308d65f202023-11-23T17:39:33ZengMDPI AGRemote Sensing2072-42922022-01-0114355110.3390/rs14030551Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation ComponentsAndrea E. Gaughan0Nicholas E. Kolarik1Forrest R. Stevens2Narcisa G. Pricope3Lin Cassidy4Jonathan Salerno5Karen M. Bailey6Michael Drake7Kyle Woodward8Joel Hartter9Department of Geographic and Environmental Sciences, University of Louisville, Louisville, KY 40292, USAHuman-Environment Systems Research Center, Boise State University, 1910 University Dr., Boise, ID 83725, USADepartment of Geographic and Environmental Sciences, University of Louisville, Louisville, KY 40292, USADepartment of Earth and Ocean Sciences, University of North Carolina Wilmington, Wilmington, NC 28403, USAOkavango Research Institute, University of Botswana, Private Bag, Maun 285, BotswanaDepartment of Human Dimensions of Natural Resources, Graduate Degree Program in Ecology, Colorado State University, Fort Collins, CO 80523, USADepartment of Environmental Studies, University of Colorado Boulder, Boulder, CO 80303, USADepartment of Environmental Studies, University of Colorado Boulder, Boulder, CO 80303, USADepartment of Earth and Ocean Sciences, University of North Carolina Wilmington, Wilmington, NC 28403, USADepartment of Environmental Studies, University of Colorado Boulder, Boulder, CO 80303, USACharacterizing compositional and structural aspects of vegetation is critical to effectively assessing land function. When priorities are placed on ecological integrity, remotely sensed estimates of fractional vegetation components (FVCs) are useful for measuring landscape-level habitat structure and function. In this study, we address whether FVC estimates, stratified by dominant vegetation type, vary with different classification approaches applied to very-high-resolution small unoccupied aerial system (UAS)-derived imagery. Using Parrot Sequoia imagery, flown on a DJI Mavic Pro micro-quadcopter, we compare pixel- and segment-based random forest classifiers alongside a vegetation height-threshold model for characterizing the FVC in a southern African dryland savanna. Results show differences in agreement between each classification method, with the most disagreement in shrub-dominated sites. When compared to vegetation classes chosen by visual identification, the pixel-based random forest classifier had the highest overall agreement and was the only classifier not to differ significantly from the hand-delineated FVC estimation. However, when separating out woody biomass components of tree and shrub, the vegetation height-threshold performed better than both random-forest approaches. These findings underscore the utility and challenges represented by very-high-resolution multispectral UAS-derived data (~10 cm ground resolution) and their uses to estimate FVC. Semi-automated approaches statistically differ from by-hand estimation in most cases; however, we present insights for approaches that are applicable across varying vegetation types and structural conditions. Importantly, characterization of savanna land function cannot rely only on a “greenness” measure but also requires a structural vegetation component. Underscoring these insights is that the spatial heterogeneity of vegetation structure on the landscape broadly informs land management, from land allocation, wildlife habitat use, natural resource collection, and as an indicator of overall ecosystem function.https://www.mdpi.com/2072-4292/14/3/551savannasvegetation compositionAfricarandom forest classifiervegetation structureunoccupied aerial systems |
| spellingShingle | Andrea E. Gaughan Nicholas E. Kolarik Forrest R. Stevens Narcisa G. Pricope Lin Cassidy Jonathan Salerno Karen M. Bailey Michael Drake Kyle Woodward Joel Hartter Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation Components Remote Sensing savannas vegetation composition Africa random forest classifier vegetation structure unoccupied aerial systems |
| title | Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation Components |
| title_full | Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation Components |
| title_fullStr | Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation Components |
| title_full_unstemmed | Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation Components |
| title_short | Using Very-High-Resolution Multispectral Classification to Estimate Savanna Fractional Vegetation Components |
| title_sort | using very high resolution multispectral classification to estimate savanna fractional vegetation components |
| topic | savannas vegetation composition Africa random forest classifier vegetation structure unoccupied aerial systems |
| url | https://www.mdpi.com/2072-4292/14/3/551 |
| work_keys_str_mv | AT andreaegaughan usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT nicholasekolarik usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT forrestrstevens usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT narcisagpricope usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT lincassidy usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT jonathansalerno usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT karenmbailey usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT michaeldrake usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT kylewoodward usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents AT joelhartter usingveryhighresolutionmultispectralclassificationtoestimatesavannafractionalvegetationcomponents |