Bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sites
This research investigates a global approach to map bare ground across diverse geographies with an ensemble of spectral indices using optimal thresholds identified in testing to train and evaluate machine learning models to extract bare ground pixels from Sentinel-2 imagery. Twelve locations in four...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10106049.2025.2465452 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850256113668194304 |
|---|---|
| author | Sarah J. Becker Megan C. Maloney Andrew W. H. Griffin Kristofer Lasko Heather S. Sussman |
| author_facet | Sarah J. Becker Megan C. Maloney Andrew W. H. Griffin Kristofer Lasko Heather S. Sussman |
| author_sort | Sarah J. Becker |
| collection | DOAJ |
| description | This research investigates a global approach to map bare ground across diverse geographies with an ensemble of spectral indices using optimal thresholds identified in testing to train and evaluate machine learning models to extract bare ground pixels from Sentinel-2 imagery. Twelve locations in four Köppen climate zones with data from two seasons were evaluated. Accuracy assessment showed a mean F1 score of 80% and a mean Overall Accuracy (OA) of 81% for random forest and an F1 score of 78% and OA of 79% for support vector machine. Higher accuracies were observed in climate region-based models with mean F1 > = 84% in three of four climate zones. Low accuracies occurred in winter imagery with leaf-off tree cover or building materials similar to bare ground. This framework provides a global approach to map bare ground without need for high-density time-series or deep learning models and moves beyond locally effective methods. |
| format | Article |
| id | doaj-art-67729b10f2814df2a216eec93cdc8d3d |
| institution | OA Journals |
| issn | 1010-6049 1752-0762 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj-art-67729b10f2814df2a216eec93cdc8d3d2025-08-20T01:56:42ZengTaylor & Francis GroupGeocarto International1010-60491752-07622025-12-0140110.1080/10106049.2025.2465452Bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sitesSarah J. Becker0Megan C. Maloney1Andrew W. H. Griffin2Kristofer Lasko3Heather S. Sussman4Geospatial Research Laboratory, Engineering Research and Development Center, US Army Corps of Engineers, Alexandria, VA, USAGeospatial Research Laboratory, Engineering Research and Development Center, US Army Corps of Engineers, Alexandria, VA, USAGeospatial Research Laboratory, Engineering Research and Development Center, US Army Corps of Engineers, Alexandria, VA, USAGeospatial Research Laboratory, Engineering Research and Development Center, US Army Corps of Engineers, Alexandria, VA, USAGeospatial Research Laboratory, Engineering Research and Development Center, US Army Corps of Engineers, Alexandria, VA, USAThis research investigates a global approach to map bare ground across diverse geographies with an ensemble of spectral indices using optimal thresholds identified in testing to train and evaluate machine learning models to extract bare ground pixels from Sentinel-2 imagery. Twelve locations in four Köppen climate zones with data from two seasons were evaluated. Accuracy assessment showed a mean F1 score of 80% and a mean Overall Accuracy (OA) of 81% for random forest and an F1 score of 78% and OA of 79% for support vector machine. Higher accuracies were observed in climate region-based models with mean F1 > = 84% in three of four climate zones. Low accuracies occurred in winter imagery with leaf-off tree cover or building materials similar to bare ground. This framework provides a global approach to map bare ground without need for high-density time-series or deep learning models and moves beyond locally effective methods.https://www.tandfonline.com/doi/10.1080/10106049.2025.2465452Bare ground classificationrandom forestsupport vector machinespectral index thresholdstexture |
| spellingShingle | Sarah J. Becker Megan C. Maloney Andrew W. H. Griffin Kristofer Lasko Heather S. Sussman Bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sites Geocarto International Bare ground classification random forest support vector machine spectral index thresholds texture |
| title | Bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sites |
| title_full | Bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sites |
| title_fullStr | Bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sites |
| title_full_unstemmed | Bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sites |
| title_short | Bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sites |
| title_sort | bare ground classification using a spectral index ensemble and machine learning models optimized across 12 international study sites |
| topic | Bare ground classification random forest support vector machine spectral index thresholds texture |
| url | https://www.tandfonline.com/doi/10.1080/10106049.2025.2465452 |
| work_keys_str_mv | AT sarahjbecker baregroundclassificationusingaspectralindexensembleandmachinelearningmodelsoptimizedacross12internationalstudysites AT megancmaloney baregroundclassificationusingaspectralindexensembleandmachinelearningmodelsoptimizedacross12internationalstudysites AT andrewwhgriffin baregroundclassificationusingaspectralindexensembleandmachinelearningmodelsoptimizedacross12internationalstudysites AT kristoferlasko baregroundclassificationusingaspectralindexensembleandmachinelearningmodelsoptimizedacross12internationalstudysites AT heatherssussman baregroundclassificationusingaspectralindexensembleandmachinelearningmodelsoptimizedacross12internationalstudysites |