Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach
Gullies are landforms with specific patterns of shape, topography, hydrology, vegetation, and soil characteristics. Remote sensing products (TanDEM-X, Sentinel-1, and Sentinel-2) serve as inputs into an iterative algorithm, initialized using a micro-mapping simulation as training data, to map gullie...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9268451/ |
| _version_ | 1819092786009341952 |
|---|---|
| author | Miguel Vallejo Orti Lukas Winiwarter Eva Corral-Pazos-de-Provens Jack G. Williams Olaf Bubenzer Bernhard Hofle |
| author_facet | Miguel Vallejo Orti Lukas Winiwarter Eva Corral-Pazos-de-Provens Jack G. Williams Olaf Bubenzer Bernhard Hofle |
| author_sort | Miguel Vallejo Orti |
| collection | DOAJ |
| description | Gullies are landforms with specific patterns of shape, topography, hydrology, vegetation, and soil characteristics. Remote sensing products (TanDEM-X, Sentinel-1, and Sentinel-2) serve as inputs into an iterative algorithm, initialized using a micro-mapping simulation as training data, to map gullies in the northwestern of Namibia. A Random Forest Classifier examines pixels with similar characteristics in a pool of unlabeled data, and gully objects are detected where high densities of gully pixels are enclosed by an alpha shape. Gully objects are used in subsequent iterations following a mechanism where the algorithm uses the most reliable pixels as gully training samples. The gully class continuously grows until an optimal scenario in terms of accuracy is achieved. Results are benchmarked with manually tagged gullies (initial gully labeled area <; 0.3% of the total study area) in two different watersheds (408 and 302 km<sup>2</sup>, respectively) yielding total accuracies of >98%, with 60% in the gully class, Cohen Kappa >0.5, Matthews Correlation Coefficient >0.5, and receiver operating characteristic Area Under the Curve >0.89. Hence, our method outlines gullies keeping low false-positive rates while the classification quality has a good balance for the two classes (gully/no gully). Results show the most significant gully descriptors as the high temporal radar signal coherence (22.4%) and the low temporal variability in Normalized Difference Vegetation Index (21.8%). This research builds on previous studies to face the challenge of identifying and outlining gully-affected areas with a shortage of training data using global datasets, which are then transferable to other large (semi-) arid regions. |
| first_indexed | 2024-12-21T23:01:09Z |
| format | Article |
| id | doaj.art-14aad8d379764798855e4354c9f5781b |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-21T23:01:09Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-14aad8d379764798855e4354c9f5781b2022-12-21T18:47:18ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-011460762310.1109/JSTARS.2020.30402849268451Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest ApproachMiguel Vallejo Orti0https://orcid.org/0000-0002-8464-772XLukas Winiwarter1https://orcid.org/0000-0001-8229-1160Eva Corral-Pazos-de-Provens2https://orcid.org/0000-0001-5033-9879Jack G. Williams3https://orcid.org/0000-0002-3031-0769Olaf Bubenzer4https://orcid.org/0000-0002-3199-1156Bernhard Hofle5https://orcid.org/0000-0001-5849-1461Department of Geo-Spatial Sciences and Technology, Namibia University of Science and Technology, Windhoek, Namibia3D Geospatial Data Processing Group, Institute of Geography, Heidelberg University, Heidelberg, GermanyDepartamento de Ciencias Agroforestales, Universidad de Huelva, Huelva, Spain3D Geospatial Data Processing Group, Institute of Geography, Heidelberg University, Heidelberg, GermanyGeomorphology and Soil ScienceInstitute of Geography3D Geospatial Data Processing Group, Institute of Geography, Heidelberg University, Heidelberg, GermanyGullies are landforms with specific patterns of shape, topography, hydrology, vegetation, and soil characteristics. Remote sensing products (TanDEM-X, Sentinel-1, and Sentinel-2) serve as inputs into an iterative algorithm, initialized using a micro-mapping simulation as training data, to map gullies in the northwestern of Namibia. A Random Forest Classifier examines pixels with similar characteristics in a pool of unlabeled data, and gully objects are detected where high densities of gully pixels are enclosed by an alpha shape. Gully objects are used in subsequent iterations following a mechanism where the algorithm uses the most reliable pixels as gully training samples. The gully class continuously grows until an optimal scenario in terms of accuracy is achieved. Results are benchmarked with manually tagged gullies (initial gully labeled area <; 0.3% of the total study area) in two different watersheds (408 and 302 km<sup>2</sup>, respectively) yielding total accuracies of >98%, with 60% in the gully class, Cohen Kappa >0.5, Matthews Correlation Coefficient >0.5, and receiver operating characteristic Area Under the Curve >0.89. Hence, our method outlines gullies keeping low false-positive rates while the classification quality has a good balance for the two classes (gully/no gully). Results show the most significant gully descriptors as the high temporal radar signal coherence (22.4%) and the low temporal variability in Normalized Difference Vegetation Index (21.8%). This research builds on previous studies to face the challenge of identifying and outlining gully-affected areas with a shortage of training data using global datasets, which are then transferable to other large (semi-) arid regions.https://ieeexplore.ieee.org/document/9268451/Arid regionsautomatic classificationgully erosioniterative learningland degradationNamibia |
| spellingShingle | Miguel Vallejo Orti Lukas Winiwarter Eva Corral-Pazos-de-Provens Jack G. Williams Olaf Bubenzer Bernhard Hofle Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Arid regions automatic classification gully erosion iterative learning land degradation Namibia |
| title | Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach |
| title_full | Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach |
| title_fullStr | Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach |
| title_full_unstemmed | Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach |
| title_short | Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach |
| title_sort | use of tandem x and sentinel products to derive gully activity maps in kunene region namibia based on automatic iterative random forest approach |
| topic | Arid regions automatic classification gully erosion iterative learning land degradation Namibia |
| url | https://ieeexplore.ieee.org/document/9268451/ |
| work_keys_str_mv | AT miguelvallejoorti useoftandemxandsentinelproductstoderivegullyactivitymapsinkuneneregionnamibiabasedonautomaticiterativerandomforestapproach AT lukaswiniwarter useoftandemxandsentinelproductstoderivegullyactivitymapsinkuneneregionnamibiabasedonautomaticiterativerandomforestapproach AT evacorralpazosdeprovens useoftandemxandsentinelproductstoderivegullyactivitymapsinkuneneregionnamibiabasedonautomaticiterativerandomforestapproach AT jackgwilliams useoftandemxandsentinelproductstoderivegullyactivitymapsinkuneneregionnamibiabasedonautomaticiterativerandomforestapproach AT olafbubenzer useoftandemxandsentinelproductstoderivegullyactivitymapsinkuneneregionnamibiabasedonautomaticiterativerandomforestapproach AT bernhardhofle useoftandemxandsentinelproductstoderivegullyactivitymapsinkuneneregionnamibiabasedonautomaticiterativerandomforestapproach |