Methodology For Extracting Poplar Planted Fields From Very High-Resolution Imagery Using Object-Based Image Analysis and Feature Selection Strategy
Poplars (<em>Populus</em> sp.), a tree that grows rapidly species, are significant as industrial forest products. The delineation and monitoring of poplar cultivated areas are invaluable for decision-making processes. With the remote sensing technology, accurate detection of poplar plant...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2024-11-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-annals.copernicus.org/articles/X-5-2024/259/2024/isprs-annals-X-5-2024-259-2024.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846168773041586176 |
|---|---|
| author | E. O. Yilmaz T. Kavzoglu I. Colkesen H. Tonbul A. Teke |
| author_facet | E. O. Yilmaz T. Kavzoglu I. Colkesen H. Tonbul A. Teke |
| author_sort | E. O. Yilmaz |
| collection | DOAJ |
| description | Poplars (<em>Populus</em> sp.), a tree that grows rapidly species, are significant as industrial forest products. The delineation and monitoring of poplar cultivated areas are invaluable for decision-making processes. With the remote sensing technology, accurate detection of poplar planted areas could be determined much faster, more economically, and with minimum labor requirements. The objective of this research is to create a map of poplar plantations in the Sakarya region of Turkey utilizing Worldview-3 satellite imagery. Object-based image analysis (OBIA) through the application of the multi-resolution segmentation method (MRS) was employed to generate image segments, and then three prevailing machine learning algorithms, namely Support Vector Machine (SVM), Random Forest (RF) and Rotation Forest (RotFor) were implemented to produce LULC maps of the study area including 11 landscape features. The most effective and contributing object features that assure high separability between landscape features were determined using a filter-based Chi-square algorithm for the prediction models constructed with SVM, RF, and RotFor classifiers. Results revealed that the SVM classifier achieved the highest overall accuracy (91.73%) with 38 features out of 88 features, about 3% improvement compared to the other algorithms. According to the SHAP analysis, the IHS feature was the most effective one in the constructed RF model, followed by the CI (red edge), NDVI-1 and NDVI-2 vegetation indices. |
| format | Article |
| id | doaj-art-307de0705bf54bd697706c60e08e4aad |
| institution | Kabale University |
| issn | 2194-9042 2194-9050 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj-art-307de0705bf54bd697706c60e08e4aad2024-11-13T11:41:08ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502024-11-01X-5-202425926510.5194/isprs-annals-X-5-2024-259-2024Methodology For Extracting Poplar Planted Fields From Very High-Resolution Imagery Using Object-Based Image Analysis and Feature Selection StrategyE. O. Yilmaz0T. Kavzoglu1I. Colkesen2H. Tonbul3A. Teke4Dept. of Geomatic Engineering, Gebze Technical University, 41400, Gebze/Kocaeli, TürkiyeDept. of Geomatic Engineering, Gebze Technical University, 41400, Gebze/Kocaeli, TürkiyeDept. of Geomatic Engineering, Gebze Technical University, 41400, Gebze/Kocaeli, TürkiyeDept. of Geomatic Engineering, Gebze Technical University, 41400, Gebze/Kocaeli, TürkiyeDept. of Geomatic Engineering, Gebze Technical University, 41400, Gebze/Kocaeli, TürkiyePoplars (<em>Populus</em> sp.), a tree that grows rapidly species, are significant as industrial forest products. The delineation and monitoring of poplar cultivated areas are invaluable for decision-making processes. With the remote sensing technology, accurate detection of poplar planted areas could be determined much faster, more economically, and with minimum labor requirements. The objective of this research is to create a map of poplar plantations in the Sakarya region of Turkey utilizing Worldview-3 satellite imagery. Object-based image analysis (OBIA) through the application of the multi-resolution segmentation method (MRS) was employed to generate image segments, and then three prevailing machine learning algorithms, namely Support Vector Machine (SVM), Random Forest (RF) and Rotation Forest (RotFor) were implemented to produce LULC maps of the study area including 11 landscape features. The most effective and contributing object features that assure high separability between landscape features were determined using a filter-based Chi-square algorithm for the prediction models constructed with SVM, RF, and RotFor classifiers. Results revealed that the SVM classifier achieved the highest overall accuracy (91.73%) with 38 features out of 88 features, about 3% improvement compared to the other algorithms. According to the SHAP analysis, the IHS feature was the most effective one in the constructed RF model, followed by the CI (red edge), NDVI-1 and NDVI-2 vegetation indices.https://isprs-annals.copernicus.org/articles/X-5-2024/259/2024/isprs-annals-X-5-2024-259-2024.pdf |
| spellingShingle | E. O. Yilmaz T. Kavzoglu I. Colkesen H. Tonbul A. Teke Methodology For Extracting Poplar Planted Fields From Very High-Resolution Imagery Using Object-Based Image Analysis and Feature Selection Strategy ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | Methodology For Extracting Poplar Planted Fields From Very High-Resolution Imagery Using Object-Based Image Analysis and Feature Selection Strategy |
| title_full | Methodology For Extracting Poplar Planted Fields From Very High-Resolution Imagery Using Object-Based Image Analysis and Feature Selection Strategy |
| title_fullStr | Methodology For Extracting Poplar Planted Fields From Very High-Resolution Imagery Using Object-Based Image Analysis and Feature Selection Strategy |
| title_full_unstemmed | Methodology For Extracting Poplar Planted Fields From Very High-Resolution Imagery Using Object-Based Image Analysis and Feature Selection Strategy |
| title_short | Methodology For Extracting Poplar Planted Fields From Very High-Resolution Imagery Using Object-Based Image Analysis and Feature Selection Strategy |
| title_sort | methodology for extracting poplar planted fields from very high resolution imagery using object based image analysis and feature selection strategy |
| url | https://isprs-annals.copernicus.org/articles/X-5-2024/259/2024/isprs-annals-X-5-2024-259-2024.pdf |
| work_keys_str_mv | AT eoyilmaz methodologyforextractingpoplarplantedfieldsfromveryhighresolutionimageryusingobjectbasedimageanalysisandfeatureselectionstrategy AT tkavzoglu methodologyforextractingpoplarplantedfieldsfromveryhighresolutionimageryusingobjectbasedimageanalysisandfeatureselectionstrategy AT icolkesen methodologyforextractingpoplarplantedfieldsfromveryhighresolutionimageryusingobjectbasedimageanalysisandfeatureselectionstrategy AT htonbul methodologyforextractingpoplarplantedfieldsfromveryhighresolutionimageryusingobjectbasedimageanalysisandfeatureselectionstrategy AT ateke methodologyforextractingpoplarplantedfieldsfromveryhighresolutionimageryusingobjectbasedimageanalysisandfeatureselectionstrategy |