Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms
The importance of land use and cover change (LUCC) has gradually attracted more attention due to its influence on the climate and ecosystem. Consequently, the necessity of accurate LUCC mapping has become increasingly apparent. Over the past decades, although a large number of machine learning algor...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-06-01
|
| Series: | Global Ecology and Conservation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2351989420300202 |
| _version_ | 1818325536360890368 |
|---|---|
| author | Genbatu Ge Zhongjie Shi Yuanjun Zhu Xiaohui Yang Yuguang Hao |
| author_facet | Genbatu Ge Zhongjie Shi Yuanjun Zhu Xiaohui Yang Yuguang Hao |
| author_sort | Genbatu Ge |
| collection | DOAJ |
| description | The importance of land use and cover change (LUCC) has gradually attracted more attention due to its influence on the climate and ecosystem. Consequently, the necessity of accurate LUCC mapping has become increasingly apparent. Over the past decades, although a large number of machine learning algorithms have been developed to improve the accuracy and reliability of remote sensing image classification, especially for LUCC classification, there is a lack of studies that assess the performance of machine learning algorithms in arid desert-oasis mosaic landscapes. In this study, the main objective is to provide a reference for the extraction of LUCC information in dryland regions with oasis-desert mosaic landscapes by comparing the performances of the k-nearest neighbor (KNN), random forest (RF), support vector machine (SVM) and artificial neural network (ANN) for the LUCC classification of the Dengkou Oasis, China. Landsat-8 Operational Land Imager (OLI) image data were used with spectral indices and auxiliary variables that were derived from a digital terrain model to classify 7 different land cover categories. The highest overall accuracy was produced by the ANN (97.16%), which was closely followed by the RF (96.92%), SVM (96.20%), and finally KNN (93.98%); statistically similar accuracies were obtained for the ANN, SVM and RF. The RF algorithm performed well across several aspects, such as stability, ease of use and processing time during the parameter tuning. Overall, the random forest algorithm is a good first choice method for land-cover classification in this study area, and the elevation and some spectral indices, such as the NDVI, MSAVI2 and MNDWI, should be used as variables to improve the overall accuracy. |
| first_indexed | 2024-12-13T11:46:02Z |
| format | Article |
| id | doaj.art-facab9c95c584749b31608a80788e776 |
| institution | Directory Open Access Journal |
| issn | 2351-9894 |
| language | English |
| last_indexed | 2024-12-13T11:46:02Z |
| publishDate | 2020-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Global Ecology and Conservation |
| spelling | doaj.art-facab9c95c584749b31608a80788e7762022-12-21T23:47:30ZengElsevierGlobal Ecology and Conservation2351-98942020-06-0122Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithmsGenbatu Ge0Zhongjie Shi1Yuanjun Zhu2Xiaohui Yang3Yuguang Hao4Institute of Desertification Studies, Chinese Academy of Forestry, Beijing, 100091, China; Experimental Center for Desert Forestry, Chinese Academy of Forestry, Dengkou, 015200, Inner Mongolia, China; Dengkou Desert Ecosystem Research Station, State Forestry Administration, Dengkou, 015200, ChinaInstitute of Desertification Studies, Chinese Academy of Forestry, Beijing, 100091, ChinaInstitute of Desertification Studies, Chinese Academy of Forestry, Beijing, 100091, ChinaInstitute of Desertification Studies, Chinese Academy of Forestry, Beijing, 100091, China; Dengkou Desert Ecosystem Research Station, State Forestry Administration, Dengkou, 015200, China; Corresponding author. Institute of Desertification Studies, Chinese Academy of Forestry, Beijing, 100091, China.Experimental Center for Desert Forestry, Chinese Academy of Forestry, Dengkou, 015200, Inner Mongolia, China; Dengkou Desert Ecosystem Research Station, State Forestry Administration, Dengkou, 015200, China; Corresponding author. Experimental Center for Desert Forestry, Chinese Academy of Forestry, Dengkou, 015200, Inner Mongolia, China.The importance of land use and cover change (LUCC) has gradually attracted more attention due to its influence on the climate and ecosystem. Consequently, the necessity of accurate LUCC mapping has become increasingly apparent. Over the past decades, although a large number of machine learning algorithms have been developed to improve the accuracy and reliability of remote sensing image classification, especially for LUCC classification, there is a lack of studies that assess the performance of machine learning algorithms in arid desert-oasis mosaic landscapes. In this study, the main objective is to provide a reference for the extraction of LUCC information in dryland regions with oasis-desert mosaic landscapes by comparing the performances of the k-nearest neighbor (KNN), random forest (RF), support vector machine (SVM) and artificial neural network (ANN) for the LUCC classification of the Dengkou Oasis, China. Landsat-8 Operational Land Imager (OLI) image data were used with spectral indices and auxiliary variables that were derived from a digital terrain model to classify 7 different land cover categories. The highest overall accuracy was produced by the ANN (97.16%), which was closely followed by the RF (96.92%), SVM (96.20%), and finally KNN (93.98%); statistically similar accuracies were obtained for the ANN, SVM and RF. The RF algorithm performed well across several aspects, such as stability, ease of use and processing time during the parameter tuning. Overall, the random forest algorithm is a good first choice method for land-cover classification in this study area, and the elevation and some spectral indices, such as the NDVI, MSAVI2 and MNDWI, should be used as variables to improve the overall accuracy.http://www.sciencedirect.com/science/article/pii/S2351989420300202Land use/cover changeMachine learning algorithmsArid areaDesert-oasis mosaic landscape |
| spellingShingle | Genbatu Ge Zhongjie Shi Yuanjun Zhu Xiaohui Yang Yuguang Hao Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms Global Ecology and Conservation Land use/cover change Machine learning algorithms Arid area Desert-oasis mosaic landscape |
| title | Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms |
| title_full | Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms |
| title_fullStr | Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms |
| title_full_unstemmed | Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms |
| title_short | Land use/cover classification in an arid desert-oasis mosaic landscape of China using remote sensed imagery: Performance assessment of four machine learning algorithms |
| title_sort | land use cover classification in an arid desert oasis mosaic landscape of china using remote sensed imagery performance assessment of four machine learning algorithms |
| topic | Land use/cover change Machine learning algorithms Arid area Desert-oasis mosaic landscape |
| url | http://www.sciencedirect.com/science/article/pii/S2351989420300202 |
| work_keys_str_mv | AT genbatuge landusecoverclassificationinanariddesertoasismosaiclandscapeofchinausingremotesensedimageryperformanceassessmentoffourmachinelearningalgorithms AT zhongjieshi landusecoverclassificationinanariddesertoasismosaiclandscapeofchinausingremotesensedimageryperformanceassessmentoffourmachinelearningalgorithms AT yuanjunzhu landusecoverclassificationinanariddesertoasismosaiclandscapeofchinausingremotesensedimageryperformanceassessmentoffourmachinelearningalgorithms AT xiaohuiyang landusecoverclassificationinanariddesertoasismosaiclandscapeofchinausingremotesensedimageryperformanceassessmentoffourmachinelearningalgorithms AT yuguanghao landusecoverclassificationinanariddesertoasismosaiclandscapeofchinausingremotesensedimageryperformanceassessmentoffourmachinelearningalgorithms |