A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide Mapping
The existing landslide recognition methods mainly focus on the use of spectral bands of optical remote sensing and machine learning base classifiers, which are insufficient in landslide characterization in complex scenes, resulting in a high missed and false detection of landslides. In this article,...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10824934/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540555492458496 |
|---|---|
| author | Yi He Hesheng Chen Qing Zhu Qing Zhang Lifeng Zhang Tao Liu Wende Li Huaiyuan Chen |
| author_facet | Yi He Hesheng Chen Qing Zhu Qing Zhang Lifeng Zhang Tao Liu Wende Li Huaiyuan Chen |
| author_sort | Yi He |
| collection | DOAJ |
| description | The existing landslide recognition methods mainly focus on the use of spectral bands of optical remote sensing and machine learning base classifiers, which are insufficient in landslide characterization in complex scenes, resulting in a high missed and false detection of landslides. In this article, we develop a landslide recognition framework, which combines the multidimensional feature advantages of spectral, terrain, and texture of optical satellite images, and constructs a heterogeneous ensemble learning method for landslide mapping. First, we construct a landslide multidimensional feature dataset using Sentinel-2A and Advanced Land Observing Satellite digital elevation model data. Then, we construct a heterogeneous ensemble learning landslide recognition method, which combines the advantages of fully convolutional network, U-Net, and attention U-Net base classifiers to fully learn the multidimensional features of landslides. Finally, we evaluate the performance of the landslide recognition framework in the Bailongjiang River Basin complex scenes. The experimental results show that integrating the multidimensional features of spectral, terrain, and texture and using the heterogeneous ensemble learning method can reduce the missed and false detection of landslides in complex scenes. Specifically, compared with using only spectral bands, integrating spectral bands, spectral indexes, terrain factors, and texture indexes achieves the highest Recall, Kappa, F1-score, and MIoU in testing areas, and missed alarm (MA) is reduced by 15.56%. Compared with deep learning base classifiers, the constructed heterogeneous ensemble learning demonstrates improvements in Recall ranging from 41.67% to 69.89%, and MA is reduced from 52.17% to 30.11%. This study provides a new idea for high-precision landslide recognition in complex environments. |
| format | Article |
| id | doaj-art-bd000390f7e14566a4530bb8f1e425f4 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-bd000390f7e14566a4530bb8f1e425f42025-02-05T00:00:30ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183746376510.1109/JSTARS.2025.352563310824934A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide MappingYi He0https://orcid.org/0000-0003-4017-0488Hesheng Chen1https://orcid.org/0009-0009-5894-5318Qing Zhu2Qing Zhang3https://orcid.org/0009-0005-0990-721XLifeng Zhang4https://orcid.org/0000-0001-6560-9042Tao Liu5https://orcid.org/0000-0003-0202-0032Wende Li6Huaiyuan Chen7https://orcid.org/0009-0002-9831-7374Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaSchool of Earth Science and Environmental Engineering, Southwest Jiaotong University, Chengdu, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaFaculty of Geomatics, Lanzhou Jiaotong University, Lanzhou, ChinaThe existing landslide recognition methods mainly focus on the use of spectral bands of optical remote sensing and machine learning base classifiers, which are insufficient in landslide characterization in complex scenes, resulting in a high missed and false detection of landslides. In this article, we develop a landslide recognition framework, which combines the multidimensional feature advantages of spectral, terrain, and texture of optical satellite images, and constructs a heterogeneous ensemble learning method for landslide mapping. First, we construct a landslide multidimensional feature dataset using Sentinel-2A and Advanced Land Observing Satellite digital elevation model data. Then, we construct a heterogeneous ensemble learning landslide recognition method, which combines the advantages of fully convolutional network, U-Net, and attention U-Net base classifiers to fully learn the multidimensional features of landslides. Finally, we evaluate the performance of the landslide recognition framework in the Bailongjiang River Basin complex scenes. The experimental results show that integrating the multidimensional features of spectral, terrain, and texture and using the heterogeneous ensemble learning method can reduce the missed and false detection of landslides in complex scenes. Specifically, compared with using only spectral bands, integrating spectral bands, spectral indexes, terrain factors, and texture indexes achieves the highest Recall, Kappa, F1-score, and MIoU in testing areas, and missed alarm (MA) is reduced by 15.56%. Compared with deep learning base classifiers, the constructed heterogeneous ensemble learning demonstrates improvements in Recall ranging from 41.67% to 69.89%, and MA is reduced from 52.17% to 30.11%. This study provides a new idea for high-precision landslide recognition in complex environments.https://ieeexplore.ieee.org/document/10824934/Ensemble learninglandslide detectionspectral indextexture indexU-Net |
| spellingShingle | Yi He Hesheng Chen Qing Zhu Qing Zhang Lifeng Zhang Tao Liu Wende Li Huaiyuan Chen A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide Mapping IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Ensemble learning landslide detection spectral index texture index U-Net |
| title | A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide Mapping |
| title_full | A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide Mapping |
| title_fullStr | A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide Mapping |
| title_full_unstemmed | A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide Mapping |
| title_short | A Heterogeneous Ensemble Learning Method Combining Spectral, Terrain, and Texture Features for Landslide Mapping |
| title_sort | heterogeneous ensemble learning method combining spectral terrain and texture features for landslide mapping |
| topic | Ensemble learning landslide detection spectral index texture index U-Net |
| url | https://ieeexplore.ieee.org/document/10824934/ |
| work_keys_str_mv | AT yihe aheterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT heshengchen aheterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT qingzhu aheterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT qingzhang aheterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT lifengzhang aheterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT taoliu aheterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT wendeli aheterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT huaiyuanchen aheterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT yihe heterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT heshengchen heterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT qingzhu heterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT qingzhang heterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT lifengzhang heterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT taoliu heterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT wendeli heterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping AT huaiyuanchen heterogeneousensemblelearningmethodcombiningspectralterrainandtexturefeaturesforlandslidemapping |