Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data
Wetlands are among the most important, yet in danger ecosystems and play a vital role for the well-being of humans as well as flora and fauna. Over the past few years, state-of-the-art deep learning (DL) tools have gained attention for wetland classification within the remote sensing community. Howe...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2021-10-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/15481603.2021.1965399 |
| _version_ | 1797679029087633408 |
|---|---|
| author | Ali Jamali Masoud Mahdianpari Brian Brisco Jean Granger Fariba Mohammadimanesh Bahram Salehi |
| author_facet | Ali Jamali Masoud Mahdianpari Brian Brisco Jean Granger Fariba Mohammadimanesh Bahram Salehi |
| author_sort | Ali Jamali |
| collection | DOAJ |
| description | Wetlands are among the most important, yet in danger ecosystems and play a vital role for the well-being of humans as well as flora and fauna. Over the past few years, state-of-the-art deep learning (DL) tools have gained attention for wetland classification within the remote sensing community. However, the DL methods could have complex structure and their efficiency greatly depends on the availability of a large number of training data. Inspired by DL methods, yet with less complexity, the Deep Forest (DF) classifier is an advanced tree-based deep learning tool with a great capability for several remote sensing applications. Despite the effectiveness of DF classifiers, few research studies have investigated the potential of such a powerful technique for classification of remote sensing, with no documented research for wetland classification. Accordingly, the potential of the DF algorithm for the classification of wetland complexes has been investigated in this study. In particular, three well-known classifiers, namely Extreme Gradient Boosting (XGB), Random Forest (RF), and Extra Tree (ET), were used as the tree-based classifier to build DF, for which the hyper parameter tuning is carried out to ensure the optimum classification accuracy. Three well-known tree-based classification algorithms, namely Decision Tree (DT), Conventional Random Forest (CRF), and Conventional Extreme Gradient Boosting (CXGB), as well as a Convolutional Neural Network (CNN) are used as benchmark tools to compare the results obtained from the DF classifiers for wetland mapping. The results demonstrated that the DF-XGB classifier outperforms both DF-RF and DF-ET in terms of classification accuracy albeit with a longer training time. The results also confirmed the superiority of all three DF-based classifiers compared to the CRF and DT classifiers. For example, the DF-XGB improved the F1-score by 14%, 13%, 7%, 3%, and 1% for fen, swamp, marsh, bog, and shallow water, respectively, compared to the optimized CRF. The results indicated that the DF algorithm has great capability to be applied over large areas to support regional and national wetland mapping and monitoring. |
| first_indexed | 2024-03-11T23:08:28Z |
| format | Article |
| id | doaj.art-76df226c46af4f4189dba0c2ef4783b5 |
| institution | Directory Open Access Journal |
| issn | 1548-1603 1943-7226 |
| language | English |
| last_indexed | 2024-03-11T23:08:28Z |
| publishDate | 2021-10-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj.art-76df226c46af4f4189dba0c2ef4783b52023-09-21T12:43:07ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262021-10-015871072108910.1080/15481603.2021.19653991965399Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 dataAli Jamali0Masoud Mahdianpari1Brian Brisco2Jean Granger3Fariba Mohammadimanesh4Bahram Salehi5University of KarabükMemorial University of NewfoundlandThe Canada Centre For Mapping and Earth ObservationC-coreThe Canada Centre For Mapping and Earth ObservationState University of New York College of Environmental Science and Forestry (Suny Esf)Wetlands are among the most important, yet in danger ecosystems and play a vital role for the well-being of humans as well as flora and fauna. Over the past few years, state-of-the-art deep learning (DL) tools have gained attention for wetland classification within the remote sensing community. However, the DL methods could have complex structure and their efficiency greatly depends on the availability of a large number of training data. Inspired by DL methods, yet with less complexity, the Deep Forest (DF) classifier is an advanced tree-based deep learning tool with a great capability for several remote sensing applications. Despite the effectiveness of DF classifiers, few research studies have investigated the potential of such a powerful technique for classification of remote sensing, with no documented research for wetland classification. Accordingly, the potential of the DF algorithm for the classification of wetland complexes has been investigated in this study. In particular, three well-known classifiers, namely Extreme Gradient Boosting (XGB), Random Forest (RF), and Extra Tree (ET), were used as the tree-based classifier to build DF, for which the hyper parameter tuning is carried out to ensure the optimum classification accuracy. Three well-known tree-based classification algorithms, namely Decision Tree (DT), Conventional Random Forest (CRF), and Conventional Extreme Gradient Boosting (CXGB), as well as a Convolutional Neural Network (CNN) are used as benchmark tools to compare the results obtained from the DF classifiers for wetland mapping. The results demonstrated that the DF-XGB classifier outperforms both DF-RF and DF-ET in terms of classification accuracy albeit with a longer training time. The results also confirmed the superiority of all three DF-based classifiers compared to the CRF and DT classifiers. For example, the DF-XGB improved the F1-score by 14%, 13%, 7%, 3%, and 1% for fen, swamp, marsh, bog, and shallow water, respectively, compared to the optimized CRF. The results indicated that the DF algorithm has great capability to be applied over large areas to support regional and national wetland mapping and monitoring.http://dx.doi.org/10.1080/15481603.2021.1965399deep forestwetland mappingsentinel-1sentinel-2random forestextreme gradient boostingnewfoundland |
| spellingShingle | Ali Jamali Masoud Mahdianpari Brian Brisco Jean Granger Fariba Mohammadimanesh Bahram Salehi Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data GIScience & Remote Sensing deep forest wetland mapping sentinel-1 sentinel-2 random forest extreme gradient boosting newfoundland |
| title | Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data |
| title_full | Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data |
| title_fullStr | Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data |
| title_full_unstemmed | Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data |
| title_short | Deep Forest classifier for wetland mapping using the combination of Sentinel-1 and Sentinel-2 data |
| title_sort | deep forest classifier for wetland mapping using the combination of sentinel 1 and sentinel 2 data |
| topic | deep forest wetland mapping sentinel-1 sentinel-2 random forest extreme gradient boosting newfoundland |
| url | http://dx.doi.org/10.1080/15481603.2021.1965399 |
| work_keys_str_mv | AT alijamali deepforestclassifierforwetlandmappingusingthecombinationofsentinel1andsentinel2data AT masoudmahdianpari deepforestclassifierforwetlandmappingusingthecombinationofsentinel1andsentinel2data AT brianbrisco deepforestclassifierforwetlandmappingusingthecombinationofsentinel1andsentinel2data AT jeangranger deepforestclassifierforwetlandmappingusingthecombinationofsentinel1andsentinel2data AT faribamohammadimanesh deepforestclassifierforwetlandmappingusingthecombinationofsentinel1andsentinel2data AT bahramsalehi deepforestclassifierforwetlandmappingusingthecombinationofsentinel1andsentinel2data |