Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland
Tropical peatlands such as Ghana’s Greater Amanzule peatland are highly valuable ecosystems and under great pressure from anthropogenic land use activities. Accurate measurement of their occurrence and extent is required to facilitate sustainable management. A key challenge, however, is the high clo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/10/3399 |
| _version_ | 1797534233269370880 |
|---|---|
| author | Alex O. Amoakoh Paul Aplin Kwame T. Awuah Irene Delgado-Fernandez Cherith Moses Carolina Peña Alonso Stephen Kankam Justice C. Mensah |
| author_facet | Alex O. Amoakoh Paul Aplin Kwame T. Awuah Irene Delgado-Fernandez Cherith Moses Carolina Peña Alonso Stephen Kankam Justice C. Mensah |
| author_sort | Alex O. Amoakoh |
| collection | DOAJ |
| description | Tropical peatlands such as Ghana’s Greater Amanzule peatland are highly valuable ecosystems and under great pressure from anthropogenic land use activities. Accurate measurement of their occurrence and extent is required to facilitate sustainable management. A key challenge, however, is the high cloud cover in the tropics that limits optical remote sensing data acquisition. In this work we combine optical imagery with radar and elevation data to optimise land cover classification for the Greater Amanzule tropical peatland. Sentinel-2, Sentinel-1 and Shuttle Radar Topography Mission (SRTM) imagery were acquired and integrated to drive a machine learning land cover classification using a random forest classifier. Recursive feature elimination was used to optimize high-dimensional and correlated feature space and determine the optimal features for the classification. Six datasets were compared, comprising different combinations of optical, radar and elevation features. Results showed that the best overall accuracy (OA) was found for the integrated Sentinel-2, Sentinel-1 and SRTM dataset (S2+S1+DEM), significantly outperforming all the other classifications with an OA of 94%. Assessment of the sensitivity of land cover classes to image features indicated that elevation and the original Sentinel-1 bands contributed the most to separating tropical peatlands from other land cover types. The integration of more features and the removal of redundant features systematically increased classification accuracy. We estimate Ghana’s Greater Amanzule peatland covers 60,187 ha. Our proposed methodological framework contributes a robust workflow for accurate and detailed landscape-scale monitoring of tropical peatlands, while our findings provide timely information critical for the sustainable management of the Greater Amanzule peatland. |
| first_indexed | 2024-03-10T11:26:46Z |
| format | Article |
| id | doaj.art-536afa731b4b44e4b1a4dd545c059025 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T11:26:46Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-536afa731b4b44e4b1a4dd545c0590252023-11-21T19:33:57ZengMDPI AGSensors1424-82202021-05-012110339910.3390/s21103399Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical PeatlandAlex O. Amoakoh0Paul Aplin1Kwame T. Awuah2Irene Delgado-Fernandez3Cherith Moses4Carolina Peña Alonso5Stephen Kankam6Justice C. Mensah7Department of Geography and Geology, Edge Hill University, Ormskirk L39 4QP, UKDepartment of Geography and Geology, Edge Hill University, Ormskirk L39 4QP, UKDepartment of Geography and Geology, Edge Hill University, Ormskirk L39 4QP, UKDepartment of Geography and Geology, Edge Hill University, Ormskirk L39 4QP, UKDepartment of Geography and Geology, Edge Hill University, Ormskirk L39 4QP, UKGrupo de Geografía Física y Medio Ambiente, Department of Geography, University of Las Palmas de Gran Canaria, 35003 Las Palmas, SpainHen Mpoano (Our Coast), Takoradi WS-289-9503, GhanaHen Mpoano (Our Coast), Takoradi WS-289-9503, GhanaTropical peatlands such as Ghana’s Greater Amanzule peatland are highly valuable ecosystems and under great pressure from anthropogenic land use activities. Accurate measurement of their occurrence and extent is required to facilitate sustainable management. A key challenge, however, is the high cloud cover in the tropics that limits optical remote sensing data acquisition. In this work we combine optical imagery with radar and elevation data to optimise land cover classification for the Greater Amanzule tropical peatland. Sentinel-2, Sentinel-1 and Shuttle Radar Topography Mission (SRTM) imagery were acquired and integrated to drive a machine learning land cover classification using a random forest classifier. Recursive feature elimination was used to optimize high-dimensional and correlated feature space and determine the optimal features for the classification. Six datasets were compared, comprising different combinations of optical, radar and elevation features. Results showed that the best overall accuracy (OA) was found for the integrated Sentinel-2, Sentinel-1 and SRTM dataset (S2+S1+DEM), significantly outperforming all the other classifications with an OA of 94%. Assessment of the sensitivity of land cover classes to image features indicated that elevation and the original Sentinel-1 bands contributed the most to separating tropical peatlands from other land cover types. The integration of more features and the removal of redundant features systematically increased classification accuracy. We estimate Ghana’s Greater Amanzule peatland covers 60,187 ha. Our proposed methodological framework contributes a robust workflow for accurate and detailed landscape-scale monitoring of tropical peatlands, while our findings provide timely information critical for the sustainable management of the Greater Amanzule peatland.https://www.mdpi.com/1424-8220/21/10/3399tropical peatlandrandom forestfeature selectionclassificationSentinelGoogle Earth Engine |
| spellingShingle | Alex O. Amoakoh Paul Aplin Kwame T. Awuah Irene Delgado-Fernandez Cherith Moses Carolina Peña Alonso Stephen Kankam Justice C. Mensah Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland Sensors tropical peatland random forest feature selection classification Sentinel Google Earth Engine |
| title | Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland |
| title_full | Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland |
| title_fullStr | Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland |
| title_full_unstemmed | Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland |
| title_short | Testing the Contribution of Multi-Source Remote Sensing Features for Random Forest Classification of the Greater Amanzule Tropical Peatland |
| title_sort | testing the contribution of multi source remote sensing features for random forest classification of the greater amanzule tropical peatland |
| topic | tropical peatland random forest feature selection classification Sentinel Google Earth Engine |
| url | https://www.mdpi.com/1424-8220/21/10/3399 |
| work_keys_str_mv | AT alexoamoakoh testingthecontributionofmultisourceremotesensingfeaturesforrandomforestclassificationofthegreateramanzuletropicalpeatland AT paulaplin testingthecontributionofmultisourceremotesensingfeaturesforrandomforestclassificationofthegreateramanzuletropicalpeatland AT kwametawuah testingthecontributionofmultisourceremotesensingfeaturesforrandomforestclassificationofthegreateramanzuletropicalpeatland AT irenedelgadofernandez testingthecontributionofmultisourceremotesensingfeaturesforrandomforestclassificationofthegreateramanzuletropicalpeatland AT cherithmoses testingthecontributionofmultisourceremotesensingfeaturesforrandomforestclassificationofthegreateramanzuletropicalpeatland AT carolinapenaalonso testingthecontributionofmultisourceremotesensingfeaturesforrandomforestclassificationofthegreateramanzuletropicalpeatland AT stephenkankam testingthecontributionofmultisourceremotesensingfeaturesforrandomforestclassificationofthegreateramanzuletropicalpeatland AT justicecmensah testingthecontributionofmultisourceremotesensingfeaturesforrandomforestclassificationofthegreateramanzuletropicalpeatland |