Mapping Growing Stem Volume Using Dual-Polarization GaoFen-3 SAR Images in Evergreen Coniferous Forests
Unaffected by cloud cover and solar illumination, synthetic aperture radar (SAR) images have great capability to map forest growing stem volume (GSV) in complex biophysical environments. Up to now, c-band dual-polarization Gaofen-3 (GF-3) SAR images, acquired by the first Chinese civilian satellite...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/9/2253 |
| _version_ | 1797601829678219264 |
|---|---|
| author | Zilin Ye Jiangping Long Huanna Zheng Zhaohua Liu Tingchen Zhang Qingyang Wang |
| author_facet | Zilin Ye Jiangping Long Huanna Zheng Zhaohua Liu Tingchen Zhang Qingyang Wang |
| author_sort | Zilin Ye |
| collection | DOAJ |
| description | Unaffected by cloud cover and solar illumination, synthetic aperture radar (SAR) images have great capability to map forest growing stem volume (GSV) in complex biophysical environments. Up to now, c-band dual-polarization Gaofen-3 (GF-3) SAR images, acquired by the first Chinese civilian satellite equipped with multi-polarized modes, are rarely applied in mapping forest GSV. To evaluate the capability of dual-polarization GF-3 SAR images in mapping forest GSV, several proposed derived features were initially extracted by mathematical operations and applied to obtain optimal feature sets by different feature sorting methods and feature selection methods. Then, the maps of GSV in an evergreen coniferous forest were inverted by various machine learning algorithms and stacking ensemble learning methods with different strategies. The results implied that backscattering coefficients and partially proposed derived features showed high sensitivity to the forest GSV, and the saturation phenomenon also obviously occurred once the forest GSV was larger than 300 m<sup>3</sup>/ha. Furthermore, the results showed that the accuracy of the mapped GSV was significantly improved using the stacking ensemble learning methods. Using various optimal feature sets and base models (MLR, KNN, SVM, and RF), the rRMSE values mainly ranged from 30% to 40%. After using the stacking ensemble learning methods, the values of rRMSE ranged from 16.71% to 20.51%. This confirmed that dual-polarization GF-3 images have great potential to map forest GSV in evergreen coniferous forests. |
| first_indexed | 2024-03-11T04:08:14Z |
| format | Article |
| id | doaj.art-acacee6c9be246e9ad10a6c66b343474 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:08:14Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-acacee6c9be246e9ad10a6c66b3434742023-11-17T23:37:37ZengMDPI AGRemote Sensing2072-42922023-04-01159225310.3390/rs15092253Mapping Growing Stem Volume Using Dual-Polarization GaoFen-3 SAR Images in Evergreen Coniferous ForestsZilin Ye0Jiangping Long1Huanna Zheng2Zhaohua Liu3Tingchen Zhang4Qingyang Wang5Research Center of Forestry Remote Sensing & Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaResearch Center of Forestry Remote Sensing & Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaResearch Center of Forestry Remote Sensing & Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaResearch Center of Forestry Remote Sensing & Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaResearch Center of Forestry Remote Sensing & Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, ChinaUnaffected by cloud cover and solar illumination, synthetic aperture radar (SAR) images have great capability to map forest growing stem volume (GSV) in complex biophysical environments. Up to now, c-band dual-polarization Gaofen-3 (GF-3) SAR images, acquired by the first Chinese civilian satellite equipped with multi-polarized modes, are rarely applied in mapping forest GSV. To evaluate the capability of dual-polarization GF-3 SAR images in mapping forest GSV, several proposed derived features were initially extracted by mathematical operations and applied to obtain optimal feature sets by different feature sorting methods and feature selection methods. Then, the maps of GSV in an evergreen coniferous forest were inverted by various machine learning algorithms and stacking ensemble learning methods with different strategies. The results implied that backscattering coefficients and partially proposed derived features showed high sensitivity to the forest GSV, and the saturation phenomenon also obviously occurred once the forest GSV was larger than 300 m<sup>3</sup>/ha. Furthermore, the results showed that the accuracy of the mapped GSV was significantly improved using the stacking ensemble learning methods. Using various optimal feature sets and base models (MLR, KNN, SVM, and RF), the rRMSE values mainly ranged from 30% to 40%. After using the stacking ensemble learning methods, the values of rRMSE ranged from 16.71% to 20.51%. This confirmed that dual-polarization GF-3 images have great potential to map forest GSV in evergreen coniferous forests.https://www.mdpi.com/2072-4292/15/9/2253growing stem volumeGaofen-3dual-polarization SARfeature selectionensemble learningevergreen coniferous forest |
| spellingShingle | Zilin Ye Jiangping Long Huanna Zheng Zhaohua Liu Tingchen Zhang Qingyang Wang Mapping Growing Stem Volume Using Dual-Polarization GaoFen-3 SAR Images in Evergreen Coniferous Forests Remote Sensing growing stem volume Gaofen-3 dual-polarization SAR feature selection ensemble learning evergreen coniferous forest |
| title | Mapping Growing Stem Volume Using Dual-Polarization GaoFen-3 SAR Images in Evergreen Coniferous Forests |
| title_full | Mapping Growing Stem Volume Using Dual-Polarization GaoFen-3 SAR Images in Evergreen Coniferous Forests |
| title_fullStr | Mapping Growing Stem Volume Using Dual-Polarization GaoFen-3 SAR Images in Evergreen Coniferous Forests |
| title_full_unstemmed | Mapping Growing Stem Volume Using Dual-Polarization GaoFen-3 SAR Images in Evergreen Coniferous Forests |
| title_short | Mapping Growing Stem Volume Using Dual-Polarization GaoFen-3 SAR Images in Evergreen Coniferous Forests |
| title_sort | mapping growing stem volume using dual polarization gaofen 3 sar images in evergreen coniferous forests |
| topic | growing stem volume Gaofen-3 dual-polarization SAR feature selection ensemble learning evergreen coniferous forest |
| url | https://www.mdpi.com/2072-4292/15/9/2253 |
| work_keys_str_mv | AT zilinye mappinggrowingstemvolumeusingdualpolarizationgaofen3sarimagesinevergreenconiferousforests AT jiangpinglong mappinggrowingstemvolumeusingdualpolarizationgaofen3sarimagesinevergreenconiferousforests AT huannazheng mappinggrowingstemvolumeusingdualpolarizationgaofen3sarimagesinevergreenconiferousforests AT zhaohualiu mappinggrowingstemvolumeusingdualpolarizationgaofen3sarimagesinevergreenconiferousforests AT tingchenzhang mappinggrowingstemvolumeusingdualpolarizationgaofen3sarimagesinevergreenconiferousforests AT qingyangwang mappinggrowingstemvolumeusingdualpolarizationgaofen3sarimagesinevergreenconiferousforests |