Assessing the accuracy for area-based tree species classification using Sentinel-1 C-band SAR data
Forest type (FTY) and tree species classification (SPP) over the Remn-ingstorp test site were performed using ground-based field observations and remote sensing data sources. The field inventory for the forest estate and for the surrounding natural reserve of Eahagen was carried out in 2016. The re-...
| Autor principal: | |
|---|---|
| Formato: | H2 |
| Lenguaje: | Inglés |
| Publicado: |
SLU/Dept. of Forest Resource Management
2019
|
| Materias: |
| _version_ | 1855572546706997248 |
|---|---|
| author | Udali, Alberto |
| author_browse | Udali, Alberto |
| author_facet | Udali, Alberto |
| author_sort | Udali, Alberto |
| collection | Epsilon Archive for Student Projects |
| description | Forest type (FTY) and tree species classification (SPP) over the Remn-ingstorp test site were performed using ground-based field observations and remote sensing data sources. The field inventory for the forest estate and for the surrounding natural reserve of Eahagen was carried out in 2016. The re-mote sensing data used were C-band Synthetic Aperture Radar (SAR) data from Sentinel-1. Dual polarization backscatter values were extracted for the period October 2017 - February 2019 and the area-based method was applied. The metrics obtained, i.e. monthly mean backscatter, were used to perform classification by machine learning models’ random forest (RF) and linear dis-criminant analysis (LDA). The models were evaluated with the leave-one-out cross-validation method and the classification outcomes were compared with reference values in terms of confusion matrixes. The best performing model was LDA with an overall accuracy of 88% for FTY and 61% for SPP, whereas RF achieved values of 84% for FTY and 56% for SPP. It was concluded that C-band SAR data can be used for FTY and SPP classification, but further investigation is needed to determine which factors affect the backscatter in order to obtain more accurate classifications. |
| format | H2 |
| id | RepoSLU15246 |
| institution | Swedish University of Agricultural Sciences |
| language | Inglés |
| publishDate | 2019 |
| publishDateSort | 2019 |
| publisher | SLU/Dept. of Forest Resource Management |
| publisherStr | SLU/Dept. of Forest Resource Management |
| record_format | eprints |
| spelling | RepoSLU152462020-06-04T12:30:21Z Assessing the accuracy for area-based tree species classification using Sentinel-1 C-band SAR data Udali, Alberto Sentinel-1 tree species random forest linear discrimi-nant analysis classification Forest type (FTY) and tree species classification (SPP) over the Remn-ingstorp test site were performed using ground-based field observations and remote sensing data sources. The field inventory for the forest estate and for the surrounding natural reserve of Eahagen was carried out in 2016. The re-mote sensing data used were C-band Synthetic Aperture Radar (SAR) data from Sentinel-1. Dual polarization backscatter values were extracted for the period October 2017 - February 2019 and the area-based method was applied. The metrics obtained, i.e. monthly mean backscatter, were used to perform classification by machine learning models’ random forest (RF) and linear dis-criminant analysis (LDA). The models were evaluated with the leave-one-out cross-validation method and the classification outcomes were compared with reference values in terms of confusion matrixes. The best performing model was LDA with an overall accuracy of 88% for FTY and 61% for SPP, whereas RF achieved values of 84% for FTY and 56% for SPP. It was concluded that C-band SAR data can be used for FTY and SPP classification, but further investigation is needed to determine which factors affect the backscatter in order to obtain more accurate classifications. SLU/Dept. of Forest Resource Management 2019 H2 eng https://stud.epsilon.slu.se/15246/ |
| spellingShingle | Sentinel-1 tree species random forest linear discrimi-nant analysis classification Udali, Alberto Assessing the accuracy for area-based tree species classification using Sentinel-1 C-band SAR data |
| title | Assessing the accuracy for area-based tree species classification using Sentinel-1 C-band SAR data |
| title_full | Assessing the accuracy for area-based tree species classification using Sentinel-1 C-band SAR data |
| title_fullStr | Assessing the accuracy for area-based tree species classification using Sentinel-1 C-band SAR data |
| title_full_unstemmed | Assessing the accuracy for area-based tree species classification using Sentinel-1 C-band SAR data |
| title_short | Assessing the accuracy for area-based tree species classification using Sentinel-1 C-band SAR data |
| title_sort | assessing the accuracy for area-based tree species classification using sentinel-1 c-band sar data |
| topic | Sentinel-1 tree species random forest linear discrimi-nant analysis classification |