More Than Meets the Eye: Using Sentinel-2 to Map Small Plantations in Complex Forest Landscapes
Many tropical forest landscapes are now complex mosaics of intact forests, recovering forests, tree crops, agroforestry, pasture, and crops. The small patch size of each land cover type contributes to making them difficult to separate using satellite remote sensing data. We used Sentinel-2 data to c...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/10/11/1693 |
id |
doaj-1c18eddb90904f709aa4503fbcd123c0 |
---|---|
record_format |
Article |
spelling |
doaj-1c18eddb90904f709aa4503fbcd123c02020-11-24T22:58:49ZengMDPI AGRemote Sensing2072-42922018-10-011011169310.3390/rs10111693rs10111693More Than Meets the Eye: Using Sentinel-2 to Map Small Plantations in Complex Forest LandscapesKeiko Nomura0Edward T. A. Mitchard1School of GeoSciences, Crew Building, The King’s Buildings, University of Edinburgh, Edinburgh EH9 3FF, UKSchool of GeoSciences, Crew Building, The King’s Buildings, University of Edinburgh, Edinburgh EH9 3FF, UKMany tropical forest landscapes are now complex mosaics of intact forests, recovering forests, tree crops, agroforestry, pasture, and crops. The small patch size of each land cover type contributes to making them difficult to separate using satellite remote sensing data. We used Sentinel-2 data to conduct supervised classifications covering seven classes, including oil palm, rubber, and betel nut plantations in Southern Myanmar, based on an extensive training dataset derived from expert interpretation of WorldView-3 and UAV data. We used a Random Forest classifier with all 13 Sentinel-2 bands, as well as vegetation and texture indices, over an area of 13,330 ha. The median overall accuracy of 1000 iterations was >95% (95.5%⁻96.0%) against independent test data, even though the tree crop classes appear visually very similar at a 20 m resolution. We conclude that the Sentinel-2 data, which are freely available with very frequent (five day) revisits, are able to differentiate these similar tree crop types. We suspect that this is due to the large number of spectral bands in Sentinel-2 data, indicating great potential for the wider application of Sentinel-2 data for the classification of small land parcels without needing to resort to object-based classification of higher resolution data.https://www.mdpi.com/2072-4292/10/11/1693classificationUAVWorldViewSentinel-2palm oilRandom ForestMyanmarGoogle Earth Enginerubberbetel nut |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Keiko Nomura Edward T. A. Mitchard |
spellingShingle |
Keiko Nomura Edward T. A. Mitchard More Than Meets the Eye: Using Sentinel-2 to Map Small Plantations in Complex Forest Landscapes Remote Sensing classification UAV WorldView Sentinel-2 palm oil Random Forest Myanmar Google Earth Engine rubber betel nut |
author_facet |
Keiko Nomura Edward T. A. Mitchard |
author_sort |
Keiko Nomura |
title |
More Than Meets the Eye: Using Sentinel-2 to Map Small Plantations in Complex Forest Landscapes |
title_short |
More Than Meets the Eye: Using Sentinel-2 to Map Small Plantations in Complex Forest Landscapes |
title_full |
More Than Meets the Eye: Using Sentinel-2 to Map Small Plantations in Complex Forest Landscapes |
title_fullStr |
More Than Meets the Eye: Using Sentinel-2 to Map Small Plantations in Complex Forest Landscapes |
title_full_unstemmed |
More Than Meets the Eye: Using Sentinel-2 to Map Small Plantations in Complex Forest Landscapes |
title_sort |
more than meets the eye: using sentinel-2 to map small plantations in complex forest landscapes |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2018-10-01 |
description |
Many tropical forest landscapes are now complex mosaics of intact forests, recovering forests, tree crops, agroforestry, pasture, and crops. The small patch size of each land cover type contributes to making them difficult to separate using satellite remote sensing data. We used Sentinel-2 data to conduct supervised classifications covering seven classes, including oil palm, rubber, and betel nut plantations in Southern Myanmar, based on an extensive training dataset derived from expert interpretation of WorldView-3 and UAV data. We used a Random Forest classifier with all 13 Sentinel-2 bands, as well as vegetation and texture indices, over an area of 13,330 ha. The median overall accuracy of 1000 iterations was >95% (95.5%⁻96.0%) against independent test data, even though the tree crop classes appear visually very similar at a 20 m resolution. We conclude that the Sentinel-2 data, which are freely available with very frequent (five day) revisits, are able to differentiate these similar tree crop types. We suspect that this is due to the large number of spectral bands in Sentinel-2 data, indicating great potential for the wider application of Sentinel-2 data for the classification of small land parcels without needing to resort to object-based classification of higher resolution data. |
topic |
classification UAV WorldView Sentinel-2 palm oil Random Forest Myanmar Google Earth Engine rubber betel nut |
url |
https://www.mdpi.com/2072-4292/10/11/1693 |
work_keys_str_mv |
AT keikonomura morethanmeetstheeyeusingsentinel2tomapsmallplantationsincomplexforestlandscapes AT edwardtamitchard morethanmeetstheeyeusingsentinel2tomapsmallplantationsincomplexforestlandscapes |
_version_ |
1725646324738555904 |