Mapping Prosopis spp. with Landsat 8 data in arid environments: Evaluating effectiveness of different methods and temporal imagery selection for Hargeisa, Somaliland
详细信息 查看全文
- 作者：Wai-Tim Nga ; tim.ng@boku.ac.at" class="auth_mail" title="E-mail the corresponding author ; Michele Meronib ; Markus Immitzera ; Sebastian Bö ; cka ; Ugo Leonardic ; Felix Remboldb ; Hussein Gadainc ; Clement Atzbergera
- 关键词：Prosopis spp. ; Invasive species ; Random forest classifier ; OBIA
- 刊名：International Journal of Applied Earth Observation and Geoinformation
- 出版年：2016
- 出版时间：December 2016
- 年：2016
- 卷：53
- 期：Complete
- 页码：76-89
- 全文大小：11957 K
文摘
-
Successful mapping and quantification of Prosopis extent using Random Forest (RF) classifier.
-
Performing a comparative assessment of pixel- and object-based classifications.
-
Optimum mapping results are obtained by using the pixel-based approach.
-
EO acquisitions during dry periods enhance class separability.
-
Spatial resolution of Landsat is the main limiting factor for Prosopis mapping.