DOI: 10.1016/j.jag.2014.05.005
Scopus记录号: 2-s2.0-84904811239
论文题名: Automated high resolution mapping of coffee in Rwanda using an expert Bayesian network
作者: Mukashema A ; , Veldkamp A ; , Vrieling A
刊名: International Journal of Applied Earth Observation and Geoinformation
ISSN: 15698432
出版年: 2014
卷: 33, 期: 1 起始页码: 331
结束页码: 340
语种: 英语
英文关键词: Bayesian network
; Coffee
; Expert knowledge
; Remote sensing
; Rwanda
; Very high resolution imagery
Scopus关键词: aerial photography
; agricultural ecosystem
; Bayesian analysis
; coffee
; expert system
; mapping
; remote sensing
; satellite imagery
; spatial resolution
; Rwanda
英文摘要: African highland agro-ecosystems are dominated by small-scale agricultural fields that often contain amix of annual and perennial crops. This makes such systems difficult to map by remote sensing. Wedeveloped an expert Bayesian network model to extract the small-scale coffee fields of Rwanda fromvery high resolution data. The model was subsequently applied to aerial orthophotos covering more than99% of Rwanda and on one QuickBird image for the remaining part. The method consists of a stepwiseadjustment of pixel probabilities, which incorporates expert knowledge on size of coffee trees and fields,and on their location. The initial naive Bayesian network, which is a spectral-based classification, yieldeda coffee map with an overall accuracy of around 50%. This confirms that standard spectral variables alonecannot accurately identify coffee fields from high resolution images. The combination of spectral andancillary data (DEM and a forest map) allowed mapping of coffee fields and associated uncertaintieswith an overall accuracy of 87%. Aggregated to district units, the mapped coffee areas demonstrated ahigh correlation with the coffee areas reported in the detailed national coffee census of 2009 (R2= 0.92).Unlike the census data our map provides high spatial resolution of coffee area patterns of Rwanda. Theproposed method has potential for mapping other perennial small scale cropping systems in the EastAfrican Highlands and elsewhere. © 2014 Elsevier B.V. Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/79788
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: Rwanda Natural Resources Authority (RNRA), P.O. Box 433, Kigali, Rwanda; Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, P.O. Box 217, 7500 AE Enschede, Netherlands
Recommended Citation:
Mukashema A,, Veldkamp A,, Vrieling A. Automated high resolution mapping of coffee in Rwanda using an expert Bayesian network[J]. International Journal of Applied Earth Observation and Geoinformation,2014-01-01,33(1)