DocumentCode :
144363
Title :
Annual space-based crop inventory for Canada: 2009–2014
Author :
Fisette, T. ; Davidson, A. ; Daneshfar, B. ; Rollin, P. ; Aly, Z. ; Campbell, L.
Author_Institution :
Agric. & Agri-Food Canada, Ottawa, ON, Canada
fYear :
2014
fDate :
13-18 July 2014
Firstpage :
5095
Lastpage :
5098
Abstract :
Starting in 2009, Agriculture and Agri-Food Canada (AAFC) began the process of generating annual crop type digital maps using satellite imagery. Focusing on the Prairie Provinces in 2009 and 2010, a Decision Tree (DT) based methodology was applied using optical (Landsat, Resourcesat-1, DMC, SPOT) and radar (Radarsat-2) imagery. Starting with the 2011 growing season, this activity was extended to other provinces in support of a national crop inventory. Since then, AAFC has consistently delivered an annual crop inventory that is close to the overall target accuracy of 85% at the national scale. However, from one province to another, and from one year to another, the classification accuracy is not uniform. It varies depending on satellite data availability and training site distribution. In an effort to improve mapping quality, the methodology is constantly evolving and new classifiers are under investigation.
Keywords :
crops; decision trees; remote sensing; AD 2009 to 2014; Agriculture and AgriFood Canada; DMC data; Decision Tree based methodology; Landsat data; Prairie Provinces; Radarsat-2 imagery; Resourcesat-1 data; SPOT data; annual space based crop inventory; satellite imagery; Accuracy; Agriculture; Optical imaging; Optical sensors; Remote sensing; Satellites; Training; Agriculture; Classification; Land Cover; Land Use; Remote Sensing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International
Conference_Location :
Quebec City, QC
Type :
conf
DOI :
10.1109/IGARSS.2014.6947643
Filename :
6947643
Link To Document :
بازگشت