Abstract
This paper presents the results of a sub-pixel classification of crop types in Bulgaria from PROBA-V 100 m normalized difference vegetation index (NDVI) time series. Two sub-pixel classification methods, artificial neural network (ANN) and support vector regression (SVR) were used where the output was a set of area fraction images (AFIs) at 100 m resolution with pixels containing estimated area fractions of each class. High-resolution maps of two test sites derived from Sentinel-2 classifications were used to obtain training data for the sub-pixel classifications. The estimated area fractions have a good correspondence with the true area fractions when aggregated to regions of 10 × 10 km2, especially when the SVR method was used. For the five dominant classes in the test sites the R2 obtained after the aggregation was 86% (winter cereals), 81% (sunflower), 92% (broad-leaved forest), 89% (maize), and 67% (grasslands) when the SVR method was used.
Highlights
One of the major benefits of low resolution sensors, such as SPOT-VEGETATION, MODIS (MODerate Resolution Imaging Spectroradiometer), and Sentinel-3, with respect to agricultural applications, is their temporal resolution, the possibility to obtain time series of vegetation indices, such as normalized difference vegetation index (NDVI), throughout the growing season of crops
Even though this study demonstrated an approach for crop mapping at national level, which was independent of existing crop type datasets, such as Integrated Administration and Control System (IACS), it did require the additional effort of collecting ground truth data in a small number of representative test sites
This study showed that the sub-pixel classification approach, used previously with 1 km SPOT-VEGETATION and other low-resolution imagery to classify crop types, was applicable to PROBA-V 100 m data as well
Summary
One of the major benefits of low resolution sensors, such as SPOT-VEGETATION, MODIS (MODerate Resolution Imaging Spectroradiometer), and Sentinel-3, with respect to agricultural applications, is their temporal resolution, the possibility to obtain (regular) time series of vegetation indices, such as normalized difference vegetation index (NDVI), throughout the growing season of crops. The applications are restricted by the coarse resolution of these sensors, and the mixture of crop types within a single pixel. To overcome this problem a variety of sub-pixel classification methods have been proposed in literature. Different methods have been proposed for deriving sub-pixel class fractions including the linear mixture model (LMM) [4], artificial neural network (ANN) [9,10,11], regression tree [5], fuzzy classification [6,12], and support vector machine (SVM) [13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
