CROP IDENTIFICATION MAPPING ON THE ARABLE TERRITORY OF BULGARIA USING MULTI-TEMPORAL 100 m PROBA-V NDVI DATA FOR 2014

The objective of this article is crop identification mapping using newly available multi-temporal 100 m PROBA-V NDVI data product for 2014, in order to evaluate suitability of the data used for crop condition assessment analysis and production based estimates for broad areas. The methodology of this article includes the following working stages: (1) Choosing PROBA-V NDVI images; (2) Applying arable land mask from CORINE 2006 land-cover database separately for north and south Bulgaria; (3) Conducting unsupervised (ISODATA) classifications with 4 classes. (4) Accuracy assessment on two selected test sites for north and south Bulgaria. The achieved crop identification accuracy reveals overall accuracy of 82.51% and Kappa statistics of 0.7710 for north Bulgaria and overall accuracy of 73.75% and Kappa statistics of 0.6648 for south Bulgaria. The PROBA-V 100m NDVI multi-temporal images shows very promising results for crop identification purposes, which is the preliminary step for crop condition assessment analysis and production based estimates for broad areas.