Crop area estimation in Ukraine using satellite data within the MARS project

In the paper we describe the results of a pilot project on crop area estimation with satellite images in Ukraine. The best results were obtained with MLP classifiers and TM images that demonstrated to give a cost-efficient contribution to the improvement of the estimators. MODIS images also demonstrated to be cost-efficient. This study provided useful insights in the framework of Geoland2-Crop CIS and updates the conclusions of the MARS project in the mid 90’s: at that time the approach had proved to be technically solid, but did not reach the cost-efficiency threshold with the costs of 15 years ago.JRC.D.5-Food Securit