Crop yield estimation in 2014 for Vojvodina using methods of remote sensing

Abstract

Monitoring phenology of crops and yield estimate based on vegetation indices as well as other parameters such as temperature or amount of rainfall were largely reported in literature. In this research, MODIS Normalized Difference Vegetation Index (NDVI) was used as an indicator of specific crop condition; the other parameter was Land Surface Temperature (LST) which can indicate the amount of crop moisture. Trial years were 2011, 2012, and 2013. For those years sowing structure was acquired from agricultural organizations Nova Budućnost from Žarkovac and Sava Kovačević from Vrbas, both in Serbia. Also, satellite images with high and medium resolution for these areas and years were available. Multiple linear regression was used for crop yield estimate for Vojvodina Province, Serbia where the NDVI and LST were independent variables and the average yield for specific crop was the dependent variable. The results of crop yield estimate two months before harvest are presented (excluding wheat).