Variable Fertilizer Recommendation by Image-based Grass Growth Status

Abstract

Objective of this research was to recommend variable rate fertilization for sod production fields depending on the site-specific grass growth levels. CCD based images were acquired from three different sod production fields and calibration relationships were obtained between the sensor measurements and grass growth levels. Based on the calibrations, fertilizer recommendation was derived based on the expert experience. For analysis of the spatial variation of growth level and mapping, geostatistical methods such as variogram modeling and Kriging were used. A range of 0.5 to 1, 0.5 to 1.5, and 2 to 4 levels of fertilizers were recommended for the sod production fields with 90%, 70%, and 50% grass growth coverage. This study would contribute greatly to increase fertilizer use efficiency and reduce environmental contamination, if the recommended fertilizers were variably applied.