Comparisons of two hand-held, multispectral field radiometers and a hyperspectral airborne imager in terms of predicting spring wheat grain yield and quality by means of powered partial least squares regression

Three radiometric instruments were compared as tools for predicting crop yield and grain quality: a CropScan instrument with 13 photodiodes (485-1650nm), a 2150-channel FieldSpec3 instrument (350-2500nm) and a HySpex airborne hyperspectral line scanner with 160 image wavelength layers (400-1000 nm). The first two instruments are point spectroradiometers, while the HySpex is an imaging instrument with a pixel size of 20 x 20cm on the ground when the instrument is used at an altitude of 1000 m. A spring wheat field experiment of 160 plots was measured five times during the 2007 growing season. At harvest, grain yield was measured on each plot and analysed for moisture, protein, gluten, starch concentration and Zeleny sedimentation value. A recent statistical method, powered partial least squares (PPLS), was used for modelling and variable selection. The predictive performance of the calibrated models was very good, with coefficients of determination for the validation data (r(pred)(2)) reaching 0.97 and 0.94 for grain yield and grain protein concentration, respectively. The predictions (r(pred)(2)) of the other grain quality variables were in the range of 0.88-0.92. The airborne HySpex did not perform as well as the other instruments, most likely due to its limited spectral range. FieldSpec3 was significantly better than CropScan in most cases, probably as the former instrument has wider spectral range, a larger number of wavelengths and higher spectral resolution than the latter. A PPLS variable selection was carried out, which reduced the analysed data set from 975 wavelengths to 3-5 wavelengths. Although the number of retained variables was very low, the reduced models still had almost the same predictive ability as the PPLS models based on the full data set. The obtained simplicity of the calibration models indicates that a very small and lightweight instrument could be suitable for crop monitoring. Lightweight instruments are crucial for the utilisation of small unmanned aerial vehicles (UAVs). UAV technology is evolving quickly and small, cost effective UAV platforms are already available on the market. The concept of combining a UAV with a specifically designed instrument could provide an extremely versatile and cost effective system for crop monitoring.