Three radiometric instruments were compared as tools for predicting crop yield and grain quality: a CropScan instrument with 13 photodiodes (485-1650 nm), a 2150-channel FieldSpec3 instrument (350-2500 nm) 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 × 20 cm 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 2 pred) reaching 0.97 and 0.94 for grain yield and grain protein concentration, respectively. The predictions (r 2 pred) 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.
Validation of reflectance-based prediction models for plant properties is often performed on just one or two years of data. Hence, we aimed to perform a more comprehensive study regarding the validation of prediction models for grain yield and protein concentration. A FieldSpec3 portable field spectroradiometer was used to measure canopy reflectance in spring wheat. Spectral reflectance data were collected from three different experimental locations in up to four different years during the period 2007-2010, so that seven unique site years were included, comprising, altogether, 976 individual plots. Several datasets had moderate to severe lodging, which had a markedly negative influence on the prediction results. To correct for this problem, a classification model for the classes "lodging" and "standing crop" was calibrated from the spectral data. The model gave a total classification accuracy of 98.3%. Prediction models for grain yield and grain protein concentration were computed by means of the recent statistical method powered partial least squares (PPLS). Models were calibrated and validated on several combinations of the spectral datasets in order to reveal spatial and temporal effects on the prediction performance. The model performance generally increased with increasing variation in the calibration data, both in time (i.e. more years included) and space (i.e. more sites included). The best model for grain yield explained 94% [root mean square error of prediction (RMSEP) = 156 g m −2 ] of the variance and the predictions of grain protein concentration explained 67% [RMSEP = 1.51 g dry matter (DM) 100 g −1 ] of the variance. The performance of the grain yield PPLS models was compared with that of models based on some widely used vegetation indices [normalised difference vegetation index (NDVI), modified soil adjusted vegetation index (MSAVI), red edge inflection point (REIP) and d-chl-ab]. The explained variance of the models based on vegetation indices did not exceed 55%, indicating that these models were inferior to full spectrum models. This study shows that one or two years of spectral measurement are insufficient for building fully operational models for cereal property predictions.
Variable selection provides useful information about the most important predictors in the dataset, information which is not always available at the beginning of an analysis. Two recent variable selection methods, backward variable selection for partial least squares (BVSPLS) and powered partial least squares (PPLS), were compared against each other and against forward stepwise selection (FSS) and full spectrum partial least squares (PLS) in terms of their ability to produce accurate prediction models in NIR spectroscopy data. All four regression methods were studied using three different NIR datasets. PPLS and BVSPLS gave good prediction results in all three datasets, even with a very limited number of calibration samples available (<40). All methods gave similar prediction results when the number of calibration samples was higher (>150). PPLS gave the best predictive performance of all methods and also gave the selections of variables that were most easily assigned to specific chemical bonds. Hence, the PPLS models were more easily interpretable than the other models. This study quantifies differences between the two recent variable selection methods as well as the differences between recent methods and more established methods. Moreover, if the number of calibration samples can be reduced through variable selection, the labour and cost associated with wet chemistry reference methods can be reduced accordingly.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.