Automated monitoring systems with different temporal and spatial resolutions can achieve precision agriculture management. Unmanned aerial vehicle (UAV) systems open new possibilities for effectively characterizing the variability within cropping systems with high spatial and temporal resolution. In this study, a UAV with a low-cost visible and near-infrared camera assessed the spatial variability in the herbage biomass (BM) and leaf area index (LAI) in an Italian ryegrass field. Using multiple linear regression (MLR) models, high coefficients of determination (R2) and low root-mean-squared error (RMSE) values were obtained between the observed and predicted herbage BM (R2 = 0.84, RMSE = 90.43 g m−2) and LAI (R2 = 0.88, RMSE = 0.82). The MLR models successfully recovered high-resolution spatial distributions of the herbage BM and LAI from the ortho-photos. The reconstructed maps verified that the proposed method can effectively characterize spatial field variations and assess forage growth to optimize field-level forage crop management.@en

Crop growth stage is critical for making decisions in nutrient management and for evaluating crop productivity. In this study, a simple visible and near-infrared (V-NIR) camera system was developed for monitoring the leaf area index (LAI) and quantifying the quick growth stage (QGS) of Italian ryegrass. RAW format images in the red, green and NIR channels over two growing seasons of 2014–15 and 2015–16 were captured hourly each day by the V-NIR camera system installed in three Italian ryegrass fields at the farm of Hiroshima University. Multiple linear regression (MLR) models that predict the forage LAI from the imagery data were calibrated and validated, with high coefficient of determination (R2 = 0.79) and low root-mean-square error (RMSE = 1.09) between the measured and predicted LAIs. The predicted LAI to which three vegetation indices were compared was fitted against a logistic model to extract forage QGS from smoothed time-series data under various micro-meteorological and nutrient conditions. The result shows the time-series data of LAI can be applied for mon-itoring seasonal changes regardless of the environmental conditions. The RMSE of the predicted phenology dates against the field-measured LAI was 0.58 and 5.2 days for the start- and end-QGS, respectively, under the high-yield condition in season 1. However, in season 2, only the start-QGS was identifiable, with an RMSE of 2.65 days under the nutritional stress condition. The forage LAI and QGS were predicted and identified with acceptable accuracy and reliability, which suggests that the V-NIR camera system can be employed as a cost-effective approach for monitoring seasonal changes in crop growth, aiding in better personalized crop and nutrient management.@en