Assessment of the nitrogen status of grapevines with high spatial, temporal resolution offers benefits in fertilizer use efficiency, crop yield and quality, and vineyard uniformity. The primary objective of this study was to develop a robust predictive model for grapevine nitrogen estimation at bloom stage using high-resolution multispectral images captured by an unmanned aerial vehicle (UAV). Aerial imagery and leaf tissue sampling were conducted from 150 grapevines subjected to five rates of nitrogen applications. Subsequent to appropriate pre-processing steps, pixels representing the canopy were segmented from the background per each vine. First, we defined a binary classification problem using pixels of three vines with the minimum (low-N class) and two vines with the maximum (high-N class) nitrogen concentration. Following optimized hyperparameters configuration, we trained five machine learning classifiers, including support vector machine (SVM), random forest, XGBoost, quadratic discriminant analysis (QDA), and deep neural network (DNN) with fully-connected layers. Among the classifiers, SVM offered the highest F1-score (82.24%) on the test dataset at the cost of a very long training time compared to the other classifiers. Alternatively, QDA and XGBoost required the minimum training time with promising F1-score of 80.85% and 80.27%, respectively. Second, we transformed the classification into a regression problem by averaging the posterior probability of high-N class for all pixels within each of 150 vines. XGBoost exhibited a slightly larger coefficient of determination (R² = 0.56) and lower root mean square error (RMSE) (0.23%) compared to other learning methods in the prediction of nitrogen concentration of all vines. The proposed approach provides values in (i) leveraging high-resolution imagery, (ii) investigating spatial distribution of nitrogen across a vine’s canopy, and (iii) defining spatial zones for nitrogen application and smart sampling.

Unmanaged spray drift from orchard pesticide application contributes to environmental contamination and causes significant danger to farmworkers, nearby residential areas, and neighbors’ crops. Most drift control approaches do not guarantee adequate and uniform canopy spray coverage. Our goal was to develop a spray backstop system that could block drifting from the top without any negative impact on spray coverage and on-target deposition. The design included a foldable mast and a shade structure that covered the trees from the top. We used a continuous loop sampling to assess and quantify the effectiveness of spray backstop on drift potential reduction. We also collected leaf samples from different sections of trees to compare on-target deposition and coverage. The results showed that the spray backstop system could significantly (p-Value < 0.01) reduce drift potential from the top (78% on average). While we did not find any statistical difference in overall canopy deposition with and without the backstop system, we observed some improvement in treetops deposition. This experiment’s output suggests that growers may be able to adjust their air-assist sprayers for a more uniform spray coverage without concern about the off-target movement of spray droplets when they employ the spray backstop system.