In the field of pesticide spraying, droplet size is one of the most important factors affecting droplet deposition and drift. In order to study the effect of different droplet size parameters on droplet deposition distribution and drift of aerial spraying by using plant protection UAV, an aerial spraying test with the same spraying rate and different size droplets in rice canopy was carried out by using multi-rotor unmanned aerial vehicles (UAV) and four TEEJET nozzles with different orifice sizes (these droplets with a volume median diameter (VMD) of 95.21, 121.43, 147.28, and 185.09 μm, respectively), and the deposition distribution and penetration of droplets in the target area and the drift distribution of droplets in the non-target area were compared and analyzed. The results showed that the deposition distribution and penetration of droplets in the target area and the drift distribution of droplets in the non-target area were influenced by the droplet size. The droplet deposition rate in the upper and lower rice canopies were increased in the target area with the increase of droplet size. The penetration results of droplets also increased with the increase of droplet size, and that of droplets with a VMD of 185.09 μm was the best, reaching 38.13%. The average values of the cumulative drift rate of droplets in the rice canopy in the four tests were 73.87%, 50.26%, 35.91%, and 23.06%, respectively, and the cumulative drift rate and the drift distance of droplets decreased with the increase of droplet size, which indicated that the increase of droplet size can effectively reduce droplet drift. It demonstrated that the droplet size is one of the most important factors affecting droplet deposition and drift for pesticide spraying by plant protection UAV, and for the application of plant protection UAV with extra-low volume spraying, the use of droplets with VMD less than 160 μm should be avoided and a more than 10 m buffer zone should be considered downwind of the spraying field to avoid drug damage caused by pesticide drift. The results have fully revealed the effect of droplet size parameters on droplet deposition and drift of aerial spraying. Moreover, the influence of the wind field below the rotors on the distribution of droplet deposition was surmised and analyzed from the perspective of plant protection UAV. It is important for optimizing the droplet parameters of aerial spraying, increasing the spraying efficiency, and realizing precision agricultural aviation spray.

Pine wilt disease causes huge economic losses to pine wood forestry because of its destructiveness and rapid spread. This paper proposes a detection and location method of pine wood nematode disease at a large scale adopting UAV (Unmanned Aerial Vehicle) remote sensing and artificial intelligence technology. The UAV remote sensing images were enhanced by computer vision tools. A Faster-RCNN (Faster Region Convolutional Neural Networks) deep learning framework based on a RPN (Region Proposal Network) network and the ResNet residual neural network were used to train the pine wilt diseased dead tree detection model. The loss function and the anchors in the RPN of the convolutional neural network were optimized. Finally, the location of pine wood nematode dead tree was conducted, which generated the geographic information on the detection results. The results show that ResNet101 performed better than VGG16 (Visual Geometry Group 16) convolutional neural network. The detection accuracy was improved and reached to about 90% after a series of optimizations to the network, meaning that the optimization methods proposed in this paper are feasible to pine wood nematode dead tree detection.

Citrus is an important cash crop in the world, and huanglongbing (HLB) is a destructive disease in the citrus industry. To efficiently detect the degree of HLB stress on large-scale orchard citrus trees, an UAV (Uncrewed Aerial Vehicle) hyperspectral remote sensing tool is used for HLB rapid detection. A Cubert S185 (Airborne Hyperspectral camera) was mounted on the UAV of DJI Matrice 600 Pro to capture the hyperspectral remote sensing images; and a ASD Handheld2 (spectrometer) was used to verify the effectiveness of the remote sensing data. Correlation-proven UAV hyperspectral remote sensing data were used, and canopy spectral samples based on single pixels were extracted for processing and analysis. The feature bands extracted by the genetic algorithm (GA) of the improved selection operator were 468 nm, 504 nm, 512 nm, 516 nm, 528 nm, 536 nm, 632 nm, 680 nm, 688 nm, and 852 nm for the HLB detection. The proposed HLB detection methods (based on the multi-feature fusion of vegetation index) and canopy spectral feature parameters constructed (based on the feature band in stacked autoencoder (SAE) neural network) have a classification accuracy of 99.33% and a loss of 0.0783 for the training set, and a classification accuracy of 99.72% and a loss of 0.0585 for the validation set. This performance is higher than that based on the full-band AutoEncoder neural network. The field-testing results show that the model could effectively detect the HLB plants and output the distribution of the disease in the canopy, thus judging the plant disease level in a large area efficiently.

“Candidatus Liberibacter asiaticus” (CLas), a non-culturable α-proteobacterium, is associated with citrus Huanglongbing (HLB, yellow shoot disease) currently threatening citrus production worldwide. Here, the whole genome sequence of CLas strain A4 from Guangdong of China was analyzed. Five copies of nrdB, encoding β-subunit of ribonucleotide reductase (RNR), a critical enzyme involving bacterial proliferation, were found. Three nrdB copies were in long form (nrdB^L, 1,059 bp) and two were in short form (nrdB^S, 378 bp). nrdB^S shared >99% identity to 3′ end of nrdB^L and had no active site. Sequences of CLas nrdB genes formed a distinct monophyletic lineage among eubacteria. To make use of the high copy number feature, a nrdB-based primer set RNRf/RNRr was designed and evaluated using real-time PCR with 262 HLB samples collected from China and USA. Compared to the current standard primer set HLBas/HLBr derived from the 16S rRNA gene, RNRf/RNRr had Ct value reductions of 1.68 (SYBR Green PCR) and 1.77 (TaqMan PCR), thus increasing the detection sensitivity three-fold. Meanwhile, RNRf/RNRr was more than twice the stability of primer set LJ900f/LJ900r derived from multi-copy prophage. The nrdB-based PCR thereby provides a sensitive and reliable CLas detection with broad application, especially for the early diagnosis of HLB.

Chemical control is necessary in order to control weed infestation and to ensure a rice yield. However, excessive use of herbicides has caused serious agronomic and environmental problems. Site specific weed management (SSWM) recommends an appropriate dose of herbicides according to the weed coverage, which may reduce the use of herbicides while enhancing their chemical effects. In the context of SSWM, the weed cover map and prescription map must be generated in order to carry out the accurate spraying. In this paper, high resolution unmanned aerial vehicle (UAV) imagery were captured over a rice field. Different workflows were evaluated to generate the weed cover map for the whole field. Fully convolutional networks (FCN) was applied for a pixel-level classification. Theoretical analysis and practical evaluation were carried out to seek for an architecture improvement and performance boost. A chessboard segmentation process was used to build the grid framework of the prescription map. The experimental results showed that the overall accuracy and mean intersection over union (mean IU) for weed mapping using FCN-4s were 0.9196 and 0.8473, and the total time (including the data collection and data processing) required to generate the weed cover map for the entire field (50 × 60 m) was less than half an hour. Different weed thresholds (0.00–0.25, with an interval of 0.05) were used for the prescription map generation. High accuracies (above 0.94) were observed for all of the threshold values, and the relevant herbicide saving ranged from 58.3% to 70.8%. All of the experimental results demonstrated that the method used in this work has the potential to produce an accurate weed cover map and prescription map in SSWM applications.