Pathogen infection has greatly reduced crop production. As the symptoms of diseases usually appear when the plants are infected severely, rapid identification approaches are required to monitor plant diseases at early the infection stage and optimize control strategies. Hyperspectral imaging, as a fast and nondestructive sensing technology, has achieved remarkable results in plant disease identification. Various models have been developed for disease identification in different plants such as arable crops, vegetables, fruit trees, etc. In these models, important algorithms, such as the vegetation index and machine learning classification and methods have played significant roles in the detection and early warning of disease. In this paper, the principle of hyperspectral imaging technology and common spectral characteristics of plant disease symptoms are discussed. We reviewed the impact mechanism of pathogen infection on the photo response and spectrum features of the plants, the data processing tools and algorithms of the hyperspectral information of pathogen-infected plants, and the application prospect of hyperspectral imaging technology for the identification of plant diseases.

Weed suppression is an important factor affecting crop yields. Precise identification of weed species will contribute to automatic weeding by applying proper herbicides, hoeing position determination, and hoeing depth to specific plants as well as reducing crop injury. However, the lack of datasets of weeds in the field has limited the application of deep learning techniques in weed management. In this paper, it presented a dataset of weeds in fields, Weed25, which contained 14,035 images of 25 different weed species. Both monocot and dicot weed image resources were included in this dataset. Meanwhile, weed images at different growth stages were also recorded. Several common deep learning detection models—YOLOv3, YOLOv5, and Faster R-CNN—were applied for weed identification model training using this dataset. The results showed that the average accuracy of detection under the same training parameters were 91.8%, 92.4%, and 92.15% respectively. It presented that Weed25 could be a potential effective training resource for further development of in-field real-time weed identification models. The dataset is available at https://pan.baidu.com/s/1rnUoDm7IxxmX1n1LmtXNXw; the password is rn5h.

Electrostatic spraying application is adopted in crop protection to prevent pest infestation, to improve product quality and to maximize yield. It involves a superposition of charges to pesticide spray droplets to attract substrate ions at obscured surfaces. The droplets wraparound effect reduces off-target deposition, enhances on-target spray and invariably improves spray efficiency. Electrostatic spraying system works effectively at optimum parameters in combination with charging voltages, application pressures, spraying height regimes, flow rate, travel speed, electrode material, and nozzle orientation. Many combinations of the system parameter settings have been systematically used by researchers for the electrostatic application, but there are unknown specific optimum parameters combinations for pesticide spraying. Since droplets chargeability influences the effectiveness of electrostatic spraying system, the parameters that produce ideal charge to mass ratio determine the functionality of the spraying deposition, retention and surface coverage. This article, therefore, analyses electrostatic system parameters that produce suitably charged droplets characteristics for effective impacting behavior of pesticides on substrates. Increasing applied voltages consequently maximizes charge-mass ratio to optimum and starts declining upon further increase in voltages beyond a critical point. This review further proposes the selection of an optimum electrostatic parameters combination that yields optimum droplets chargeability in pesticide application. Also, it is necessary to investigate the charge property of substrates prior to pesticide application in order to superpose the right opposite charge on spray droplets at rupture time during electrostatic spraying system. Keywords: electrostatic spraying, charged droplets, substrates, deposition, wraparound, charge-mass ratio DOI: 10.25165/j.ijabe.20191202.4673 Citation: Appah S, Wang P, Ou M X, Gong C, Jia W D. Review of electrostatic system parameters, charged droplets characteristics and substrate impact behavior from pesticides spraying. Int J Agric & Biol Eng, 2019; 12(2): 1–9.

Droplet characteristics are identified as essential factors in agricultural spray application. The aims of this study were to analyse the influence of spray parameters on droplet characteristics and to determine possible candidate sprays that would produce the same droplet size categorizations as the American Society of Agricultural and Biological Engineers (ASABE) standard S-572.1 for air induction nozzles (AINs). Six different orifice sizes of the Billericay Farm Services (BFS) air induction (AI) flat fan hydraulic nozzles (the air bubblejet) were examined at different spray pressures (200 kPa, 300 kPa, 400 kPa, 500 kPa, 600 kPa and 700 kPa) and concurrent air velocities (2 m/s, 3 m/s, 4 m/s and 5 m/s). The influences of spray parameters on the droplet characteristics were analysed using analysis of covariance (ANCOVA) and analysis of variance (ANOVA). Results showed that: (1) The values of droplet characteristics and the results of ANOVA were significantly different before and after eliminate the influence of dynamic surface tension (DST) on droplet characteristics by ANCOVA; (2) (a) the reduction rates of the droplet diameter sizes decreased with increasing spray pressure; (b) air velocities of 2 m/s and 5 m/s resulted in smaller droplets reports, and air velocities of 3 m/s and 4 m/s are more suitable for agricultural spray applications; (c) a larger nozzle orifice size not always result in a larger droplet size and (3) Fine, Medium, Coarse, Very Coarse and Extremely Coarse droplet classification categories as the ASABE S-572.1 standard categorizations were determined to classify AINs.