Application of Machine Learning Method to Quantitatively Evaluate the Droplet Size and Deposition Distribution of the UAV Spray Nozzle

Unmanned Aerial Vehicle (UAV) spray has been used for efficient and adaptive pesticide applications with its low costs. However, droplet drift is the main problem for UAV spray and will induce pesticide waste and safety concerns. Droplet size and deposition distribution are both highly related to droplet drift and spray effect, which are determined by the nozzle. Therefore, it is necessary to propose an evaluating method for a specific UAV spray nozzles. In this paper, four machine learning methods (REGRESS, least squares support vector machines (LS-SVM), extreme learning machine, and radial basis function neural network (RBFNN)) were applied for quantitatively evaluating one type of UAV spray nozzle (TEEJET XR110015VS), and the case of twin nozzles was investigated. The results showed REGRESS and LS-SVM are good candidates for droplet size evaluation with the coefficient of determination in the calibration set above 0.9 and root means square errors of the prediction set around 2 µm. RBFNN achieved the best performance for the evaluation of deposition distribution and showed its potential for determining the droplet size of overlapping area. Overall, this study proved the accuracy and efficiency of using the machine learning method for UAV spray nozzle evaluation. Additionally, the study demonstrated the feasibility of using machine learning model to predict the droplet size in the overlapping area of twin nozzles.

[1]  S. Chatterjee,et al.  Influential Observations, High Leverage Points, and Outliers in Linear Regression , 1986 .

[2]  N. Nagelkerke,et al.  A note on a general definition of the coefficient of determination , 1991 .

[3]  Andrew J. Hewitt.  DROPLET SIZE AND AGRICULTURAL SPRAYING, PART I: ATOMIZATION, SPRAY TRANSPORT, DEPOSITION, DRIFT, AND DROPLET SIZE MEASUREMENT TECHNIQUES , 1997 .

[4]  C. Tuck,et al.  Techniques for measurement of droplet size and velocity distributions in agricultural sprays , 1997 .

[5]  Jongsoo Jurng,et al.  Spherical-shaped ice particle production by spraying water in a vacuum chamber , 2000 .

[6]  S. Edward Law,et al.  Agricultural electrostatic spray application: a review of significant research and development during the 20th century , 2001 .

[7]  A. P. Watkins,et al.  Application of artificial neural networks modelling to sprays and spray impingement heat transfer , 2002 .

[8]  Johan A. K. Suykens,et al.  Weighted least squares support vector machines: robustness and sparse approximation , 2002, Neurocomputing.

[9]  Meng Joo Er,et al.  Face recognition with radial basis function (RBF) neural networks , 2002, IEEE Trans. Neural Networks.

[10]  A. Kai Qin,et al.  Evolutionary extreme learning machine , 2005, Pattern Recognit..

[11]  R. E. Wolf.  COMPARING DOWNWIND SPRAY DROPLET DEPOSITS OF FOUR FLAT-FAN NOZZLE TYPES MEASURED IN A WIND TUNNEL AND ANALYZED USING DROPLETSCAN. SOFTWARE , 2005 .

[12]  David M. Reif,et al.  Machine Learning for Detecting Gene-Gene Interactions , 2006, Applied bioinformatics.

[13]  Witold Pedrycz,et al.  Improving RBF networks performance in regression tasks by means of a supervised fuzzy clustering , 2006, Neurocomputing.

[14]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[15]  Yang Yu,et al.  SPRAY CHARACTERISTICS AND DRIFT REDUCTION POTENTIAL WITH AIR INDUCTION AND CONVENTIONAL FLAT-FAN NOZZLES , 2007 .

[16]  David Nuyttens,et al.  Effect of nozzle type, size and pressure on spray droplet characteristics , 2007 .

[17]  Kyoungtae Kim,et al.  Characterization of deposition patterns produced by twin-nozzle electrospray , 2008 .

[18]  N. C. Van de Giesen,et al.  Monthly streamflow prediction in the Volta Basin of West Africa: A SISO NARMAX polynomial modelling , 2008 .

[19]  Yubin Lan,et al.  Development of a Spray System for an Unmanned Aerial Vehicle Platform , 2009 .

[20]  R. N. Barbosa,et al.  Technical Note: Effect of Spray Rate and Method of Application in Spray Deposition , 2009 .

[21]  T. J. Jankun-Kelly,et al.  Guided analysis of hurricane trends using statistical processes integrated with interactive parallel coordinates , 2009, 2009 IEEE Symposium on Visual Analytics Science and Technology.

[22]  Yuan Lan,et al.  Constructive hidden nodes selection of extreme learning machine for regression , 2010, Neurocomputing.

[23]  Andrew J. Landers,et al.  Dosage Adjustment for Pesticide Application in Vineyards , 2012 .

[24]  E. Hilz,et al.  Spray drift review: The extent to which a formulation can contribute to spray drift reduction , 2013 .

[25]  Jian Zhang,et al.  Laser Gyro Temperature Compensation Using Modified RBFNN , 2014, Sensors.

[26]  H. Taghavifar,et al.  Diesel engine spray characteristics prediction with hybridized artificial neural network optimized by genetic algorithm , 2014 .

[27]  R. S. Henry,et al.  Influence of Herbicide Active Ingredient, Nozzle Type, Orifice Size, Spray Pressure, and Carrier Volume Rate on Spray Droplet Size Characteristics , 2015, Weed Technology.

[28]  Bhagirath S. Chauhan,et al.  Determining the uniformity and consistency of droplet size across spray drift reducing nozzles in a wind tunnel , 2015 .

[29]  Bo Lu,et al.  CORRIGENDUM: Separable Bilayer Microfiltration Device for Viable Label-free Enrichment of Circulating Tumour Cells , 2015, Scientific Reports.

[30]  Y. Lü,et al.  Recent ecological transitions in China: greening, browning, and influential factors , 2015, Scientific Reports.

[31]  I. Dhouib,et al.  From immunotoxicity to carcinogenicity: the effects of carbamate pesticides on the immune system , 2016, Environmental Science and Pollution Research.

[32]  Jose I. Bilbao,et al.  A review and analysis of regression and machine learning models on commercial building electricity load forecasting , 2017 .

[33]  He Xiongkui,et al.  Recent development of unmanned aerial vehicle for plant protection in East Asia , 2017 .

[34]  Zhang Yanliang,et al.  Design and test of a six-rotor unmanned aerial vehicle (UAV) electrostatic spraying system for crop protection , 2017 .

[35]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  A Machine Learning-Based Approach for Prediction of Plant Protection Product Deposition , 2017, 2017 Brazilian Conference on Intelligent Systems (BRACIS).

[36]  Kwok-wing Chau,et al.  Flood Prediction Using Machine Learning Models: Literature Review , 2018, Water.

[37]  Xiongkui He,et al.  Testing method and distribution characteristics of spatial pesticide spraying deposition quality balance for unmanned aerial vehicle , 2018 .

[38]  Yubin Lan,et al.  Drift and deposition of pesticide applied by UAV on pineapple plants under different meteorological conditions , 2018 .

[39]  Wang Ling,et al.  Research on the prediction model and its influencing factors of droplet deposition area in the wind tunnel environment based on UAV spraying , 2018 .

[40]  Feng Kang,et al.  Establishment of a static nozzle atomization model for forest barrier treatment , 2018, Crop Protection.

[41]  Chu Zhang,et al.  Application of Hyperspectral Imaging to Detect Sclerotinia sclerotiorum on Oilseed Rape Stems , 2018, Sensors.

[42]  Dongpu Cao,et al.  Driving-Style-Oriented Multi-Objective Optimal Control of an Electric Vehicle , 2018 .

[43]  Se-woon Hong,et al.  CFD simulation of pesticide spray from air-assisted sprayers in an apple orchard: Tree deposition and off-target losses , 2018 .

[44]  Zhaoxia Lou,et al.  Effect of Unmanned Aerial Vehicle Flight Height on Droplet Distribution, Drift and Control of Cotton Aphids and Spider Mites , 2018, Agronomy.

[45]  Yeyin Shi,et al.  Distribution characteristics on droplet deposition of wind field vortex formed by multi-rotor UAV , 2019, PloS one.

[46]  Rui Yao,et al.  A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm , 2017, Soft Computing.