Estimativa do Coeficiente de Uniformidade de Microaspersores por Meio da Aplicação de Técnicas de Redes Neurais Artificiais
Abstract
The objective of this study was to evaluate the capacity of artificial neural networks to estimate distribution uniformity coefficient of micro sprinklers. The following features of a micro sprinkler model Pingo 360° brand Fabrimar were observed: pressure (kgf/cm3), nozzle (mm), jet breakup, wind average speed (m/s) and direction (degrees), initial flow rate, final flow rate, total flow rate, time and date of the experiment. In total, 256 rain gauges scattered around the micro sprinkler were used to measure how much water were spent during irrigation. Using Bayesian search and hyper parameter optimization techniques, an artificial neural network model, capable of estimate the Christiansen Uniformity Coefficient, was created. Using a distance of 12x12 meters between sprinklers, this model achieved an R2 of 92.87%, demonstrating that the methodology applied in this work is capable of simulate the irrigation process of the micro sprinkler used during the experiments.
References
R. Testezlaf, "Irrigação: métodos, sistemas e aplicações," 2011.
A. Phocaides, Handbook on pressurized irrigation techniques. Food & Agriculture Org., 2007.
O. Sheikhesmaeili, J. Montero, and S. Laserna, "Analysis of water application with semi-portable big size sprinkler irrigation systems in semi-arid areas," Agricultural Water Management, vol. 163, pp. 275-284, 2016.
B. Salvatierra-Bellido, J. Montero-Martínez, and L. Pérez-Urrestarazu, "Development of an automatic test bench to assess sprinkler irrigation uniformity in different wind conditions," Computers and Electronics in Agriculture, vol. 151, pp. 31-40, 2018.
P. Carrión, J. Tarjuelo, and J. Montero, "Sirias: a simulation model for sprinkler irrigation," Irrigation Science, vol. 20, no. 2, pp. 73-84, 2001.
S. Sayari, A. Mahdavi-Meymand, and M. Zounemat-Kermani, "Irrigation water infiltration modeling using machine learning," Computers and Electronics in Agriculture, vol. 180, p. 105921, 2021.
A. Dubois, F. Teytaud, and S. Verel, "Short term soil moisture forecasts for potato crop farming: A machine learning approach," Computers and Electronics in Agriculture, vol. 180, p. 105902, 2021.
P. L. d. Menezes, C. A. de Azevedo, E. Eyng, J. Dantas Neto, and V. L. de Lima, "Artificial neural network model for simulation of water distribution in sprinkle irrigation," Revista Brasileira de Engenharia Agrícola e Ambiental, vol. 19, pp. 817-822, 2015.
L. Yang and A. Shami, "On hyperparameter optimization of machine learning algorithms: Theory and practice," Neurocomputing, vol. 415, pp. 295-316, 2020.
I. Shcherbatyi, T. Head, and G. Louppe. (2017) Scikit-learn hyperparameter search wrapper. [Online]. Available: [link].
I. Goodfellow, Y. Bengio, and A. Courville, Deep learning. MIT press, 2016.
E. Jumin, F. B. Basaruddin, Y. B. Yusoff, S. D. Latif, A. N. Ahmed et al., "Solar radiation prediction using boosted decision tree regression model: A case study in malaysia," Environmental Science and Pollution Research, vol. 28, no. 21, pp. 26 571-26 583, 2021.
A. Wuraola, N. Patel, and S. K. Nguang, "Efficient activation functions for embedded inference engines," Neurocomputing, vol. 442, pp. 73-88, 2021.
C. K. Dewa et al., "Suitable cnn weight initialization and activation function for javanese vowels classification," Procedia computer science, vol. 144, pp. 124-132, 2018.
J. Wolfrann et al., "Redes neurais artificiais para estimar a precipitação na irrigação por aspersão," Master's thesis, Universidade Tecnológica Federal do Paraná, 2018.
