Resumen

VILLAVICENCIO_QUINTERO, Dennis; CABRERA_HERNANDEZ, Emilio; GODO_ALONSO, Alain  y  SANTANA CHING, Ivan. Decision-making system for irrigation of protected crops based on machine learning. EAC [online]. 2023, vol.44, n.3, pp. 41-49.  Epub 01-Feb-2024. ISSN 1815-5928.

The water scarcity is a concern of the agricultural industry as it uses four fifths of the of the total fresh water consumed for irrigation and two thirds of the total used for human consumption. For this reason, the development of systems that optimize the use of water in irrigation is essential. In the greenhouses of the UEB "Valle del Yabú" of the Santa Clara municipality, irrigation is carried out using a drip-based system that requires the presence of an operator for decision-making who does not have information about some of the hydrometeorological variables that govern the crop. This paper focused on to design a support system for decision-making in irrigation based on machine learning. As an important parameter of the system, the evapotranspiration coefficient of the crop is calculated using the Turc formula. The collected environmental data is conditioned and linear regression, regressive random forests, and gradient-boosted trees regression models are trained with them to determine future evapotranspiration values using the Apache Spark framework. The model that obtained the best results was the regressive random forest with a coefficient of determination (r2) of 0,79 and with it the volume of water lost by the crop is calculated. Finally, the system was able to provide the estimates of both variables, which favour decision-making by specialists.

Palabras clave : greenhouse cultivation; artificial intelligence; machine learning; evapotranspiration; random regressive forests.

        · resumen en Español     · texto en Español     · Español ( pdf )