A Decision Support System for Irrigation Management: Analysis and Implementation of Different Learning Techniques
Roque Torres-Sanchez,
Honorio Navarro-Hellin,
Antonio Guillamon-Frutos,
Rubén San-Segundo,
Maria Carmen Ruiz-Abellón,
Rafael Domingo-Miguel
Affiliations
Roque Torres-Sanchez
Dpto. de Automática, Ingeniería Eléctrica y Tecnología Electrónica, Escuela Técnica Superior de Ingeniería Industrial, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
Honorio Navarro-Hellin
Widhoc Smart Solutions S.L., CEDIT, Parque Tecnológico de Fuente Álamo, ctra. del Estrecho-Lobosillo, km. 2, 30320 Fuente Alamo, Spain
Antonio Guillamon-Frutos
Dpto. de Matemática Aplicada y Estadística, Escuela Técnica Superior de Ingeniería Industrial, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
Rubén San-Segundo
Information Processing and Telecommunications Center, E.T.S.I. Telecomunicación, Universidad Politécnica de Madrid, 28040 Madrid, Spain
Maria Carmen Ruiz-Abellón
Dpto. de Matemática Aplicada y Estadística, Escuela Técnica Superior de Ingeniería Industrial, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
Rafael Domingo-Miguel
Dpto. de Ingeniería Agronómica, Escuela Técnica Superior de Ingeniería Agronómica, Universidad Politécnica de Cartagena, 30202 Cartagena, Spain
Automatic irrigation scheduling systems are highly demanded in the agricultural sector due to their ability to both save water and manage deficit irrigation strategies. Elaborating a functional and efficient automatic irrigation system is a very complex task due to the high number of factors that the technician considers when managing irrigation in an optimal way. Automatic learning systems propose an alternative to traditional irrigation management by means of the automatic elaboration of predictions based on the learning of an agronomist (DSS). The aim of this paper is the study of several learning techniques in order to determine the goodness and error relative to expert decision. Nine orchards were tested during 2018 using linear regression (LR), random forest regression (RFR), and support vector regression (SVR) methods as engines of the irrigation decision support system (IDSS) proposed. The results obtained by the learning methods in three of these orchards have been compared with the decisions made by the agronomist over an entire year. The prediction model errors determined the best fitting regression model. The results obtained lead to the conclusion that these methods are valid engines to develop automatic irrigation scheduling systems.