In this paper, an automatic Smart Irrigation Decision Support System, SIDSS, is proposed to manage irrigation in agriculture. Our system estimates the weekly irrigations needs of a plantation, on the basis of both soil measurements and climatic variables gathered by several autonomous nodes deployed in field. This enables a closed loop control scheme to adapt the decision support system to local perturbations and estimation errors. Two machine learning techniques, PLSR and ANFIS, are proposed as reasoning engine of our SIDSS. Our approach is validated on three commercial plantations of citrus trees located in the South-East of Spain. Performance is tested against decisions taken by a human expertThe development of this work was supported by the Spanish Ministry of Science and Innovation through the projects MICINN, AGL2010-19201-C04-04 and Spanish Ministry of Economy and Competitiveness MINECO, AGL2013-49047-C2-1-R. We would like to thank Widhoc Smart Solutions S.L. and Queen’s Belfast University for letting us use their facilities and equipment to carry out the tests

Water is an essential resource for the development of agriculture. In several locations like the south-east of Spain water is scarce and its cost is high, so optimal management of this important resource isessential. Therefore, the application of irrigation strategies to improve the watering process, affects theprofitability of crops quite significantly. It is necessary to carry out the instrumentation of the variablesthat affect the growing process of the crop (soil, water and plant) and use the techniques associatedwith this instrumentation to take actions to optimize the production. The system proposed in this paperuses information and communication technologies, allowing the user to consult and analyze the infor-mation obtained by different sensors from any device (computer, mobile phone or tablet) in an easy andcomfortable way. The proposed architecture is based on different wireless nodes equipped with GPRSconnectivity. Each wireless node is completely autonomous and makes use of solar energy, giving it vir-tually unlimited autonomy. Different commercial sensors for measuring the wide range of parametersof the soil, plant and atmosphere can be connected to the nodes. The data is sent and processed on aremote server, which stores the information of the sensors in a database, allowing further consultationand analysis of data in a simple and versatile way.The development of this work was supported by the Span-ish Ministry of Science and Innovation (Ministerio de Ciencia e Innovación) (MICINN) through the projects MICINN, AGL2010-19201-C04-04 and MINECO, AGL2013-49047-C2-1-R. We wouldlike to thank Widhoc Smart Solutions S.L. for letting us use theirfacilities to carry out the tests