About the lab
Research, development and implementation of multidisciplinary techniques for the improvement of precision agriculture and oceanic monitoring, including deficit irrigation strategies, fruit quality analysis, sensor design or extraction of characteristics from soil and plant measurements leading to the automation of optimal irrigation management.
Featured projects (2)
The project is based on the need to have a precise knowledge of crop response to water deficit, both agronomical and physiological level, to develop precise regulated deficit irrigation (RDI) scheduling. The data acquisition for evaluating the plant water status and the irrigation scheduling automation lies in the use of both manual and continuous measurements of soil and plant water status. The objective marked of this finalist project aims to combine the advantages of using deficit irrigation strategies in commercial orchards in areas with limited water availability with the use of new technologies.
The main objective of this subproject is to contribute to the improvement of agricultural water management in woody crops located at the Mediterranean basin. Carrying out an optimal water resources management requires to accurately know the crop response to water deficit at both physiological and agronomic levels. The Regullated Deficit Irrigation is a complex method since many factors, related to the Soil-Plant-Atmosphere continuum and its high variability should be taking into account. This is the reason for which reliable measurement systems that continuously measure plant and soil water status, on real time, should be developed and deployed, before automating the irrigation procedure. Even though there are many commercial sensors able to measure certain parameters that provide information about the soil water potential or the plant water status, and it would be ideal to use such information as support for decision making and irrigation automation, they are barely deployed in real crops, since their economical cost is high, signal management is difficult and properly defining thresholds is also rather hard. Because of this, the proposed project is focused on developing a technique that allows a suitable implementation of the RDI by considering three major issues: a) The need of designing appropriate sensors, measurement techniques and interfaces capable of measuring parameters that represent the amount of water in soil in a clear, easy-to-understand and more direct manner. Such sensors should be easy to install and they should deliver reliable measurements providing enough variability. b) The need of determining better indexes and signs to estimate the water stress in the studied crops, such as the CWSI that allows the information about top tree and air temperature to be acquired. Data acquisition and term-radiometry equipment installation should be made as easy as possible, by taking autonomous systems based on Wireless Sensor Networks (WSNs). c) The need of adopting DSS-Decision Support Systems that allow stakeholders to define the required parameters for reliably programming the RDI. Thus, techniques for managing big data volumes obtained from the Soil-Plant-Atmosphere continuum, and autolearning methods to adapt the variability of the received information, should be also considered and properly developed.
Featured research (37)
Water is a limited resource in arid and semi-arid regions, as is the case in the Mediterranean Basin, where demographic and climatic conditions make it ideal for growing fruits and vegetables, but a greater volume of water is required. Deficit irrigation strategies have proven to be successful in optimizing available water without pernicious impact on yield and harvest quality, but it is essential to control the water stress of the crop. The direct measurement of crop water status is currently performed using midday stem water potential, which is costly in terms of time and labor; therefore, indirect methods are needed for automatic monitoring of crop water stress. In this study, we present a novel approach to indirectly estimate the water stress of 15-year-old mature sweet cherry trees from a time series of soil water status and meteorological variables by using Machine Learning methods (Random Forest and Support Vector Machine). Time information was accounted for by integrating soil and meteorological measurements within arbitrary periods of 3, 6 and 10 days. Supervised binary classification and regression approaches were applied. The binary classification approach allowed for the definition of a model that alerts the farmer when a dangerous crop water stress episode is about to happen a day in advance. Performance metrics F2 and recall of up to 0.735 and 0.769, respectively, were obtained. With the regression approach a R2 of up to 0.817 was achieved.
Crop canopy temperature measurement is necessary for monitoring water stress indicators such as the Crop Water Stress Index (CWSI). Water stress indicators are very useful for irrigation strategies management in the precision agriculture context. For this purpose, one of the techniques used is thermography, which allows remote temperature measurement. However, the applicability of these techniques depends on being affordable, allowing continuous monitoring over multiple field measurement. In this article, the development of a sensor capable of automatically measuring the crop canopy temperature by means of a low-cost thermal camera and the implementation of artificial intelligence-based image segmentation models is presented. In addition, we provide results on almond trees comparing our system with a commercial thermal camera, in which an R-squared of 0.75 is obtained.
Sensor platforms are used as sources of information for certain specific environments. In the field of maritime and oceanographic systems, these platforms make it possible to sensorize certain properties of the water based on various variables, such as the oxygen level, the levels of turbidity, chlorophyll, salinity, etc. Due to the different stratifications that occur in this environment at different depths, it is necessary to perform the measurement at different depths. Therefore, this project will focus on the design of a control algorithm to manage the depth of an object with immersion capacity, thus allowing the submersible architecture to be stopped at a desired depth. The control system will be progressively analyzed, which will allow the depth to be managed depending on the position of the actuators. For this, different points will be addressed, such as the considerations and constructive characteristics of the model, the detailed study of the behavior of each of the main components of the system, as well as the response of the variables to be studied. In addition, said control system will be implemented in a microcontroller to provide the appropriate signals at each instant of time, thus allowing the actuators to introduce or dislodge a specific volume of water and, consequently, achieve an adequate and autonomous platform movement.