A Decision Support System for Irrigation Management: Analysis and Implementation of Different Learning Techniques

Abstract

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.

Characterization of Low-Cost Capacitive Soil Moisture Sensors for IoT Networks

“…Modernization and automated scheduling of irrigation systems demands for sensor-based equipment. Traditionally, sensor data are associated with environmental conditions and soil water status to provide information about the full crop water requirements [15]. The most commonly used soil parameter sensors exploit dielectric properties, since they are relatively cheap and flexible [16,17].…”

Machine Learning Applications for Precision Agriculture: A Comprehensive Review

“…Singh et al [122] have discussed an ML and IoT based model for soil moisture prediction during irrigation. Torres-Sanchez et al [123] proposed a decision support system for irrigation management of citric crops in southeast Spain. In the proposed model smart sensors are deployed in the field to monitor water supplied previous week, weather data, soil water status, and based on this data three regression models SVM, RF, and Linear regression was trained to build the irrigation decision support system.…”

Short term soil moisture forecasts for potato crop farming: A machine learning approach

“…Moreover, like [31,50,33] we compare different learning algorithms, in our case NN, RF and SVR which have proven their relevance for solving similar problems (see section 1). However, we choose to predict SWP and not evapotranspiration and those over a larger time window, namely 7 days (like in [25])…”

“…In the context of agriculture, [25] successfully applied machine learning approach to predict weekly evapotranspiration for orchards crop and therefore the water needs. On the subject of potato cultivation in farmland, various topics are highlighted and well-documented.…”