Dynamic Neural Network Modelling of Soil Moisture Content for Predictive Irrigation Scheduling

Abstract

Sustainable freshwater management is underpinned by technologies which improve the efficiency of agricultural irrigation systems. Irrigation scheduling has the potential to incorporate real-time feedback from soil moisture and climatic sensors. However, for robust closed-loop decision support, models of the soil moisture dynamics are essential in order to predict crop water needs while adapting to external perturbation and disturbances. This paper presents a Dynamic Neural Network approach for modelling of the temporal soil moisture fluxes. The models are trained to generate a one-day-ahead prediction of the volumetric soil moisture content based on past soil moisture, precipitation, and climatic measurements. Using field data from three sites, a R2 value above 0.94 was obtained during model evaluation in all sites. The models were also able to generate robust soil moisture predictions for independent sites which were not used in training the models. The application of the Dynamic Neural Network models in a predictive irrigation scheduling system was demonstrated using AQUACROP simulations of the potato-growing season. The predictive irrigation scheduling system was evaluated against a rule-based system that applies irrigation based on predefined thresholds. Results indicate that the predictive system achieves a water saving ranging between 20 and 46% while realizing a yield and water use efficiency similar to that of the rule-based system.

Exploring the Adoption of Precision Agriculture for Irrigation in the Context of Agriculture 4.0: The Key Role of Internet of Things

“…Agriculture is a window, so this must be done before, based on this window ”. The inputs transformed by irrigation planning are crop characteristics, weather data and soil characteristics [ 9 , 39 , 41 , 91 , 104 , 105 ]. The resources which perform the irrigation planning are farmer or farm manager (depending on farm organization), farm characteristics and IoT sensing technologies [ 9 , 39 , 52 ].…”

Gesture Prediction Using Wearable Sensing Systems with Neural Networks for Temporal Data Analysis

“…As shown in Figure 3, the input sequence is a combination of the 20 most recent resistance values obtained from each strain sensor, and the output data are trained to predict the resistance value one point ahead of that of each sensor. The only data pre-processing step the model applied was the standardization of the resistance data of each finger [29]. In the post-processing stage, the predicted resistance data are back-transformed to the actual scale.…”

Decision support systems for scheduling tasks in Biosystems Engineering

“…However, predominant decision support systems prevailed. -Forest management model [21] -Impact of water resources on forest productivity [22] -Watershed Management Priority Indices (WMPI) [22] -Forest Road Evaluation System (FRES) [22] -Harvest Schedule Review System (HSRS) [22] Agriculture -Planning the harvest of tomatoes [23] -Dynamic Bayesian Network [23] -Optimization of the sugar cane harvest [24] -Regression analysis [24] -Optimization of grass harvest [25] -Mixed Integer Programming [25] Decision problem Method / algorithm / framework to support scheduling -evaluate the DSS for Agrotechnology Transfer Cropping System Model (DSSAT-CSM) for assessing grain sorghum yield and water productivity [26] -DSS for Agrotechnology Transfer Cropping System Model (DSSAT-CSM) [26] -Predictive irrigation planning system [27,28] -Artificial Neural Network (ANN) [27] -Predictive methods [28] -Basin Irrigation Design with Multi-Criteria Analysis Focusing on Water Saving and Economic Returns [29] -(meta-)heuristics [29] -A simulation tool which integrate the energy efficiency of the pumping station taking into account irrigation events distribution according to the crop irrigation scheduling at each plot [30] -GREDRIP [30] -Quantify the effects of The El Nino Southern Oscillation (ENSO) phenomenon on tomato crop water requirements [31] -AgroClimate irrigation tool [31] -Development of an integrated decision support system (IDSS) based on wireless sensor networks (WSN) and simulation procedures [32] -Platform Matlab (R) i Opnet (R) [32] -A decision support system based on the combination of the wireless sensor and actuation network technology and the fuzzy logic theory [33] -Fuzzy Logic [33] -Modeling the water and nitrogen productivity of sunflower using OILCROP-SUN model in Pakistan [34] -DSS for Agro-Technology Transfer (DSSAT) [34] , 0 (2019) https://doi.org/10.1051/e3sconf /2019 0 E3S Web of Conferences 132 10 1320100 POLSITA 2019 8 8 -A flexi...…”