Root zone soil moisture prediction models based on system identification: Formulation of the theory and validation using field and AQUACROP data

Delgoda, Dilini; Saleem, Syed K.; Malano, Hector; Halgamuge, Malka N.

doi:10.1016/j.agwat.2015.08.011

Cited by 32 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A prediction of future input values and disturbances is required in an MPC system in order to determine the optimal system output [138]. This highlights the need for the incorporation of weather forecast data into the MPC framework for irrigation decision support.…”

Section: Model Predictive Controlmentioning

confidence: 99%

“…The authors of the discussed systems however fail to account for the stochastic nature of rainfall and crop water use in the system dynamics. Delgoda et al [138] noted that an adequate consideration of the uncertainty in rainfall and ET inputs into the water balance model employed in the MPC framework will improve the capability of the MPC system. Delgoda et al [115] addressed the drawbacks noted in the above MPC frameworks by employing disturbance affine feedback control, an uncertainty modelling technique widely applied in MPC to account for the stochastic nature of rainfall and crop water use.…”

Section: Model Predictive Controlmentioning

confidence: 99%

See 1 more Smart Citation

Advanced Monitoring and Management Systems for Improving Sustainability in Precision Irrigation

et al. 2017

View full text Add to dashboard Cite

Globally, the irrigation of crops is the largest consumptive user of fresh water. Water scarcity is increasing worldwide, resulting in tighter regulation of its use for agriculture. This necessitates the development of irrigation practices that are more efficient in the use of water but do not compromise crop quality and yield. Precision irrigation already achieves this goal, in part. The goal of precision irrigation is to accurately supply the crop water need in a timely manner and as spatially uniformly as possible. However, to maximize the benefits of precision irrigation, additional technologies need to be enabled and incorporated into agriculture. This paper discusses how incorporating adaptive decision support systems into precision irrigation management will enable significant advances in increasing the efficiency of current irrigation approaches. From the literature review, it is found that precision irrigation can be applied in achieving the environmental goals related to sustainability. The demonstrated economic benefits of precision irrigation in field-scale crop production is however minimal. It is argued that a proper combination of soil, plant and weather sensors providing real-time data to an adaptive decision support system provides an innovative platform for improving sustainability in irrigated agriculture. The review also shows that adaptive decision support systems based on model predictive control are able to adequately account for the time-varying nature of the soil-plant-atmosphere system while considering operational limitations and agronomic objectives in arriving at optimal irrigation decisions. It is concluded that significant improvements in crop yield and water savings can be achieved by incorporating model predictive control into precision irrigation decision support tools. Further improvements in water savings can also be realized by including deficit irrigation as part of the overall irrigation management strategy. Nevertheless, future research is needed for identifying crop response to regulated water deficits, developing improved soil moisture and plant sensors, and developing self-learning crop simulation frameworks that can be applied to evaluate adaptive decision support strategies related to irrigation.

show abstract

Section: Model Predictive Controlmentioning

confidence: 99%

Section: Model Predictive Controlmentioning

confidence: 99%

Advanced Monitoring and Management Systems for Improving Sustainability in Precision Irrigation

et al. 2017

View full text Add to dashboard Cite

show abstract

“…There have been previous attempts in literature to model the soil moisture dynamics and predict the soil moisture content in order to aid irrigation scheduling. Delgoda et al [ 25 ] presented a linear dynamic model with assumptions made on the absence of saturation flows. This lead to a degradation in the modelling results.…”

Section: Resultsmentioning

confidence: 99%

“…King and Shellie [ 24 ] used neural network modelling to estimate the lower threshold (

) needed to calculate the crop water stress index for wine grapes. Delgoda et al [ 25 ] applied a system identification model in predicting the soil moisture deficit using climatic and soil moisture data as model inputs. These statistical methods explore the spatial and temporal patterns hidden in historical data in order to map input data to an output space.…”

Section: Introductionmentioning

confidence: 99%

“…This is because of the complex nonlinear relationship between the climatic parameters, soil hydraulic properties, and the soil moisture dynamics [ 29 ]. Lozoya et al [ 30 ], Delgoa et al [ 25 ], Giusti and Marsili-Libelli [ 23 ], and Saleem et al [ 31 ] presented system identification models for the prediction of soil moisture dynamics, which are parameterized based on the soil water balance method. This involved assumptions relating to the absence of surface run-off and deep percolation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Adeyemi

Grove

Peets

et al. 2018

Sensors

168

View full text Add to dashboard Cite

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.

show abstract

Intelligent decision‐making for fertigation treatment of tomatoes cultivated in greenhouse: An experimental study

Li,

Hu,

et al. 2024

Irrigation and Drainage

View full text Add to dashboard Cite

To verify the effectiveness of the intelligent decision method for fertigation, an automatic control system for fertigation in greenhouses was designed, and three intelligent decision methods based on evapotranspiration (T1), soil moisture (T2) and accumulated temperature (T3) were tested. Intelligent decisions included monitoring meteorological information, automatically monitoring soil moisture, utilizing fertigation application systems and using automated control modules. The system was stable and accurately controlled according to the decision scheme. The results showed that the average errors of the automated control system for decision‐making and irrigation were 1.1 and 0.8%, respectively. The study findings serve as a reference for the integration of intelligent irrigation decision‐making and control systems and for further improving the efficiency of water and fertilizer utilized. Compared with those of the control, the three intelligent decision‐making methods increased the tomato yield by 8, 12 and 7%, respectively. In addition, the irrigation water and fertilizer levels decreased significantly compared with those in the control treatment. Although the accuracy of the soil water content (SWC) estimated based on ET and temperature in irrigation decision‐making is low, the general trend is consistent with practice. In addition, the irrigation water use efficiency (IWUE) and partial factor productivity of fertilizer (PFP) were significantly improved. Similarly, the IWUE in T1 was the highest (60 kg m⁻3), and the PFP in T3 was the highest (669 kg kg⁻¹).

show abstract

Root zone soil moisture prediction models based on system identification: Formulation of the theory and validation using field and AQUACROP data

Cited by 32 publications

References 19 publications

Advanced Monitoring and Management Systems for Improving Sustainability in Precision Irrigation

Advanced Monitoring and Management Systems for Improving Sustainability in Precision Irrigation

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

Intelligent decision‐making for fertigation treatment of tomatoes cultivated in greenhouse: An experimental study

Contact Info

Product

Resources

About