Smart Agricultural Technology 3 (2023) 100074

Contents lists available at ScienceDirect

Smart Agricultural Technology

journal homepage: www.journals.elsevier.com/smart-agricultural-technology

Data-driven model predictive control for precision irrigation management

Erion Bwambale a, b, c, *, Felix K. Abagale a, b, Geophrey K. Anornu d
a
West African Center for Water, Irrigation and Sustainable Agriculture (WACWISA), University for Development Studies, P. O. Box TL 1882, Tamale, Ghana
b
Department of Agricultural Engineering, University for Development Studies, P. O. Box TL 1882, Tamale, Ghana
c
Department of Agricultural and Biosystems Engineering, Makerere University, P. O. Box 7062, Kampala, Uganda
d
Department of Civil Engineering, Regional Water and Environmental Sanitation Center Kumasi (RWESCK), Kwame Nkrumah University of Sciences and Technology,
Kumasi, Ghana

A R T I C L E I N F O A B S T R A C T

Keywords: The future of agriculture faces a threat from a changing climate and a rapidly growing population. This has put
Data-driven models enormous pressure on water and land resources as more food is expected from less inputs. Advancement in smart
Model predictive control agriculture through the use of the Internet of Things and improvement in computational power has enabled
Precision irrigation
extensive data collection from agricultural ecosystems. This review introduces model predictive control and
System identification
describes its application in precision irrigation. An overview of the application of data-driven modelling and
model predictive control for precision irrigation management is presented. Model predictive control has been
applied in irrigation canal control, irrigation scheduling, stem water potential regulation, soil moisture regula­
tion and prediction of plant disturbances. Finally, the benefits, challenges, and future perspectives of data-driven
model predictive control in the context of irrigation scheduling are presented. This review provides useful in­
formation to researchers and agriculturalists to appreciate and use data collected in real-time to learn the dy­
namics of agricultural systems.

1. Introduction in space and time, in the right quantities to compensate for losses. This is
possible through effective monitoring and optimal control strategies,
The current and future generations face significant challenges in reducing pumping costs.
ensuring that nutritious food is sustainably produced from limited land Over the years, there has been a paradigm shift from traditional
and water resources. The FAO’s food and agriculture report of 2020 irrigation methods to smart irrigation systems. This has somewhat
posits that 40% of the world population are inhabitants of water-scarce improved the water use efficiency by reducing conveyance losses.
agricultural areas; of these, 37% inhabit agricultural zones with severe However, irrigation control is still a challenge due to the complex nature
water scarcity [27,51]. Coupled with the rising population indices, of agricultural systems. For example, most irrigation systems are
meeting the food demand by 2050 will need a 70% increase in food designed based on historical climatic data, and irrigation schedules are
production [28]. In addition to developing quick maturing and developed based on this data. Precision agriculture has been facilitated
high-yielding plant varieties, scientists need to ensure that less water is by the tremendous advancement in the agricultural Internet of Things
used to produce more food. It is estimated that about 70% of the water (IoT) and Wireless Sensor Networks (WSN) through remote sensing [32,
abstracted for irrigation is lost through conveyance losses and poor 69]. The controlled monitoring of agricultural systems has enhanced the
water allocation methods [76]. This means that a lot of water is pres­ sapience of the changing dynamics of the water, plant and soil envi­
ently used to produce a unit of food. Improving water use efficiency in ronment throughout the cropping season [5]. With advances in Big data
irrigation systems requires intelligent irrigation monitoring and control analytics, more agricultural systems are becoming data-driven for
systems to ensure that no water is wasted and precise water application decision-making purposes rather than relying on heuristic physics-based
is achieved [15]. Sustainable precision irrigation presents a timely so­ models [68].
lution to water wastage in irrigated agriculture by ensuring that inten­ Sustainable irrigation necessitates the adoption of irrigation control
ded irrigation amounts are applied at the right time and place. Precision strategies that precisely direct irrigation water to the plant’s root zone.
irrigation scheduling is striving to achieve efficient water use per plant, Boman et al. [11] observed improved water, energy, and fertilizer use

* Correspondence author.
E-mail address: [email protected] (E. Bwambale).

https://doi.org/10.1016/j.atech.2022.100074
Received 31 March 2022; Received in revised form 21 May 2022; Accepted 26 May 2022
Available online 29 May 2022
2772-3755/© 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

efficiency when precision irrigation control strategies are implemented. techniques aided by machine learning and data science advancements.
Precision irrigation control strategies are divided into two, namely, Table 1 summarizes the different types of MPC since 1980. Fig. 1 pre­
closed-loop systems and open-loop systems. Whereas open-loop systems sents the evolution of model predictive control.
apply a preset action like in simple irrigation timers, closed-loop systems There has been a progression from the past decades in the category of
receive feedback from sensors, make decisions and implement the systems where model predictive control is applied. Literature has re­
resulting findings in the irrigation system [15]. Several authors have ported a significant rise in MPC application in mechanical and electrical
reviewed and classified closed-loop irrigation control strategies into systems [52]. Some of the application domains include suspension [34],
three, namely, linear control, intelligent control and optimal control [4, vehicle traction control [12], direct injection stratified charge engines
15,23]. Model predictive control has evolved over the past four decades [35], Grain drying processes [82], traffic management [48], automatic
with advances in real-time data measurements and an increase in boats for aquaculture [81], modelling temperatures in buildings [25],
computational power. amongst others. This is facilitated by the precedent developments,
Model Predictive Control (MPC) refers to a category of advanced which enable MPC implementation on hardware, making it faster than
computer-controlled algorithms that use an explicit process model to traditional processes.
predict a plant’s future response [23]. Developed in the 1960s, Model
Predictive Control emanates from optimal control. The basic principle of 2.2. Main components of model predictive control
MPC is to use a dynamic model to predict system behavior and optimize
the prediction to decide the control move at the current time [71]. In The key to effective implementation of a control strategy is under­
addition to its flexibility, Model predictive control repeatedly solves standing how model predictive control works. Model predictive control
constrained optimal control problems online ([57]b). The ability to has seven essential components (Fig. 2): prediction, receding horizon,
handle multivariate processes and address state and input constraints modelling, performance index, degrees of freedom, constraint handling,
has made MPC indispensable in modern manufacturing industries [23, and multivariable [73].
56,55,70]. In a control problem, the model predictive controller’s goal is Prediction: Model predictive control considers the future implica­
to compute the plant input to follow the desired reference [60]. MPC tion of current control actions by computing the predicted behavior over
uses a plant model to predict future plant output behavior and an a horizon. Predictions must capture all the system’s transient and
optimizer that ensures that the predicted plant output tracks the desired steady-state behavior [73]. Therefore, the prediction horizon dictates
reference [15,60] how far the future state will be predicted.
MPC has been widely studied and applied in processing industries Receding horizon: This is the horizon over which system dynamics
([4,23,33]; F. [38,52]; L. [78]). However, in the agricultural sector, not are predicted. After defining the optimal trajectory of the future state,
much has been reported on the application of model predictive control the actual control input to the plant only takes the first sample of the
in modelling dynamic agricultural systems. The most recent review by control signal, neglecting the rest of the trajectory [78].
Ding et al. [23] focused on model predictive control applications in Modelling: Prediction of a system’s future state requires a plant
agriculture in general. [23] assert that the application of MPC to agri­ model. A good dynamic model will give a consistent and accurate pre­
culture can yield significant productivity and efficiency benefits despite diction of the future. A mode of the system shows the dependence of the
its limited use in the past years. However, no review of data-driven output on the current measured variable and the present/future inputs.
model predictive control in precision irrigation applications has been Performance index: Performance index measures the numerical
reported. MPC has been applied to agriculture, but it has not been definition of the best input trajectory. Performance indices of a model
applied in all respects. This work builds upon existing reviews in the change with time as the system’s internal model gets better over time.
field of agriculture with a particular focus on precision irrigation. This Performance indices must therefore be realistic and matched with model
review presents an overview of model predictive control in section 2; accuracy.
data-driven MPC can be done through system identification, machine Degree of freedom: Degrees of freedom describe the complexity of
learning, and iterative learning control, as discussed in section 3. Section input trajectories. Brownlee [13] defined degree of freedom as the sum
4 presents the specific application domains of data-driven MPC in irri­ of parameters in the model that are determined from data. This is in­
gation systems. The challenges and future perspectives of data-driven clusive of the coefficients of the model and the data used to calculate the
MPC are discussed in section 5. Finally, the conclusion and future error of the model.
research are presented. Constraint handling: Model predictive control embeds constraints
into the strategy development. The proposed input trajectory is optimal
2. Overview of model predictive control while satisfying constraints. The systematic embedding of constraint
information is critical to effective and robust closed-loop behavior.
2.1. Historical perspective of model predictive control Multivariable: Almost all dynamic systems have numerous inputs
and outputs. Model predictive control can handle multi-input-multi-
The concept of model predictive control dates way back in the 1960s output systems (MIMO) systematically. In traditional control like Pro­
to 1970s [66]. However, MPC found its way into process industries until portional Integral Derivative (PID), it is complex to design MIMO sys­
the 1980s [23]. Since then, model predictive control has undergone tems because limited data about the plant is used in the model design,
several stages of development. The first stage involves classical model and interaction becomes cumbersome. On the other hand, model pre­
predictive control between 1980 and 1990 and mainly solves multi­ dictive control algorithms require a model and thus utilize more data,
variable constraint control problems [52]. As a result of the failure to making it easier to handle MIMO systems.
handle nonlinear systems in process industries, improved MPCs evolved
towards the end of the 20th century giving more computational power 2.3. Theoretical formulation of model predictive control
with an extraordinary ability to handle constraints. This phase saw the
continued penetration of the commercial MPC algorithms into various A model predictive controller is designed based on the state space
industries and a sound theoretical foundation for it. In the 1st decade of equation of the process dynamics model as described by Rawlings et al.
the 21st century, latest MPC evolved as many industries adopted model [71]. A state-space model is a probabilistic graphical model that de­
predictive control [52]. The latest MPC methods reduced computation scribes probabilistic dependence between the latent state variable and
time by decentralizing large-scale problems, reducing computation time the observed measurement [16,20]. Model predictive control solves an
directly, or simplifying computational processes [23]. The fourth phase optimal control problem over a receding horizon, subject to system
has seen the evolution of data-driven model predictive control constraints, to determine the next control action ([43], 2018). The

2
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

Table 1
Historical perspective of model predictive control.
MPC Examples Characteristics Reference

Classical Dynamic matrix Model algorithm Generalized The first-generation model predictive Its major setback was [66] [71] [23]
MPC control control predictive control strategy aimed to solve industrial inability to handle
control multivariable control challenges. nonlinear systems.
Improved Adaptive MPC Robust MPC Nonlinear MPC Improved model predictive control solve [18,23,36,
MPC the problem of robustness associated with 39,78]
classical MPC. It was able to handle
nonlinear systems.
Latest MPC Hybrid MPC, Distributed MPC Explicit MPC Customized optimization of algorithms ([47,52,
Tube-based MPC, because of improved computing power. 83,85])
Stochastic MPC
Data- Robust data- Model of the system Requires real- High computational power required Enabled by ([9,10,14,
Driven driven MPC derived from time data advancement in IoT and 42,47,52,
MPC experimental data collection WSN technologies. 72,77,83,
85])

Fig. 1. Evolution of model predictive control.

optimization is iterated at each time step, and the control law is updated implicit feedback control law.
Fig. 3a . ( ) ( ⃒ )
K xj = u j + 1⃒xj = uj+1 (2)
Kaiser et al. [44] formulates a receding horizon control problem as an
open-loop optimization for every time step with an optimal sequence of The cost optimization at each timestep is described as minimizing a
control inputs u (Fig. 3b ) performance index with up to three terms; an output penalty, an input
( ⃒ ) penalty, and an input rate penalty;
u ⋅⃒xj := {uj+1 , …, uj+k , …, uj+mc (1)
[ m ( )]
∑ p− 1 ∑
m c− 1
Over the control horizon Tc = mc Δt given the current measurement J= ‖̂ x j+mp ‖2Qm + x j+mp ‖2Q +
‖̂ ‖
⌢ 2
‖ +‖ Δ
⌢
‖
2

xj that minimizes a cost J over the prediction horizon Tp = mp Δt, where p

k=0 k=1
u j+k Ru u j+k RΔu
Δt is the timestep of the model. The control horizon is less than or equal (3)
to the prediction horizon such that Tc ≤ Tp ; if Tc > Tp then the input u is
The minimized cost function J is subject to constraints on the inputs
assumed constant after that. The first control value uj+1 is then applied
and outputs;
and the optimization is reinitialized and repeated at each subsequent
⃒
timestep to solve for the unknown sequence u(⋅⃒xj ). This results in an

3
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

Fig. 2. Components of Model Predictive Control.

Fig. 3. Schematic of model predictive control with a moving horizon window. Adapted from [14].

( )T planetary motion. Initially, modelling of dynamic systems relied on a

um = uT0 , uT1 , …uTm− 1 u ≤ uk ≤ u
combination of high-quality measurements and expert intuition. With
xk+1 = f (xk , uk ) Δu ≤ Δuk ≤ Δu vast data and increasing computational power, the automated discovery
of governing equations and dynamical systems is a new and exciting
yk+1 = g(xk+1 ) + bk+1 y ≤ yk ≤ y (4) scientific paradigm. Data-driven models require automatic data collec­
tion, as they can react in real-time to changes in the input variables [31].
The data-driven models’ response can create a feedback loop into a
2.4. Data-driven model predictive control larger online system. However, automatic data collection is associated
with some challenges, and thus, characteristics of big data, namely,
Data-driven control systems are broadly classified under control volume, velocity, variety, value and veracity (5Vs), need to be consid­
systems. The identification of the process model and the design of the ered (Fig. 4).
controller are based entirely on experimental data collected from the
plant [9]. Learning dynamical systems models from data is a vital 3. System identification
challenge in mathematical physics, with a rich history dating back as far
as the time of Kepler and Newton and the discovery of the laws of System identification is a form of machine learning, where an input-

4
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

Fig. 4. The 5Vs of data-driven modelling.

output map of a system is learned from training data in a representation

xk+1 = F(xk , uk ) (6)
that generalizes the data that was not in the training set [14]. Ljung [53]
defined it as the art and science of building mathematical models of
dynamic systems from observed input-output data. System identification 3.2. Online and recursive system identification
is essential where first principles or physics-based modelling of the
system is not possible. Here, nothing is known about the system dy­ Online systems identification means that the algorithm is running
namics, also known as the black-box approach. Data is used to learn a during the operation of the physical system. Online system identification
mathematic model that mimics the input-output relationship using a algorithms estimate the parameters and states of a system model as data
model structure that represents the system behavior and parameter se­ is obtained in real-time or near real-time from measuring devices [24].
lection for fitting the data. A better understanding of the model is ach­ Referring to the agro-hydrologic balance equation, the process dynamics
ieved with system identification, and future prediction becomes easy. of the system can be described as one with three inputs, rainfall, irri­
Fig. 5 represents a flowchart for a system identification process gation, and crop evapotranspiration and one output, soil moisture, as
System identification can be done for linear systems, nonlinear sys­ shown in Fig. 6. The process dynamics model assumes that deep
tems and online and recursive systems. percolation in an irrigated agricultural system is proportional to soil
moisture.
The soil moisture dynamics of the system can be denoted as
3.1. Nonlinear system identification for control
ẋ(t) = P(t) + I(t) − b0 x(t) − ETC (t) (7)
Powerful model-based control techniques like linear optimal control
and model predictive control are aided by data-driven techniques that Where;
characterize the input-output dynamics from observed measurements b0 = Constant the denotes relationship between soil moisture and deep percolation
without relying on first principles modelling. Nonlinear systems iden­
tification is made possible due to high computing power and powerful Euler approximation theory is used on the soil moisture variations to
data-driven techniques. create a discrete model for the soil moisture.
Once a low order model of the input-output dynamics from actuation
u to measurements y and a full state x of the system is measured, then ẋ(t) =
θ(k + 1) − θ(k)
(8)
identification of dynamics f is made possible that satisfy Ts

d Where Ts is the sampling interval

x = f (x, u) (5)
dt The discrete-time dynamics then can be written as,
This then is discretized since data is collected in time steps and x(k + 1) − x(k)
control laws are digitally implemented. This state dynamics then Ts
= P(k) + I(k) − b0 θ(k) − ETC (k)
becomes.

Fig. 5. System identification process.

5
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

Fig. 6. Inputs and outputs of the process dynamics model.

x(k + 1) = b1 P(k) + b2 I(k) + b3 x(k) − b4 Kc ET0 (k) (9) The objective is to design a controller based on sensor measurements
of the system that can then drive the system through actuation. Exam­
Where; ples of machine learning methods include genetic algorithms, genetic
programming, reinforcement learning and adaptive neural networks
b1 , b2 , b3 , b4 are discrete coefficents (Fig. 8). These machine learning algorithms use biological principles like
Kc is the crop coefficient and varies according to the crop growth neural networks, evolutional algorithms, and reinforcement learning.
stage. Detailed information on machine learning control can be found in ([8,
A soil model can be developed over time by updating the model 14,26] and [64])
parameters each time step. For example, the algorithm could measure
irrigation and compare it with the predicted irrigation amount to pro­ 5. Iterative learning control
duce a prediction error. An online algorithm adjusts the model param­
eters to reduce the error. In the next step, a new set of measurements is Iterative learning control (ILC) is an efficient technique used to
recorded and compared with the model prediction. An error is again improve the performance of transient systems that operate repetitively
obtained and added to the old measurements and the process repeats [79]. The aim of ILC is to improve the transient response through input
itself. Online system identification is crucial where the model parame­ adjustment based on observed errors. A standard iterative learning
ters are time-variant, especially as is the case for the weather parameters control scheme assumes stable dynamics, and the system returns to the
in the crop evapotranspiration model. same initial conditions at the start of each trial of the same length. A
schematic of data-driven iterative learning control is presented in Fig. 9
4. Machine learning control [65].
An Iterative Learning Control takes the form
Machine learning is a rapidly developing field transforming our uk+1 (t) = uk (t) + γ ek (t+1) (10)
ability to learn and characterize dynamic systems [14]. Machine
learning makes the control of complex, nonlinear systems possible Where;
because of its high dimensional, nonlinear and optimization techniques uk = input to the system during the kth repetition,
[26]. For example, given a schematic in Fig. 7 with high dimensional ek = tracking error during the kth repetition and
dynamics with external disturbances to achieve a high-level objective γ = design parameter representing operations on ek .
function.

Fig. 7. Schematic of machine learning control.

6
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

Fig. 8. Sub-divisions of machine learning control.

Fig. 9. Iterative learning control process.

There has to be a convergence of the input signals as k becomes large. processes, model predictive control has been applied in product pro­
This will ensure perfect tracking through the iteration process. The rate cessing, agricultural production, greenhouses and irrigation systems
of convergence represents the desirable need for a rapid iterative [23]. For example, model predictive control has been applied in canal
learning process. Despite the uncertainty about the process dynamics, flow control and regulation, irrigation scheduling, stem water potential
good algorithm performance is desirable. The operation γ ranges from regulation, soil moisture regulation and precipitation and evapotrans­
simple scalar gains to sophisticated optimization computations and is piration prediction.
necessary to achieve design objectives.

5.2. Irrigation canal flow control and regulation

5.1. Applications of data-driven model predictive control in precision
irrigation management Model predictive control has found applicability to canal flow con­
trol and gate operation. The management objective of MPC for irrigation
Owing to the similarity of agricultural processes to industrial canals is to keep the water levels as close to the setpoints as possible

7
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

[45]. Therefore, a suitable model representing the canal water level strategy for gate opening at different intervals [49].
dynamic is needed. Furthermore, the models need to be set up in such a
way that they contain the appropriate dynamics of the water system for 6. Irrigation scheduling
water level regulation. In this regard, MPC has been applied to model the
behavior of the water movement in the open channel, maintaining Irrigation scheduling is the process of determining the frequency,
certain water levels at various locations and the water flows that influ­ duration and quantity of irrigation water to apply to meet the crop water
ence these water levels [29,30,63,79,80,84]. requirements [59]. In conventional irrigation systems, irrigation
Control structures are used to manipulate the water flows, through scheduling is determined through experience, observation, and heuristic
which the controller can achieve the management objective [45]. methods. On the other hand, precision irrigation systems rely on feed­
However, achieving this objective is not straightforward, as some back from sensing devices. Irrigation scheduling can be achieved
varying inflows and outflows disturb the water system. To predict the through weather-based, soil-based, or plant-based approaches. Precision
future water levels and flows as a result of disturbances and control irrigation systems aim at spatio-temporal irrigation scheduling
actions, the water system (canal reaches, structures, disturbances, depending on weather, soil, and plant physiological characteristics [3].
controller) needs to be modelled. Fig. 10 depicts a typical irrigation Model predictive control is used to perform irrigation scheduling
canal with water flowing by gravity and different offtakes along the using real-time field data to calibrate a crop and soil model and then
canal reach. using the calibrated model to determine optimum irrigation schedules
De Saint Venant partial differential equations Eqs. (11) and (12) [61]. Plant and soil real-time measurements are crucial to calibrate the
accurately describe the water flow dynamics in the irrigation canal. model during the growing stages of the crop as irrigation advances.
Considering the soil moisture balance model, the plant input is the
∂y 1 ∂Q q
+ + =0 (11) irrigation amount, whereas the plant output is the soil moisture deficit.
∂t T ∂x r
The crop evapotranspiration and precipitation values are considered
{ } disturbances as they cannot be controlled.
∂Q Q2 ∂A 2Q ∂Q ∂y
− + + gA − s +s + qv = 0 (12) Delgoda et al. [22], Lozoya et al. [56], and Saleem et al. [74] used
∂t A2 ∂x A ∂x ∂x 0 f
model predictive control to predict the frequency, duration and quantity
Where; y is the depth of water in m, of irrigation water using a soil moisture dynamics model. The authors
T the top width of the canal at the water surface in m, used a combined mechanistic and data-driven modelling approach to
Q is the water flow rate in the canal m3/s, x is the longitudinal dis­ describe the dynamics of the soil-plant-atmosphere system using sensing
tance on the flow direction in m, q the lateral outflow per unit length of devices for real-time feedback to the control algorithm. However, the
the channel in m2/s, v the velocity in m/s, authors neglected the effect of precipitation and crop water use on the
A is the wetted cross-sectional area, g the acceleration due to gravity system dynamics. Delgoda et al. [21] addressed the drawbacks noted in
(9.81 m/s2), so the channel bottom slope and sf is the friction slip of the the above model predictive control framework. The authors employed a
irrigation canal. disturbance affine feedback control approach and uncertainty modelling
Several scholars have used model predictive control in controlling techniques to account for the dynamic nature of rainfall and crop water
irrigation canal flows. Puig et al. [70] used model predictive control to use. Moreover, the study reported optimal system performance in a
generate flow control strategies from the water source to the consumer humid region where considerable uncertainties in climate variables
and irrigation areas in the Guadiana River. The results showed effec­ existed. Recently, Abioye, Abidin, Aman, et al. [2] and Abioye, Abidin,
tiveness in the use of model predictive control. Zhang et al. [83] Mahmud, et al. [2] used a data-driven model predictive control to
designed a non-cooperative distributed model predictive control algo­ schedule irrigation in a greenhouse irrigation experiment. The authors
rithm based on Nash optimality for water level regulation in irrigation used Laguerre functions in order to reduce the computation complexity
canals. The system simulation results showed the effectiveness of the brought about by input constraints.
proposed algorithm. To effectively deliver canal flow without fluctua­
tions, Han & Qiao [39]; Hashemy et al. [41,40]combined model pre­ 6.1. Stem water potential regulation
dictive control with online water storage to compensate for an existing
time delay and avoid wave disturbances. The results showed significant Another important aspect in precision irrigation management is the
improvement for canal operations employing automation. Recently, soil water potential. It determines the ease with which plants can extract
Kong et al. [50] used model predictive control toolbox to control gate water from the soil. Soil water potential is a measure of the energy status
interval and water level. The authors tested it on a simulation model of of the soil water relative to that of water at a standard reference [59]. On
an irrigation canal in Beijing consisting of 13 cascaded canal pools. The the other hand, stem water potential (SWP) is the direct measure of
authors affirmed that model predictive control is a useful control water tension within the plant [75]. Suter et al. suggested that plant

Fig. 10. Irrigation canal with control gates. Adapted from [45].

8
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

Fig. 11. Schematic of an agro-hydrological system. Adapted from [7].

moisture status needs to be determined through SWP measurements approximation of the soil moisture dynamics and the designed zone
rather than the soil moisture content. Chen et al. [18] developed a stem model predictive control suitability.
water potential model using data-driven model predictive control to
help reduce uncertainty in weather forecast errors. The authors formu­
6.3. Precipitation and evapotranspiration prediction
lated a state-space model that captures water dynamics in a
plant-root-soil system. The water status of the system was modelled by
One of the challenges in precision irrigation management is the
monitoring water flow in the soil, root and plant system. Precipitation in
scarcity of climate data. Precision irrigation requires real-time data to
the system was the water inflow, and evapotranspiration was the driving
aid in irrigation decisions. In developed countries, prediction systems
force in the system. The state-space model was linearized to reduce the
are used to predict future weather events, and this data is availed to
computation burden caused by robust nonlinear optimization. The au­
farmers for irrigation management decisions. In the absence of such,
thors used the formulation of a robust optimal control problem that
there is a need to bridge the gap using model predictive control to
maintained stem water potential within certain limits. The authors re­
quantity the sources of uncertainty in the soil moisture dynamics model.
ported a 7.9% reduction in the water consumption in almond trees using
To address this, Guo and You [37] used a novel data-driven local pre­
data-driven robust model predictive control.
cipitation and evapotranspiration prediction by implementing an arti­
ficial neuro-network (ANN). It was embedded in the model predictive
control toolbox and updated in real-time to formulate the dynamic un­
6.2. Soil moisture regulation
certainty set to account for weather prediction errors in the irrigation
control system. The authors reported effective control of the root zone
Irrigation aims to maintain the root zone soil moisture between field
soil moisture. A summary of studies conducted in the different appli­
capacity and the permanent wilting point (Fig. 10). When the soil
cation domains is presented in Table 2.
moisture goes above the field capacity, the soil becomes saturated, and
below the wilting point, the plant experiences water stress and eventu­
ally dies. Management allowable depletion of 50% is adopted for most 6.4. Challenges and future perspectives of data-driven modelling in smart
irrigation designs to ensure that the available moisture does not get irrigation
depleted before irrigation occurs. This available moisture in the root
zone depends on the plant’s effective root zone. Model predictive control Data collection that is representative of the real dynamic system is
has been used to minimize root zone soil moisture and irrigation challenging. When more data is provided, machine learning can be used
amounts within a specific threshold or at specific set points [22,55,62]. in data-driven modelling to fit data and make predictions when more
However, recent studies argue that a zone needs to be considered rather data is required. Some of the challenges encountered in data collection
than a reference set point to ensure maximum water extraction from the are discussed in this section.
root zone. The aim should be to regulate the soil moisture within the One of the major challenges affecting precision irrigation is the high
readily available moisture zone.
Mao et al. [57c] proposed a methodical approach to system identi­ Table 2
fication and root zone model predictive control design for soil moisture Summary of applications of MPC in irrigation.
control of agro-hydrological systems. First, the authors simulated the
Application Domain Author
soil water dynamics of the field from a mechanistic soil-water balance
Irrigation Canal control ([6,17,30,54,80]; R. [83,84,
model. The model consisted of a nonlinear partial differential equation
86])
with source and sink terms characterizing the root water extraction, Irrigation scheduling [1,2,16,37,46,55,67]
evaporation and transpiration, precipitation, and irrigation. A linear Soil moisture regulation ([7,57]c, [57,58]
parameter varying model was identified based on the input and output Soil water potential regulation ([19], 2021; [75])
data of the soil-water balance model, which was then used for zone Prediction of Precipitation and [37]
Evapotranspiration
model predictive control design. The authors report a satisfactory

9
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

cost of obtaining data in irrigation systems. To develop a data-driven Declaration of Competing Interest
model for smart irrigation, data about the soil, plant, and environment
need to be monitored. Plant sensors need to monitor the physiological The authors declare no conflict of interest
processes in plant-like crop water use. The different growth stages and
their effect on the crop factors need to be established. The climatic Funding information
factors that affect the rate of evapotranspiration need to be monitored in
real-time, otherwise relying on historical data that is not representative This research is being funded by Institut de Recherche pour le
of the real system. The data collection strategies and control methods are Développement (IRD), AFD and the West African Centre for Water,
discussed in [4,15]. The challenges relating to data availability range Irrigation and Sustainable Agriculture (WACWISA), University for
from sampling frequency, incomplete data, sensor malfunction, working Development Studies, Ghana.
conditions, communication exceptions or database shutdown. This can
affect the integrity of the experimental dataset collected, thereby Acknowledgement
resulting in poor model development.
In addition, developing models from data requires capturing a large This publication was made possible through support provided by the
volume of data to represent the real systems and capture any variations. West African Centre for Water, Irrigation and Sustainable Agriculture
For example, in irrigation, the components of the agro-hydrological (WACWISA), University for Development Studies, Ghana, with funding
model vary from time to time. This variation must be captured, which support from the Government of Ghana and World Bank through the
makes the data collection process time-consuming. This may involve African Centres of Excellence for Development Impact(ACE Impact)
monitoring the dynamics for the entire season or year to get a repre­ initiative. We would like to thank the unknown reviewers and editors for
sentative model for the dynamics. their enormous contributions to this paper.
Predictions are a key feature of data-driven models for irrigation
optimization and intelligent decision-making. System boundaries define
References
the capability of data-driven models. If the data is only a subsection of
the field, the model may fail to make accurate predictions for an entire [1] J. Abel Gomez, F. Capraro, C. Soria, M Pena, Design of an irrigation controller
irrigation field. Therefore, it is pertinent to define the system boundaries based on a water movement model in the soil, in: 2018 Argentine Conference on
Automatic Control, AADECA 2018, 2018, https://doi.org/10.23919/
and ensure model data development extends to the boundaries ensuring
AADECA.2018.8577455.
that only predictions made from the model boundaries are acted upon. [2] E.A. Abioye, M.S.Z. Abidin, M.N. Aman, M.S.A. Mahmud, S. Buyamin, A model
The application of model predictive control in irrigation is still predictive controller for precision irrigation using discrete lagurre networks,
limited compared to processing industries. Large water and irrigation Comput. Electron. Agric. 181 (2021), 105953, https://doi.org/10.1016/j.
compag.2020.105953. July 2020.
systems must reduce computation times and now incorporate data- [3] E.A. Abioye, M.S.Z. Abidin, M.S.A. Mahmud, S. Buyamin, M.K.I. AbdRahman, A.
driven model predictive control. In the future, there’s a need to model O. Otuoze, M.S.A. Ramli, O.D. Ijike, IoT-based monitoring and data-driven
soil moisture dynamics in open field agricultural systems as past studies modelling of drip irrigation system for mustard leaf cultivation experiment, in:
Inform. Process. Agricult., 8, 2021, pp. 270–283, https://doi.org/10.1016/j.
stopped at simulation or implemented in a controlled environment inpa.2020.05.004.
agricultural system where disturbances to the model are minimized. [4] E.A. Abioye, M.S.Z. Abidin, M.S.A. Mahmud, S. Buyamin, M.H.I. Ishak, M.K.I.
Model predictive control can be applied to diverse aspects of precision A. Rahman, A.O. Otuoze, P. Onotu, M.S.A. Ramli, A review on monitoring and
advanced control strategies for precision irrigation, Comput. Electron. Agric. 173
agriculture to enhance agricultural productivity in the future. These (2020), 105441, https://doi.org/10.1016/j.compag.2020.105441. August 2019.
application domains include aquaponics, hydroponics, viticulture, [5] E.A. Abioye, O. Hensel, T.J. Esau, O. Elijah, Precision irrigation management using
controlled environment agriculture, aquaculture, disease and pest con­ machine learning and digital farming solutions, AgriEngineering 4 (2022) 70–103,
https://doi.org/10.3390/agriengineering4010006. February.
trol, and mechanization systems.
[6] A. Álvarez, M.A. Ridao, D.R. Ramirez, L. Sánchez, Constrained predictive control of
an irrigation canal, J. Irrig. Drain. Eng. 139 (10) (2013) 841–854, https://doi.org/
7. Conclusion 10.1061/(asce)ir.1943-4774.0000619.
[7] M.A. Ayaz, T. Manzoor, A. Muhammad, MPC based soil moisture regulation of a
canal-connected crop field, IFAC-PapersOnLine 53 (5) (2020) 170–175, https://
Data-driven modelling in agriculture is on the rise due to the doi.org/10.1016/j.ifacol.2021.04.095.
advancement of Internet of Things technologies and improved compu­ [8] F. Barkrot, M. Berggren, Using machine learning for control systems in transform-
tational power. This article presents an overview of model predictive ing environments (2020).
[9] S.A. Bazanella, L. Campestrini, D. Eckhard, Data-driven controller design- The H2
control over the past four decades, and data-driven model predictive approach, A. I. r J. H. van S. r E. D. S. r M. T. r M. Krstic (Ed. Commun. Control Eng.
control is discussed. From the review, model predictive control has been (2012).
used in precision irrigation management, ranging from irrigation canal [10] J. Berberich, J. Köhler, M.A. Müller, F. Allgöwer, Data-driven model predictive
control: closed-loop guarantees and experimental results, At -
control, irrigation scheduling, stem water potential regulation, soil Automatisierungstechnik 69 (7) (2021) 608–618, https://doi.org/10.1515/auto-
moisture regulation, and precipitation prediction and evapotranspira­ 2021-0024.
tion. It is noted that for data-driven MPC to solve complex dynamic [11] B. Boman, S. Smith, B. Tullos, Control and Automation in Citrus Microirrigation
Systems, January 5, EDIS; University of Florida, 2018, https://doi.org/10.32473/
systems in irrigation, the availability of data, variability, boundary edis-ch194-2002.
conditions and model evaluation must be harmonized for one to come [12] F. Borrelli, A. Bemporad, M. Fodor, D. Hrovat, An MPC/hybrid system approach to
up with a good representative model of the system. There is more traction control, IEEE Trans. Control Syst. Technol. 14 (3) (2006) 541–552,
https://doi.org/10.1109/TCST.2005.860527.
research opportunity to explore on the application of data-driven
[13] J. Brownlee, A gentle introduction to degrees of freedom in machine learning,
modelling and controller development for predictive irrigation Mach. Learn. Mastery (2020) https://machinelearningmastery.com/degrees-of-
management. freedom-in-machine-learning/.
[14] Brunton, S.L., & Kutz, J.N. (2017). Data Driven Science & Engineering - Machine
Learning, Dynamical Systems, and Control (p. 572). databook.uw.edu.
8. Author contributions [15] E. Bwambale, F.K. Abagale, G.K. Anornu, Smart irrigation monitoring and control
strategies for improving water use efficiency in precision agriculture : a review, in:
Conceptualization, EB; methodology, EB; formal analysis, EB; Agric. Water Manage., 260, 2022, pp. 1–12, https://doi.org/10.1016/j.
agwat.2021.107324.
investigation, EB; writing original draft preparation, EB; writing—re­ [16] G. Cáceres, P. Millán, M. Pereira, D. Lozano, Smart farm irrigation: model
view and editing, FKA, GKA YK; visualization, FKA; supervision, FKA, predictive control for economic optimal irrigation in agriculture, Agronomy 11 (9)
GKA YK; project administration, FKA; funding acquisition, FKA, GKA (2021) 1–18, https://doi.org/10.3390/agronomy11091810.
[17] L. Cen, Z. Wu, X. Chen, Y. Zou, S. Zhang, On Modeling and constrained model
YK. All authors have read and agreed to publish the manuscript. predictive control of open irrigation canals, J. Control Sci. Eng. 2017 (2017),
https://doi.org/10.1155/2017/6257074.

10
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

[18] W.-.H. Chen, C. Shang, S. Zhu, K. Haldeman, M. Santiago, A.D. Stroock, F. You, [42] H. Jafarzadeh, C. Fleming, DMPC: a data-and model-driven approach to predictive
Data-driven robust model predictive control framework for stem water potential control, Automatica 131 (2021), 109729, https://doi.org/10.1016/j.
regulation and irrigation in water management, Control Eng. Pract. 113 (2021), automatica.2021.109729.
104841, https://doi.org/10.1016/j.conengprac.2021.104841. November 2020. [43] E. Kaiser, J.N. Kutz, S.L. Brunton, Sparse identification of nonlinear dynamics for
[19] W.-.H. Chen, C. Shang, S. Zhu, K. Haldeman, M. Santiago, A.D. Stroock, F. You, model predictive control in the low-data limit, in: Proceedings of the Royal Society
Theoretical exploration of irrigation control for stem water potential through A: Mathematical, Physical and Engineering Sciences 474, 2017, https://doi.org/
model predictive control, in: 2020 American Control Conference (ACC), 2020, 10.1098/rspa.2018.0335.
pp. 1992–1997, https://doi.org/10.23919/ACC45564.2020.9147296. 2020-July. [44] E. Kaiser, J.N. Kutz, S.L. Brunton, Sparse identification of nonlinear dynamics for
[20] Z. Chen, E. Brown, State space model, Scholarpedia 8 (3) (2013) 30868, https:// model predictive control in the low-data limit, in: Proceedings of the Royal Society
doi.org/10.4249/scholarpedia.30868. A: Mathematical, Physical and Engineering Sciences 474, 2018, https://doi.org/
[21] D. Delgoda, H. Malano, S.K. Saleem, M.N. Halgamuge, Irrigation control based on 10.1098/rspa.2018.0335.
model predictive control (MPC): formulation of theory and validation using [45] R. Kassing, Model Predictive Control of Open Water Systems With Mobile
weather forecast data and AQUACROP model, Environ. Model. Softw. 78 (2015) Operators, Delft University of Technology, 2018.
40–53, https://doi.org/10.1016/j.envsoft.2015.12.012. [46] R. Kassing, B. De Schutter, E. Abraham, Optimal control for precision irrigation of a
[22] D. Delgoda, S.K. Saleem, H. Malano, M.N. Halgamuge, Root zone soil moisture large-scale plantation, Water Resour. Res. (10) (2020) 56, https://doi.org/
prediction models based on system identification : formulation of the theory and 10.1029/2019WR026989.
validation using field and AQUACROP data Root zone soil moisture prediction [47] E. Kayacan, E. Kayacan, H. Ramon, W. Saeys, Distributed nonlinear model
models based on system identification : formulation of the theory and vali, in: predictive control of an autonomous tractor-trailer system, Mechatronics 24 (8)
Agric. Water Manage., 163, 2016, pp. 344–353, https://doi.org/10.1016/j. (2014) 926–933, https://doi.org/10.1016/j.mechatronics.2014.03.007.
agwat.2015.08.011. September. [48] B. Kersbergen, T. van den Boom, B De Schutter, Distributed model predictive
[23] Y. Ding, L. Wang, Y. Li, D. Li, Model predictive control and its application in control for railway traffic management, Transport. Res. Part C 68 (2016) 462–489,
agriculture: a review, Comput. Electron. Agric. 151 (2018) 104–117, https://doi. https://doi.org/10.1016/j.trc.2016.05.006.
org/10.1016/j.compag.2018.06.004. May. [49] L. Kong, X. Lei, H. Wang, Y. Long, L. Lu, Q. Yang, A model predictivewater-level
[24] B. Douglas, System identification, part 4: online and recursive system identification difference control method for automatic control of irrigation canals, Water
video - MATLAB, MATLAB Tech Talks (2021) https://in.mathworks.com/videos/ (Switzerland) 11 (4) (2019), https://doi.org/10.3390/w11040762.
system-identification-part-4-online-and-recursive-system-identification- [50] L. Kong, P. Song, Q. Ji, S. Zhu, J. Li, Water level predictive control in multi-cascade
1641279672000.html. pools with large control interval demand based on constraint methods, J. Hydrol.
[25] J. Drgoňa, J. Arroyo, I. Cupeiro Figueroa, D. Blum, K. Arendt, D. Kim, E.P. Ollé, (Amst.) 603 (2021), 127024, https://doi.org/10.1016/j.jhydrol.2021.127024. PC.
J. Oravec, M. Wetter, D.L. Vrabie, L. Helsen, All you need to know about model [51] W. Leal Filho, E. Totin, J.A. Franke, S.M. Andrew, I.R. Abubakar, H. Azadi, P.
predictive control for buildings, Annu. Rev. Control 50 (2020) 190–232, https:// D. Nunn, B. Ouweneel, P.A. Williams, N.P. Simpson, Understanding responses to
doi.org/10.1016/j.arcontrol.2020.09.001. August. climate-related water scarcity in Africa, Sci. Total Environ. 806 (2022), 150420,
[26] T. Duriez, S.L. Brunton, B.R. Noack, Machine learning control (MLC), Fluid Mech. https://doi.org/10.1016/j.scitotenv.2021.150420.
Its Applic. 116 (2017) 11–48, https://doi.org/10.1007/978-3-319-40624-4_2. Mlc. [52] J.H. Lee, Model predictive control: review of the three decades of development, Int.
[27] FAO, The state of food and agriculture 2020. Overcoming Water Challenges in J. Control Autom. Syst. 9 (3) (2011) 415–424, https://doi.org/10.1007/s12555-
Agriculture, In Fao, 2020 https://doi.org/https://doi.org/10.4060/cb1447en. 011-0300-6.
[28] FAO, The state of food and agriculture 2021. Making Agrifood Systems More [53] L. Ljung, Perspectives on system identification, Annu. Rev. Control 34 (1) (2010)
Resilient to Shocks and Stresses, In The Eugenics review, 2021, https://doi.org/ 1–12, https://doi.org/10.1016/j.arcontrol.2009.12.001.
10.4060/cb4476en. [54] F. López Rodríguez, K. Horváth, J. García Martín, J.M. Maestre, Mobile model
[29] A. Farhadi, A. Khodabandehlou, Distributed model predictive control with predictive control for the évora irrigation test canal, IFAC-PapersOnLine 50 (1)
hierarchical architecture for communication: application in automated irrigation (2017) 6570–6575, https://doi.org/10.1016/j.ifacol.2017.08.614.
channels, Int. J. Control 89 (8) (2016) 1725–1741, https://doi.org/10.1080/ [55] C. Lozoya, C. Mendoza, A. Aguilar, A. Román, R. Castelló, Sensor-based model
00207179.2016.1145358. driven control strategy for precision irrigation, J. Sens. 2016 (2016), https://doi.
[30] F. Fele, J.M. Maestre, S.M. Hashemy, D. Muñoz De La Peña, E.F Camacho, org/10.1155/2016/9784071.
Coalitional model predictive control of an irrigation canal, J. Process. Control 24 (4) [56] C. Lozoya, C. Mendoza, L. Mejía, J. Quintana, G. Mendoza, M. Bustillos, O. Arras,
(2014) 314–325, https://doi.org/10.1016/j.jprocont.2014.02.005. L. Solís, Model predictive control for closed-loop irrigation, in: IFAC Proceedings
[31] O.J. Fisher, N.J. Watson, J.E. Escrig, R. Witt, L. Porcu, D. Bacon, M. Rigley, R. Volumes (IFAC-PapersOnline) 19, 2014, pp. 4429–4434, https://doi.org/10.3182/
L. Gomes, Considerations, challenges and opportunities when developing data- 20140824-6-za-1003.02067. January.
driven models for process manufacturing systems, Comput. Chem. Eng. 140 [57] Y. Mao, S. Liu, J. Nahar, J. Liu, F. Ding, Regulation of soil moisture using zone
(2020), https://doi.org/10.1016/j.compchemeng.2020.106881. model predictive control, IFAC-PapersOnLine 51 (18) (2018) 762–767, https://doi.
[32] S. Fountas, B. Espejo-Garcia, A. Kasimati, N. Mylonas, N. Darra, The future of org/10.1016/j.ifacol.2018.09.271.
digital agriculture: technologies and opportunities, IT Prof. 22 (1) (2020) 24–28, [58] Y. Mao, S. Liu, J. Nahar, J. Liu, F. Ding, Soil moisture regulation of agro-
https://doi.org/10.1109/MITP.2019.2963412. hydrological systems using zone model predictive control, Comput. Electron. Agric.
[33] J.B. Froisy, Model predictive control-Building a bridge between theory and 154 (2018) 239–247, https://doi.org/10.1016/j.compag.2018.09.011. September.
practice, Comput. Chem. Eng. 30 (10–12) (2006) 1426–1435, https://doi.org/ [59] D.E. Eisenhauer, D.L Martin, D.M. Heeren, G.J. Hoffman, Irrigation Systems
10.1016/j.compchemeng.2006.05.044. Management, American Society of Agricultural and Biological Engineers (2021),
[34] N. Giorgetti, A. Bemporad, H.E. Tseng, D. Hrovat, Hybrid model predictive control https://doi.org/10.13031/ISM.2021.
application towards optimal semi-active suspension, in: Proceedings of the IEEE [60] MathWorks, Understanding model predictive control, part 2: what is MPC? Video -
International Symposium on Industrial Electronics, 2005, 2005, pp. 391–398, MATLAB, Videos and Webinars (2018) https://www.mathworks.com/videos/
https://doi.org/10.1109/ISIE.2005.1528942. ISIE 2005., I. understanding-model-predictive-control-part-2-what-is-mpc–1528106359076.
[35] N. Giorgetti, G. Ripaccioli, A. Bemporad, I. Kolmanovsky, D. Hrovat, Hybrid model html.
predictive control of direct injection stratified charge engines, IEEE/ASME Trans. [61] A.C. McCarthy, N.H. Hancock, S.R. Raine, Advanced process control of irrigation:
Mechatron. 11 (5) (2006) 499–506, https://doi.org/10.1109/ the current state and an analysis to aid future development, Irrigat. Sci. 31 (3)
TMECH.2006.882979. (2013) 183–192, https://doi.org/10.1007/s00271-011-0313-1.
[36] J.K. Gruber, J.L. Guzmán, F. Rodríguez, C. Bordons, M. Berenguel, J.A. Sánchez, [62] A.C. McCarthy, N.H. Hancock, S.R. Raine, Simulation of irrigation control
Nonlinear MPC based on a Volterra series model for greenhouse temperature strategies for cotton using Model Predictive Control within the VARIwise
control using natural ventilation, Control Eng. Pract. 19 (4) (2011) 354–366, simulation framework, Comput. Electron. Agric. 101 (2014) 135–147, https://doi.
https://doi.org/10.1016/j.conengprac.2010.12.004. org/10.1016/j.compag.2013.12.004.
[37] C. Guo, F. You, A data-driven real-time irrigation control method based on model [63] J. Menon, B.V. Mudgal, M. Guruprasath, S. Sivalingam, Control of an irrigation
predictive control, in: 2018 IEEE Conference on Decision and Control (CDC), 2018, branch canal using model predictive controller, Curr. Sci. 118 (8) (2020)
pp. 2599–2604. Cdc. 1255–1264, https://doi.org/10.18520/cs/v118/i8/1255-1264.
[38] F. Han, C. Zuo, W. Wu, J. Li, Z. Liu, Model predictive control of the grain drying [64] S. Moe, A.M. Rustad, K.G. Hanssen, Machine learning in control systems: an
process, Math. Probl. Eng. 2012 (2012), https://doi.org/10.1155/2012/584376. overview of the state of the art, In M. Bramer & M. Petridis (Eds.). SGAI-AI,
[39] H. Han, J. Qiao, Nonlinear model-predictive control for industrial processes: an Springer International Publishing, 2018, pp. 250–265. https://doi.org/10.1007/
application to wastewater treatment process, IEEE Trans. Ind. Electron. 61 (4) 978-3-030-04191-5_23.
(2014) 1970–1982, https://doi.org/10.1109/TIE.2013.2266086. [65] K.L. Moore, An Introduction to Iterative Learning Control, Csm Eges (2006).
[40] S.M. Hashemy, E.A. Majd, A. Firoozfar, J.M. Maestre, Improving operation of a [66] M. Morari, C.E. Garcia, D.M. Prett, Model predictive control: theory and practice,
main irrigation canal suffering from inflow fluctuation within a centralized model in: IFAC Proceedings Volumes 21, 1988, pp. 1–12, https://doi.org/10.1016/b978-
predictive control system: case study of Roodasht Canal, Iran, J. Irrig. Drain. Eng. 0-08-035735-5.50006-1.
142 (11) (2016), 05016007, https://doi.org/10.1061/(asce)ir.1943- [67] J. Nahar, S. Liu, Y. Mao, J. Liu, S.L. Shah, Closed-loop scheduling and control for
4774.0001087. precision irrigation † [research-article], Ind. Eng. Chem. Res. 58 (26) (2019)
[41] S.M. Hashemy, M.J. Monem, J.M. Maestre, P.J. Van Overloop, Application of an in- 11485–11497, https://doi.org/10.1021/acs.iecr.8b06184.
line storage strategy to improve the operational performance of main irrigation [68] S.A. Osinga, D. Paudel, S.A. Mouzakitis, I.N. Athanasiadis, Big data in agriculture:
canals using model predictive control, J. Irrig. Drain. Eng. 139 (8) (2013) 635–644, between opportunity and solution, Agric. Syst. 195 (2022), 103298, https://doi.
https://doi.org/10.1061/(ASCE)IR.1943-4774.0000603. org/10.1016/j.agsy.2021.103298. June 2021.
[69] M. Pramanik, M. Khanna, M. Singh, D.K. Singh, S. Sudhishri, A. Bhatia, R. Ranjan,
Automation of soil moisture sensor-based basin irrigation system, Smart Agricult.

11
E. Bwambale et al. Smart Agricultural Technology 3 (2023) 100074

Technol. 2 (2022), 100032, https://doi.org/10.1016/j.atech.2021.100032. [78] L. Wang, Model Predictive Control System Design and Implementation Using
December 2021. MATLAB. Advances in Industrial Control, Springer, 2009, p. 403.
[70] V. Puig, C. Ocampo-Martinez, J. Romera, J. Quevedo, R. Negenborn, P. Rodríguez, [79] Y. Wang, S. Riaz, Z. Bao, W. Zhang, Accelerated iterative learning control for linear
S. De Campos, Model predictive control of combined irrigation and water supply discrete time invariant switched systems, Math. Comput. Model. (2022). 2022.
systems: application to the Guadiana river, in: Proceedings of 2012 9th IEEE [80] A. Zafra-Cabeza, J.M. Maestre, M.A. Ridao, E.F. Camacho, L. Sánchez, Hierarchical
International Conference on Networking, Sensing and Control, ICNSC, 2012, distributed model predictive control for risk mitigation: an irrigation canal case
pp. 85–90, https://doi.org/10.1109/ICNSC.2012.6204896. 2012. study, in: Proceedings of the American Control Conference, 2011, pp. 3172–3177,
[71] B.J. Rawlings, Q.D. Mayne, M.M. Diehl, Model predictive control: theory, https://doi.org/10.1109/acc.2011.5990923.
computation, and design, in: Studies in Systems, Decision and Control, Second Edi, [81] J. Zhang, T. Sun, D. Zhao, J. Hong, Y. Sun, Robust model predictive control of the
1, Nob Hill Publishing, 2018, https://doi.org/10.1007/978-3-030-11869-3_4. automatic operation boats for aquaculture, Comput. Electron. Agric. 142 (2017)
[72] U. Rosolia, X. Zhang, F. Borrelli, Data-driven predictive control for autonomous 118–125, https://doi.org/10.1016/j.compag.2017.08.016.
systems, Ann. Rev. Control Robot. Autonom. Syst. 1 (1) (2018) 259–286, https:// [82] L. Zhang, H. Cui, H. Li, F. Han, Y. Zhang, W. Wu, Parameters online detection and
doi.org/10.1146/annurev-control-060117-105215. model predictive control during the grain drying process, Math. Probl. Eng. 2013
[73] J. Rossiter, Model Based Predictive Control: A Practical Approach, Taylor and (2013), https://doi.org/10.1155/2013/924698.
Francis Ltd, 2005. [83] R. Zhang, A. Liu, L. Yu, W.A. Zhang, Distributed model predictive control based on
[74] S.K. Saleem, D.K. Delgoda, S.K. Ooi, K.B. Dassanayake, L. Liu, M.N. Halgamuge, nash optimality for large scale irrigation systems, IFAC-PapersOnLine 28 (8)
H. Malano, Model predictive control for real-time irrigation scheduling, in: IFAC (2015) 551–555, https://doi.org/10.1016/j.ifacol.2015.09.025.
Proceedings Volumes (IFAC-PapersOnline), IFAC 46, 2013, https://doi.org/ [84] Z. Zheng, Z. Wang, J. Zhao, H. Zheng, Constrained model predictive control
10.3182/20130828-2-SF-3019.00062. PART 1. algorithm for cascaded irrigation canals, J. Irrig. Drain. Eng. 145 (6) (2019),
[75] B. Suter, R. Triolo, D. Pernet, Z. Dai, C. Van Leeuwen, Modeling stem water 04019009, https://doi.org/10.1061/(asce)ir.1943-4774.0001390.
potential by separating the effects of soil water availability and climatic conditions [85] H. Zhou, J. Liu, D.S. Jayas, Z. Wu, X. Zhou, A distributed parameter model
on water status in Grapevine (Vitis vinifera L.), Front. Plant Sci. 10 (2019) 1–11, predictive control method for forced air ventilation through stored grain, Appl.
https://doi.org/10.3389/fpls.2019.01485. November. Eng. Agric. 30 (4) (2014) 593–600, https://doi.org/10.13031/aea.30.10574.
[76] United Nations. The United Nations World Water Development Report 2021: [86] Z. Zhu, G. Guan, Z. Mao, K. Wang, S. Gu, G. Chen, Application of model predictive
Valuing Water, UNESCO, Paris, 2021. control for large-scale inverted siphon in water distribution system in the case of
[77] J. Wang, S. Li, H. Chen, Y. Yuan, Y. Huang, Data-driven model predictive control emergency operation, Water (Switzerland) 12 (10) (2020), https://doi.org/
for building climate control: three case studies on different buildings, Build. 10.3390/w12102733.
Environ. 160 (2019), 106204, https://doi.org/10.1016/j.buildenv.2019.106204.
June.

12