Internet of Things (IoT) and Agricultural Unmanned Aerial Vehicles (UAVs) in Smart Farming: A Comprehensive Review

Journal Pre-proof

Internet of Things (IoT) and Agricultural Unmanned Aerial Vehicles

(UAVs) in Smart Farming: A Comprehensive Review

Achilles D. Boursianis, Maria S. Papadopoulou,

Panagiotis Diamantoulakis, Aglaia Liopa-Tsakalidi,
Pantelis Barouchas, George Salahas, George Karagiannidis,
Shaohua Wan, Sotirios K. Goudos

PII: S2542-6605(20)30023-8
DOI: https://doi.org/10.1016/j.iot.2020.100187
Reference: IOT 100187

To appear in: Internet of Things

Received date: 13 November 2019

Revised date: 29 February 2020
Accepted date: 1 March 2020

Please cite this article as: Achilles D. Boursianis, Maria S. Papadopoulou, Panagiotis Diamantoulakis,
Aglaia Liopa-Tsakalidi, Pantelis Barouchas, George Salahas, George Karagiannidis, Shaohua Wan,
Sotirios K. Goudos, Internet of Things (IoT) and Agricultural Unmanned Aerial Vehicles
(UAVs) in Smart Farming: A Comprehensive Review, Internet of Things (2020), doi:
https://doi.org/10.1016/j.iot.2020.100187

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition
of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of
record. This version will undergo additional copyediting, typesetting and review before it is published
in its final form, but we are providing this version to give early visibility of the article. Please note that,
during the production process, errors may be discovered which could affect the content, and all legal
disclaimers that apply to the journal pertain.

© 2020 Published by Elsevier B.V.

 Internet of Things (IoT) and Agricultural Unmanned
Aerial Vehicles (UAVs) in Smart Farming: A
Comprehensive Review
Achilles D. Boursianisa , Maria S. Papadopouloua , Panagiotis
Diamantoulakisb , Aglaia Liopa-Tsakalidic , Pantelis Barouchasc , George
Salahasc , George Karagiannidisb , Shaohua Wand , Sotirios K. Goudosa
a
School of Physics, Aristotle University of Thessaloniki, AUTh Campus, 54 124,
Thessaloniki, Greece
b
School of Electrical and Computer Engineering, Aristotle University of Thessaloniki,
AUTh Campus, 54 124, Thessaloniki, Greece
c
Department of Agriculture, School of Agricultural Sciences, University of Patras,
Theodoropoulou Terma, 27 200 Amaliada, Greece
d
School of Information and Safety Engineering, Zhongnan University of Economics and
Law, Wuhan, Hubei 430073, China

Abstract
Internet of Things (IoT) and Unmanned Aerial Vehicles (UAVs) are two hot
technologies utilized in cultivation fields, which transform traditional farming
practices into a new era of precision agriculture. In this paper, we perform
a survey of the last research on IoT and UAV technology applied in agricul-
ture. We describe the main principles of IoT technology, including intelligent
sensors, IoT sensor types, networks and protocols used in agriculture, as well
as IoT applications and solutions in smart farming. Moreover, we present the
role of UAV technology in smart agriculture, by analyzing the applications of
UAVs in various scenarios, including irrigation, fertilization, use of pesticides,
weed management, plant growth monitoring, crop disease management, and
field-level phenotyping. Furthermore, the utilization of UAV systems in com-
plex agricultural environments is also analyzed. Our conclusion is that IoT
and UAV are two of the most important technologies that transform tradi-
tional cultivation practices into a new perspective of intelligence in precision

∗
Corresponding author: Achilles D. Boursianis
Email address: [email protected] (Achilles D. Boursianis)

Preprint submitted to Internet of Things March 6, 2020

agriculture.
Keywords: Internet of Things, Unmanned Aerial Vehicles, Smart Farming,
Wireless Sensor Networks, Agriculture, Survey

1. Introduction
During the last few years, agriculture is undergoing a fourth revolution
(Farming 4.0) by integrating Information and Communications Technologies
(ICT) in traditional farming practices [1]. Technologies, like Remote Sens-
ing, Internet of Things (IoT), Unmanned Aerial Vehicles (UAVs), Big Data
Analytics (BDA) and Machine Learning (ML) are particularly promising
and they can give a new breakthrough in agricultural practices [2], [3]. In
smart farming, a wide range of agricultural parameters can be monitored to
improve crop yields, to reduce costs and optimize process inputs, such as en-
vironmental conditions, growth status, soil status, irrigation water, pest and
fertilizers, weed management, and greenhouse production environment [4].
Smart farming is a green technology approach, since it reduces the ecological
footprint of traditional farming [3]. In precision agriculture, smart irrigation
and the minimal use of fertilizers and pesticides in agricultural crops can fur-
ther reduce leaching problems and emissions, as well as the impact of climate
change [3], [5].
IoT is one of the most revolutionary technologies in modern wireless com-
munications [6]. The basic concept is the interaction between a variety of
physical things or objects using specific addressing schemes to being con-
nected to the Internet. IoT technology can be applied in various vertical
markets including industry, transportation, healthcare, vehicles, smart home,
and agriculture [7]. In an agricultural environment, IoT devices provide use-
ful information on a wide range of physical parameters to enhance cultivation
practices [4]. The role of Wireless Sensor Networks (WSNs) in IoT technol-
ogy is of paramount importance since the vast majority of IoT applications
in various markets is based on wireless data transmission.
The use of unmanned aerial systems (UAS) as sensing and/or communi-
cation platforms is also a breakthrough technology with tremendous potential
in precision agriculture [8]. It was introduced as a low-cost alternative tech-
nique in environmental monitoring, in high spatial and temporal resolution,
and in imagery acquisition. Nowadays, the use of UAVs in agriculture is
expanding to assist cultivators with monitoring and decision support on the

2
farm [9]. UAS are utilized in various agricultural practices, such as irrigation,
fertilization, pesticides, weed management, etc. Moreover, the combination
of UAS technology with novel 3D reconstruction modeling techniques has
allowed to monitoring growth parameters of the crop on a plant-level basis.
The agricultural sector is evolving by integrating several key emerging
technologies towards a new and well promising era of agriculture-food pro-
duction, so-called “Agri-Food 4.0” [10]. IoT technology, smart sensors, re-
mote sensing, UAV technology, Low Power Wide Area Networks (LPWAN),
Long Range Wide Area Access Networks (LoRaWAN) and Wireless Sen-
sor Networks (WSN), etc. are included among all. These smart farming
technologies can be categorized in data acquisition, data analysis, and eval-
uation and precision application technologies [11]. Various combinations of
the aforementioned emerging technologies in smart agriculture have been
successfully applied in the continents of Europe, United States of America,
and Australia [12], [13], as well as in individual countries, like Brazil [14],
India [15], Italy [16], and Ireland [17].
The rest of this paper is organized as follows. Section 2 includes the main
objectives that motivated the authors for introducing this paper as well as
the contributions of this work. Section 3 briefly outlines sensor types and
wireless sensor networks commonly used in agriculture. The IoT technology
application in smart farming is discussed in Section 4. Section 5 describes the
basic IoT communication protocols in physical and link layers as well as cloud
computing service basics used in smart farming. The applications of UAV
technology in smart farming is thoroughly discussed in Section 6. Moreover,
the use-case of AREThOU5A project is briefly outlined (Section 7). Finally,
Section 8 includes the discussion of the paper and gives future trends and
challenges for IoT and UAV technology, whereas Section 9 concludes the
paper.

2. Motivation and Contribution

The motivation for preparing this comprehensive review issues from the
fact that IoT and UAV are the two key enabling technologies in smart farm-
ing. Undoubtedly, IoT and UAV will be the leaders of the fourth revolution
in smart agriculture for the upcoming years. The bibliographic analysis of
the review involved a keyword-based search for conference and/or journal
articles. The scientific research databases of IEEE Xplore and ScienceDirect,
as well as the scientific web search engine of Google Scholar were selected to

3
 Figure 1: Distribution of journal articles and conference papers that were analyzed.

perform this review. A total of 65 papers were analyzed. Fig. 1 illustrates

the distribution of journal articles and conference papers that were analyzed
in this paper review.
The main contributions of this research are summarized in the following.
In this work, we combine two key enabling technologies in a single paper
review, as these technologies play (now and in the future) a pivotal role in
the agricultural industry. It is expected that the agricultural industry, and
in general the agricultural economy, will be undoubtedly transformed by the
adoption of these two enabling technologies on a large-scale cultivation ba-
sis. Also, we outline enabling techniques incorporated with IoT technology,
we describe the main application of these techniques in Agriculture, and we
point out the benefits that derive by their utilization. Moreover, we perform
a detailed analysis of applications that using UAV technology in smart farm-
ing. This approach is applied not only from the technological point of view,
which is actually significant, yet of interest and usefulness only to workers in
the field, but from the agricultural point of view as well, notating all the key
aspects in this research field. To the best of the authors’ knowledge, this is
the first time that this approach is taking place in a review article. Finally,
the AREThOU5A project framework, as a use case of combined state-of-the-
art technologies, is briefly described. The use case is included in this review
work to exploit the importance of the incorporation of various emerging tech-
nologies, such as IoT technology, to promote rational use of irrigation water
in Agriculture.

4
3. Sensors and Sensor Networks In Smart Farming
This section provides a brief overview of sensor types and sensor networks
used in smart farming.

3.1. Basic and Intelligent Sensors

A sensor is a device that detects as input several types of physical or envi-
ronmental quantities, such as pressure, heat, light, pollution levels, humidity,
wind, and so on. The output of the sensor is in most of the cases an electrical
signal that is transmitted to a microcontroller and, consequently, to a net-
work for further processing. The evolution of basic to intelligent electronic
sensors is creating a revolution in how we collect data from the environment,
analyze them, make decisions for further investigation, and connect vast in-
telligence systems to enable new solutions and to accomplish tasks that we
have never been able to perform before [18], [19].
It is estimated that the first intelligent sensor was proposed in 1980 [20].
The authors described the development of silicon micro-sensors that can fit
on the same chip with a microcontroller. They presented various sensor types
and indicated their possible applications. However, Microelectromechanical
systems (MEMs) and Complementary MetalOxideSemiconductor (CMOS)
technology was not able at that time to create this integrated device. Nowa-
days, the technology is mature and intelligent sensors are the key factor for
the development of innovative IoT systems. Fig. 2 illustrates the basic com-
ponents of a sensor in IoT technology. As depicted in Fig. 2b, an intelligent
sensor usually consists of:

(a)

(b)

Figure 2: Block diagram of (a) Basic sensor and (b) Intelligent sensor.

5
 1. A sensing device that measures specific physical parameters from real-
world (temperature, humidity, pollution levels, etc.).
2. A signal conditioning to transform the signal into data that the intel-
ligent sensor can use.
3. A computational block, such as a processor or Digital Signal Processor
(DSP), that analyses and pre-process the measurements.
4. A communication block, such as a wireless transmitter, that exchanges
information with the gateway sensor node.

3.2. Sensor Types in Agriculture

Nowadays, technological innovations are reforming the traditional farm-
ing practices. Unmanned aerial systems, satellite imagery and sensor tech-
nology are remarkably transforming the agricultural industry. Smart farming
is the application of information and data technologies for optimizing com-
plex and multi-factorial farming systems [21]. Smart farming is not oriented
to perform precise measurements, but rather to access data and the applica-
tion of these data [22]. The main objective is to identify how the collected
information can be used in an “intelligent” way [23]. Smart farming is also
a concept that involves all farm operations [24]. Farmers can use smart
mobile devices, such as smartphones and tablets, to access real-time agricul-
tural data (soil and plant condition, irrigation, fertilization, weeds, climate,
weather, etc). As a result, farmers can act based on solid data and intervene
when necessary, rather than their traditional intuition.
There are various types of sensors that can be used to measure and cal-
culate the parameters of an agricultural field. The basic principles of these
sensors and their related specifications are briefly outlined below.

Soil water content sensor

Soil water content sensor is used in a wide range of scientific areas. Soil water
content is the ratio of the amount of water presents in the test soil to the
total amount of the test soil. It is expressed by the change in capacitance
value, which depends on the dielectric constant of the soil. It can range from
0 (completely dry) to the value of the materials’ porosity at saturation [25].
The measurements are soil type dependent; therefore the sensor must be cal-
ibrated for each location.

Soil Moisture Content Sensor

Soil moisture content sensor (sometimes referred to as soil volumetric water

6
content sensor) measures the water content of soil [26]. This sensor evaluates
the soil water tension or suction, which is a denotation of the plant root
system effort while extracting water from the soil. It can be used to estimate
the amount of stored water in the soil or how much irrigation is required to
reach a desired amount of water in the soil.

Soil Electrical Conductivity Sensor

The electrical conductivity (EC) of soil is used to measure the soil solute
concentration while assessing the soil salinity hazard [27]. Irrigation water
contains at least some salt. If salts build up around the root zone of a crop,
they injure plants, reduce yields and can cause long-term damage to the land
itself. The salt content of a soil is measured by using a soil electrical con-
ductivity sensor, which is based on Faradays law.

pH Sensor
pH is a measure of acidity and alkalinity in a given solution. In agricul-
ture, soil pH value ∈/ [5.5, 6.5] are considered as non-optimum as it indicates
lack of availability in soil nutrients. Farmers must regulate pH value by the
utilization of alkaline or acidic fertilizers, which also improves also farming
production [28]. If we consider that soil pH value varies within the field, one
of the best practices is to spatially apply the fertilizer according to the soil
pH variation.

Weed Seeker Sensor

Weed seeker is a self-contained unit, which is usually equipped with optical
and electronic components for weed detection and spraying. The unit con-
sists of an active light source and a chlorophyll identifying selective spray
sensor. The optical system allows the unit to detect and spray only weeds in
the field. The systematic use of the system can significantly reduce herbicide
usage. As a result, very limited use of chemicals is required, which consecu-
tively decreases application cost [29].

Temperature Sensor
In agriculture, soil temperature specifies the crop type that can be culti-
vated in a field. Temperature controls plant development processes such as
photosynthesis, transpiration, absorption, etc. Each crop has a different tem-
perature range in which it can grow. Outside this range, enzymes essential
for growth become inactive. The temperature sensor provides alerts if the

7
temperature goes above or below a certain threshold. The sensor is a p-n
junction diode of CMOS technology [30].

Wind Speed Sensor

The wind speed sensor designates the surface wind speed. In a field, it is
usually necessary to observe phenomena, such as modifications in wind speed
and direction. The wind speed sensor must be mounted at a suitable height,
depending on the crop [31].

Generally speaking, sensors can be classified into the following types: i)

optical, ii) mechanical, iii) electrochemical, iv) dielectric soil moisture, v)
airflow, and vi) location sensors [32]. Table 1 provides the most commonly
used sensor types and their application in agriculture.

3.3. Wireless Sensor Networks in Agriculture

Wireless sensor network (WSN) can be defined as a group of spatially and
dedicated sensors for monitoring the physical conditions of the environment,
temporarily storing the collected data, and transmitting the gathered infor-
mation at a central location [33]. In recent years an efficient Wireless Sensor
Network designed for smart farming is a point of interest for most of the re-
searchers. A WSN for smart farming consists of several nodes with wireless
communication capabilities. Fig. 3 illustrates a general WSN node archi-
tecture. Each sensor node comprises of sensors, microcontrollers, converters
and power sources [34]. A node can support one or more sensors to monitor
and measure different variables. In agricultural applications, it is essential
to measure several physical quantities related to soil, such as soil moisture
content, soil water content, soil temperature, soil electrical conductivity, as
well as weather condition parameters.
Nowadays, wireless sensor networks can be self-organized, self-configured
and self-diagnosed. WSNs are developed and installed to cope with problems
or to enable applications that traditional technologies cannot address. The
most obvious advantage in WSNs is the considerable reduction and simpli-
fication of wiring, which results in a more simplified final system. Typical
wiring cost in industrial applications has been estimated to US$ 130650 per
meter and the adoption of wireless technology could reduce this cost up to
80% [35].
Wireless sensors enable monitoring practices in dangerous, hazardous,
non-wired or remote areas. This technology provides practically unlimited

8
 Table 1: Summary of IoT sensor types used in Agriculture.

Sensor Sensor Function Application in

Type agriculture
Optical Photodiode Use of light to Determines clay,
measure soil prop- organic matter and
erties moisture content of
the soil
Mechanical Tensiometer Use of probes to Detects the force
measure soil com- used by the roots in
paction water absorption
Electro- Ion-Selective Elec- Use of electrodes Detects Nitrogen
mechanical trodes (ISE) and to detect specific Phosphorus Potas-
Ion-Selective Field ions in the soil sium (NPK) in
Effect Transistor soils
sensors (ISFET)
Dielectric Electrodes for Use of electrodes Measures soil water
soil Mois- Frequency Do- to assess moisture content
ture main (FDR) or levels
Time Domain
Reflectometry
(TDR)
Airflow Measurements can Measures soil air Classifies various soil
be made at fixed permeability types, moisture lev-
or dynamic loca- els, and soil struc-
tions ture/compaction
Location Global positioning Provides informa- The GPS provides
system (GPS) tion about the lat- precise positioning
itude, longitude,
and altitude

installation flexibility for sensors and increased network robustness. More-

over, wireless technology simplifies the maintenance of these networks and
reduces installation costs. One of the primary advantages of wireless sensors
is their portability. These sensors can be placed on a farm machinery, as in a
tractor, or on animals. As a result, farmers can measure critical parameters

9
 Figure 3: General WSN node architecture [34].

and monitor the entire field at any time. On the contrary, wired commu-
nication and sensors are rather expensive, require regular maintenance, and
deliver with a high failure rate in their connectors. To overwhelm the draw-
backs of wired sensors, the farm industry must develop new measures to
improve production performance, while further reducing costs and extending
the operational life cycle of new and used equipment [36].

4. Applications of IoT Technology in Smart Farming

Internet of Things (IoT) [6] refers to devices having unique identities and
capabilities to perform remote sensing, monitoring and temporarily storing
certain blocks of data. IoT is a cross-platform where devices are getting
smarter, the processing is becoming intelligent, and communication is result-
ing in informative [37]. IoT devices are also capable of having a real-time
exchange of data with other devices and applications, either directly or indi-
rectly. Any IoT based device consists of the following components:

• Input/ Output interface for Sensors

• Interface for connecting to the Internet

10
Figure 4: Stack diagram of papers from Scopus database with topic “IoT and Smart
Farming”.

• Interface for Memory and Storage

• Interface for Audio/ Video

A search in the Scopus database about IoT and Smart Farming reveals a
total number of 231 papers starting from the year 2012. The current research
trend towards IoT applications in Smart Farming is depicted in Fig. 4. It is
noteworthy that there is a growing research interest over recent years.
Smart Agriculture has the capability to provide a profitable and sustain-
able agricultural production [38], which will be based on a combination of
innovative solutions of new ICTs, such as IoT [39]. All the technologies used
in smart agriculture are complex, resulting from the complexity of the ac-
tivities performed by the farmers. Sensor-based irrigation systems provide a
promising solution to the farmers. IoT technologies can reduce the cost and
increase the scale of sensor-based irrigation systems through data collection
from sensor networks. IoT is a worldwide network based on standard com-
munication protocols. It utilizes several technologies for data collection from
physical measured quantities to IoT applications [40].
Internet of Things adopts various enabling techniques, such as wireless
sensor networks, cloud computing, big data, embedded systems, security pro-
tocols and architectures, communication protocols, and web services. Table 2

11
 Table 2: IoT Technologies in Smart Agriculture.

IoT Technology Application in Agri- Benefits in Agricul-

culture ture
WSNs: Sensor nodesSensors integrated to- Easy collection and man-
with radio communi-
gether to monitor var- agement of data gathered
cation capabilities
ious physical parame- from sensors
ters
Cloud Computing Provides shared pro- Easy collection and man-
(on-demand com- cessing resources and agement of data gath-
puting): A type data to computers and ered from cloud comput-
of Internet based other devices on de- ing services like agricul-
computing mand ture fields maps, cloud
storage, etc.
Big Data Analytics: Access to various forms Uncover patterns, corre-
The process of exam- of data types lations, market trends,
ining and analyzing customer preferences,
large data sets and other useful informa-
tion
Embedded Systems: System performs spe- Productions costs can be
A computer system cific tasks, such as reduced to a remarkable
that consists of both monitoring, controlling level which will increase
hardware and soft- and efficient manage- profitability and sustain-
ware ment of various activ- ability
ities
Communication These protocols facili- Easy collection and man-
Protocols: The tate exchange of data agement of tons of data
backbone of IoT over the network in gathered from sensors
systems to enable various data exchange and cloud computing
connectivity formats services, cloud storage,
etc.

depicts the main applications and benefits of each IoT technology in smart
agriculture.
There are several IoT systems in smart farming that reveal the great role
and the necessity of IoT-based technology and applications. In [41] the au-

12
thors proposed a Decision-Support System (DSS) based on the integration of
wireless sensors and actuation network (WSAN) technology. The suggested
actions were oriented to reduce water waste and to improve cultivation yield
following the weather conditions. In [42] the researchers presented a frame-
work, which was called AgriTech, to optimize several farming resources (wa-
ter, fertilizers, insecticides, and manual labor) in agriculture using IoT. The
farmers could monitor the crops and farmland from a distance using a mobile
terminal device. In [43], a model of a smart greenhouse was proposed, which
helped the farmers to carry out automatically the work on a farm. The proper
amount of nitrogen, phosphorus, potassium, and other minerals were applied
based on data from soil health cards by using drip fertigation techniques.
In [44], the authors proposed a mobile device system to remotely monitor
various soil characteristics. They utilized the inverse relation between soil
resistance and soil moisture to estimate soil moisture content.
Many IoT technology systems have been successfully applied to irrigation
and water quality monitoring in agricultural crops. In [45], an automated
irrigation system was designed and implemented. The system used a smart-
phone to capture and process imagery of the soil near the root zone of the crop
and estimated the water contents optically. In [46], the authors presented an
autonomous drip irrigation system that was operated and monitored by an
ARM9 processor. The system informed the user about any abnormal con-
ditions, like lack of moisture, temperature rise, and concentration of CO2 .
A real-time feedback control module was developed to monitor and control
all the activities of a drip irrigation system. In [47], a fully automated and
wireless controlled irrigation system was developed that mitigates subjective
decisions about irrigation volumes and timing. In [48], the authors investi-
gated an integrated system of IoT-based wetting front detector (IoT-WFD).
The implemented system was divided in two sub-systems, a sensor node, and
a web application server. In [49], the researchers developed an automated
system that uses the IoT technology to monitor and gather the data related
to the growth of crops in real time. The central unit extracted the recorded
data to establish the crop growth model, predicted the requirement of crops
in water for different growth periods, and applied the decision of irrigation.
Open Platform Communications (OPC) have been studied for agricul-
tural machinery telemetry in smart farming. In [50], the suitability of Open
Platform Communications Unified Architecture (OPC UA), which is the lat-
est version of OPC technology for agricultural machinery telemetry applica-
tions, was studied. The authors presented both the server-side system, which

13
was responsible for the combine harvester and the client system, which was
utilized for remote monitoring. Moreover, they reported that the subscrip-
tion latency was less than 250 ms when both the server and the client were
located in the same region.
IoT technology systems have been also used in various aspects of agricul-
tural crops in smart farming. In [51], the authors developed an intelligent
IoT system to monitor wheat diseases, pests, and weeds. The system could
diagnose and forecast wheat diseases, pests, and weeds, but also could pro-
vide recommendations to the farmers. In [52], an IoT system was designed to
restrict the use of insecticides and fungicides. The system provided disease
and pest data by utilizing prediction models based on correlation informa-
tion, so that farmers could quickly handle them. In [53], the authors applied
IoT humidity sensors to record the moisture in a Lingzhi mushroom farm.
The average humidity was reached up to 90-95%. The functional status of
sprinkler and fog pumps were monitored using a CCTV (Closed-Circuit Tele-
vision) system, while a microcontroller was used to control switching on and
off operations.
IoT applications have been utilized in livestock, too. In [54] the health
status of dairy cows was investigated using IoT and Wireless Body Area
Networks (WBANs). The Long Range (LoRa) off-body wireless channel
has been characterized at 868 MHz. Results demonstrated that large-scale
fading could be sufficiently described by a log-normal path loss model. In
[55], authors introduced a WSN for snail detection in the field. The proposed
network could be used both to trigger an alarm in case of snail tracking or to
further incorporate statistical models of snail detection with environmental
variables as temperature or humidity.
Nowadays, many platforms for IoT solutions in agriculture are commer-
cially available. These platforms provide data storage, data management and
data analytics. Table 3 summarizes the most popular IoT solutions for smart
agriculture. These IoT platforms have a common goal; to simplify the input
and utilize of data from all kinds of sources, using a common Application
Programming Interface (API). Such platforms usually implement functions
of data filtering and aggregation. The benefits of these IoT platforms in
smart agriculture are not clearly clarified [56]. Currently, there are some
challenges to overcome that still prevent the widespread use of IoT for smart
irrigation, such as the advanced IoT software platforms, the integration of
advanced sensors, etc. [57]. Furthermore, emerging IoT technologies can be
used to collate a vast amount of data. Such data can then be analyzed to

14
 Table 3: IoT Solutions in Smart Agriculture.

IoT Platform Services

OnFarm View critical information in the office or on the go in a
user-friendly dashboard
Phytech Plant-based application for optimized irrigation
Semios A powerful tool in yield improvement (insect assessment
and respond, disease and plant health conditions in real-
time)
EZFarm IBM Research team uses the Internet of Things to help
local farmers in Kenya optimize crop growth
KAA An open IoT cloud platform, fully customizable, based on
flexible microservices, provides a set of most wanted IoT
features out of the box
MbeguChoice The result of a collaboration between the Kenya Agri-
culture and Livestock Research Organization (KALRO),
the Kenya Plant Health Inspectorate Service (KEPHIS),
Kenyas crop seed companies, Agri Experience, Ltd., and
Kenya Markets Trust
Farmlogs Farm management software for automatic activity record-
ing
Cropx Provides an integrated hardware and software system for
measuring soil moisture, temperature and electrical con-
ductivity
Farmx Provides ground-truth sensing from the soil. Adds canopy
growth and water content imaging to see the impact of
your management on canopy health
Easyfarm Tracks crops, crop rotations, field histories, livestock, ma-
chinery, fuel, seed, and inventory

filter and calculate personalized crop suggestions for any agricultural farm.

15
5. IoT Protocols in Smart Farming
According to [58], the basic components of a smart farming architecture
are the network sensors, the gateways, the server, and, of course, the network.
The network sensors, which are a collection of sensors placed in farm swathe,
i.e., an area of 1 × 1 or 2 × 2 meters of farmland, communicate with the
gateway [58], which stores the data locally and sends data to the internet
according to predefined scheduling. The data from the gateway are sent
to the server via Remote Terminal Unit (RTU), which is responsible for
capturing data from sensors. For the communication between the gateway
and the server, the selection of the utilized radio access technology depends on
the application. The server can be implemented by using a cloud computing
infrastructure, which offers the advantages of low-cost implementation and
scalability. For the connection between the network sensor and the server
(and consequentially the users), the Transmission Control Protocol/ Internet
(TCP/IP) protocol can be used, which is compatible with the majority of
the network hardware components. It should be noted that the integration
of heterogeneous data from different sensors used in smart farming systems is
particularly challenging, due to software and hardware compatibility issues.

5.1. Wireless Communication Protocols for physical and link layer

The most relevant communication protocols that can be used are IEEE
802.11 (Wireless Fidelity - Wi-Fi), IEEE 802.16 (Worldwide Interoperability
Microwave Access - WiMax), IEEE 802.15.4 (Low-rate Wireless Personal
Area Networks - LR-WPAN), 2nd /3rd /4th generation of cellular networks
(2G/3G/4G), IEEE 802.15.1 (Bluetooth), LoRaWAN R1.0 (LoRA) [59], Sig-
Fox, and Narrowband Internet of Things (NB-IoT) [60]. Among them, LoRA
and NB-IoT are the two promising technologies, which comprise several tech-
nical differences. The selection of the communication protocol depends on
the desired achievable rate, the energy consumption, the range, the imple-
mentation cost, etc. NB-IoT is a Low Power Wide Area Network (LPWAN)
radio technology standard developed by 3GPP to enable a wide range of
cellular devices and services. It focuses specifically on indoor coverage, low
cost, long battery life, and high connection density. NB-IoT uses a subset
of the LTE (Long Terminal Evolution) standard but limits the bandwidth
to a single narrow-band of 200kHz. On the other hand, LoRaWAN offers a
very high range (20 miles) and very low energy consumption, but very lim-
ited data rates, i.e., 0.3-50 kbps. In fact, this is satisfactory for transmitting

16
measurement data from the most typical agriculture sensors. A comparison
of these protocols is provided in Table 4. Indicatively, for the communica-
tion between the sensor nodes and the gateway, the IEEE 802.15.4 protocol
has been proposed by [58]. In the same work, the use of General Packet
Radio Service (GPRS) or Enhanced Data Rates for Global System for Mo-
bile Communication (GSM) Evolution (EDGE) has been proposed for the
communication between the RTU and the server.
Table 4: Comparison of relevant wireless communication protocols.

Frequency Data Range Energy con- Cost

band rate sumption
WiFi 5 - 60 GHz High Medium High High
WiMAX 2 - 66 GHz High High Medium High
LR- 868/915 MHz, Low Low Low Low
WPAN 2.4 GHz
Cellular 865 MHz, 2.4 Flexible High Medium Medium
GHz
Bluetooth 2.4 GHz Medium Low Very low Low
LoRa 868/900 MHz Low High Very low High
SigFox 868/902/920 Low High Very low Medium
MHz
NB-IoT 800/900/1800 Low High Low High
MHz (EU)

5.2. Cloud Computing Service

Cloud computing can be used for a twofold purpose in smart farming
applications, i.e., i) to gather and store information that is transmitted from
the remote client and ii) to process the data and display the results to the
users. Data processing includes visualization, data analytics, decision mak-
ing, etc. The cloud service models can be categorized into three connected
layers, namely Infrastructure as a Service, Platform as a Service, and Soft-
ware as a Service, which correspond to the physical resources, the tools to
implement a wide range of applications, and the Internet-based applications
accessed by the end-users, respectively [61]. When developing and/or using

17
Figure 5: Stack diagram of papers from Scopus database with topic “UAV and Smart
Farming”.

a smart farming system, there are several issues that need to be considered,
such as the corresponding charges and the security protocols.

6. Applications of UAV Technology in Smart Farming

The use of UAV technology for gathering information that helps farmers
to taken decisions is currently a major research trend. The obtained results
from the Scopus database with keywords “UAV and Smart Farming” show
865 total papers from 2004 to the present day. Fig. 5 shows the distribution
of papers versus time. It is worth noting that the growth in the number of
papers over the last seven years is almost exponential.
One of the key emerging technologies in smart farming is remote sensing
[62]. The use of UAVs in agriculture along with extremely small MEMS
sensors makes agricultural drones very attractive. In 2014, the Massachusetts
Institute of Technology described agricultural UAVs as a green-tech tool
in smart farming [63]. Undoubtedly, UAVs have played an important role
during the last years in agricultural crops; moreover, it is expected that the
development of UAV technology will continue expanding its application in
smart agriculture [64]. In the following paragraphs, a systematic review of the
role of UAVs in smart farming is performed, thus highlighting the importance
and the dynamics of this green technology in precision agriculture.

18
 UAVs in agriculture have been deployed to address various issues in farm
production. In [65], the authors introduced a new method for registering im-
ages of agricultural crops taken by UAV. Based on their proposed model, they
presented a technique to align three-dimensional point clouds on the field,
thus reconstructing 3D models of the crop to monitor growth parameters on
a plant-level basis. A similar technique was applied in [66] to determine the
crop height of maize and sorghum plants in the field. A novel method to mon-
itor crop height of Sorghum plants using UAV and 3D model reconstruction
was also utilized in [67]. The authors reported that the Root Mean Square
Error (RMSE) of average individual sorghum height with hand-sampling field
data was 0.33 m. A rather dissimilar problem was addressed by the authors
in [68]. In their work, they used UAV and 3D model reconstruction to extract
leaf area index (LAI) in Soybean plants. Measured LAI predicted accuracy
corresponded with the one of a handheld device (R2 = 0.92) and correlated
with destructive LAI measurements (R2 = 0.89). The researchers in [69]
mounted a multi-spectral camera on a multi-rotor micro-UAV to simulta-
neously collect multi-spectral imagery and SoilPlant Analysis Development
(SPAD) values of maize. The derived results indicated that UAV multi-
spectral remote sensing technology is instructive for precision agriculture.
The authors in [70] used a UAV with an RGB digital camera to extract veg-
etation indices based on visible reflectance for evaluating crop biomass. An
acquisition platform to manipulate the farmland crop information collected
by UAV was presented in [71]. Moreover, the potential of UAV-based remote
sensing for aiding precision agriculture was examined in Indonesia [72]. The
proposed system produced Orthophoto images and Digital Elevation models
with accuracy up to 3 pixels or sub-meter discrimination.
The introduction of multiple-UAV systems in smart farming can provide
a new breakthrough in cultivation. Although there are still many technolog-
ical issues to be solved, there is a noticeable increase in the multiple-UAV
systems in smart agriculture. The authors in [73] developed a multi-UAV
system for agricultural fields using the distributed swarm algorithm. They
analyzed the performance of the proposed system and they compared the de-
rived results with a single-UAV system. Experimental results indicated that
the multi-UAV system performed better than the single-UAV one. The re-
searchers in [74] developed and presented an autonomous system for precision
agriculture based on the use of multiple-UAVs. In [75], the authors combined
Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) to address
the problem of mission planning of multiple-UAV systems, which is actually

19
a multi-objective optimization problem. They proposed a precision farming
system consisted of several components/agents/drones to accomplish com-
posite agricultural missions cooperatively. The objective of this work was to
utilize limited resources of machinery equipment in smart farming. Finally,
the combination of UAVs and unmanned ground vehicles (UGVs) was tested
in various agricultural fields [76].
Smart sensors in precision agriculture have also been integrated using
UAVs. The authors in [77] developed a smart flying sensor using UAVs and
mapped the volume of grain inside a trailer during forage harvesting. A
set of various sensors (Gas sensor, RGB-D sensor, Adafruit AMG8833 IR
thermal camera, Raspberry Pi model 3B) has been combined to produce a
comprehensive solution for the improvement of agricultural drones in [78].
This solution has been tested in the plowing process. Moreover, a supervised
learning model based on the Support Vector Machine (SVM) was used to
analyze and classify the data. In [79], the authors performed a feasibility
study of a harmless tiltrotor for specific smart farming applications using
Remotely Piloted Aircraft Systems (RPAS). An innovative approach of real-
time processing using UAVs in smart agriculture has been utilized in [80].
The researchers developed and presented a hyper-spectral flying platform
in detail with advanced processing capabilities in order to manage the data
acquisition and allow onboard processing of various vegetation indices. The
proposed system has been tested in a vineyard field.
One of the most important and useful applications of UAV technology in
smart farming is weed detection and management. A new method was intro-
duced in [81] to fuse low resolution multi-spectral and high-resolution RGB
images for weed detection in rice fields. The researchers reported, by utilizing
three different Neural Networks (NNs), that NN with the best weed detection
performance was the one having M/MGT 1 index between 80 and 108% and
M P 2 between 70 and 85%. In [82], the authors proposed a system that de-
tects vegetation, extracts features, and classifies results using Random Forest
(RF) technique to obtain an estimation of the crops and weeds distribution
in the field of sugar beet plants. Experimental results demonstrated that the
system can identify crops and weeds in the field individually. The authors in
[83] applied the same as in [82] machine learning technique to UAV imagery

1
The M/MGT index indicates the percentage of pixels found to be weed
2
The M P index shows the percentage of correct weed pixel detection

20
from sunflower and cotton fields by developing an automatic object-based
image analysis algorithm. The field of sugar beet plants was selected by the
researchers in [84], [85] to address the problem of selective weed treatment
in autonomous crop management. Their approach was based on semantic
weed classification with multi-spectral imagery obtained by a micro aerial
vehicle (MAV). Derived results reported performance of 0.8 F1-score3 for
weed detection. A new classification system for weed detection in vegetable
fields, such as spinach, beet, and bean, by applying Convolutional Neural
Networks (CNN) was introduced in [86], [87]. In these two studies, the au-
thors incorporated deep learning techniques with line detection to enhance
the classification procedure. They reported that the overall precision for the
bean, spinach, and beet was 69%, 81%, and 93%, respectively. Finally, a
new weed detection approach from RGB images acquired by low-cost UAV
imagery system was presented in [88], [89], [90].
UAV technology in smart farming has been tested and applied in agri-
cultural crops by extracting various vegetation indices. The authors in [91]
utilized single state vegetation indices (VIs) and multi-temporal VIs to pre-
dict the grain yield based on multi-spectral and digital images obtained by
UAV. In [92], they used imagery acquired with a UAV and a multi-spectral
sensor to test the correlation between reflectance and vegetation indices.
Several key parameters have been estimated using UAV technology in agro-
nomic wheat crops. Among all, vegetation indices and normalized difference
vegetation index (NDVI), as well as spectral vegetation index (SVI), green
area index (GAI) and high-resolution imagery have been evaluated to predict
grain yield [93], to monitor wheat breeding in a large trial [94], to monitor
key development stages of winter wheat [95], to detect plant stress caused by
yellow rust disease in winter wheat [96], to support decision making systems
for wheat and rapeseed crops [97], and to quantify plant density in wheat
crop [98].
UAV technology has been utilized also in various agricultural crops of
smart farming to manage yield. In [99], the authors applied UAV-based
smart agriculture technology to address various issues of palm oil planta-
tions, such as disease detection, yield prediction, pest monitoring, virtual
plantations creation, etc. The researchers in [100] integrated a WSN with a

3
F1-score is a measure of a test’s accuracy in the statistical analysis of binary classifi-
cation

21
smart UAV platform to perform real-time measurements that influence grape
yield and quality. The objective of this work was to optimize the produc-
tion efficiency in a cost-effective way. An innovative approach to support
farmers with automation tools and strategies for the analysis of fertilization
techniques in barley was introduced in [101]. In this work, the authors used
a UAV-based solution to capture aerial RGB images in order to estimate
nitrogen fertilization and barley yield. To achieve their objective, they de-
veloped a deep convolutional neural network to extract key features from the
images automatically. They reported an accuracy of 83% for the estimation
of nitrogen fertilization, and high correlation with low RMSE for yield esti-
mation. Finally, a deep convolutional neural network was developed for the
prediction of crop yield in [102].
Field-level phenotyping is considered in the literature as the main bot-
tleneck to improve efficiency in breeding programs [103]. The evolution of
IoT and UAV technology is expecting to mitigate this bottleneck in breed-
ing techniques of precision farming and precision phenotyping. To this end,
the authors in [104] examined the combination of UAV technology and image
analysis as a high-throughput phenotyping technique. For their experiments,
they planted four different maize cultivars. A similar research approach
was also applied in [105]. This work aimed to evaluate the use of multi-
spectral imagery obtained by UAVs as phenotyping tools. The authors in
[103] proposed an unmanned aerial system (UAS) high throughput pheno-
typing framework for the selection of cotton genotype. The researchers in
[106] estimated UAS-based phenotyping (chlorophyll content, nitrogen con-
centration, and LAI) of soybean combining multi-sensor data fusion, such as
high spatial resolution RGB, multispectral and thermal data, and extreme
learning machine (Partial Least Squares Regression (PLSR), Support Vector
Regression (SVR), and Extreme Learning Machine based Regression (ELR)).
A dual-camera high throughput phenotyping (HTP) platform on a UAV was
developed by the authors in [107] to collect multispectral images for large
scale soybean breeding fields. They applied a machine learning model based
on the Random Forest technique to measure crop geometric features and
they reported a 93% accuracy in classifying soybean maturity.
The application of UAV technology in smart farming has also been tested
in more complex problems. The researchers in [108] hypothesized that UAV
technology can be applied to estimate the number of existing flowers, the
quantity of nectar, and habitat potential for honeybees. Generally speaking,
flowers is a sensitive ecosystem, which is difficult to analyze. To overcome

22
Table 5: Summary of key innovations and UAV utilization endeavors in smart farming.

Key innovation /
UAV utilization endeavor References
3D crop modeling [65], [66], [67], [68]
Multi-spectral imagery [69], [70], [71], [72]
Multiple-UAV systems [73], [74], [75], [76]
Smart sensors integration [77], [78], [79], [80]
[81], [82], [83], [84], [85], [86], [87], [88],
Weed detection and management
[89], [90]
Vegetation indices extraction [91], [92], [93], [94], [96], [97], [98], [95]
Yield management [99], [100], [101], [102]
Field-level phenotyping [104], [105], [103], [106], [107]
Complex agricultural issues [108], [109], [110], [111], [112]

this, the authors proposed a methodology to analyze flowers in tree planta-

tions and they reported an estimation of 5.3 million flowers in a one-hectare
plantation. Irrigation management is also a complex issue in smart agricul-
ture. In [109], the authors acquired images from a thermal imaging camera
mounted on a UAV to evaluate the soil properties of sugar beet plants in
water. The use of pesticides in agriculture is also essential for crop yields, as
well as for the environment. The researchers in [110] developed and evaluated
an algorithm to self-adjust UAV routes during the chemical spraying proce-
dure in a crop field in order to reduce the waste of pesticides and fertilizers.
An extension of the previously mentioned algorithm was performed in [111],
by utilizing meta-heuristics (Genetic Algorithms, Particle Swarm Optimiza-
tion, Simulated Annealing, and Heal Climbing) in route adaptation of UAV.
Finally, the authors in [112] introduced an alternative approach to address
the problem of birds invasion in rice fields. They presented a UAV-based
system to detect and chase birds from cultivated fields by producing various
sounds, such as birds distress call or predators call.
Table 5 summarizes the related work that has been published in the
literature grouped by the key innovations and UAV utilization endeavors
in smart farming.

23
7. Use case: The AREThOU5A Project description
In this section, the main concepts of AREThOU5A4 project are briefly
outlined. AREThOU5A Project will exploit the state-of-the-art technolo-
gies and, in particular, the emerging developments in the field of Internet of
Things (IoT), low-power wide-access radio technologies, energy harvesting,
and machine learning, as a means to promote rational use of water resources
in agriculture. AREThOU5A will contribute to the acceleration of the Smart
Agriculture concept through a series of research and innovation actions fo-
cusing on the design, development, operation, and commercial exploitation
of relevant hardware/software and IoT applications. These activities will
eventually lead to a prototype end-to-end smart irrigation system deployed
and demonstrated in the field.
The aim of AREThOU5A project is to design and develop the rational
management of irrigation water in two agricultural farms using 5G-IoT ca-
pabilities; one in a vineyard field and the other in a perennial olive field.
In particular, the project provides a detailed description of an actual com-
plete integrated IoT-5G network. Its flexibility allows meeting completely
different performance requirements of real services for water irrigation. The
project describes the design of an IoT-based platform that can automate the
collection of environmental, soil and irrigation data.
The project framework is divided generally into three main layers, as
illustrated in Fig. 6.

Figure 6: The main layers of AREThOU5A project framework.

In the physical layer, all the requested information from the sensors in-
stalled on the field are gathered through WSNs and LoRaWAN networks,

4
https://arethousa.dataverse.gr

24
incorporating IoT and 5G key technologies. The network layer is responsible
for routing the collected data to the cloud. The application layer is fetching
all the available data to the end-users (as well as to the administrators of
the platform), providing various useful alerts or prediction values about ir-
rigation. The framework of the project AREThOU5A is designed based on
the capability of exploiting irrigation water in two farms (with grapes and
olives) using 5G-IoT smart sensor technology. The physical quantities that
will be primarily measured are the air temperature, relative humidity, and
soil moisture. The weather forecast will also be recorded in these two farms
for feeding the machine learning models.

Figure 7: The system architecture of AREThOU5A project framework.

Based on the design requirements of the system as defined above, the sys-
tem architecture of the AREThOU5A project is depicted in Fig. 7. It con-
sists of seven discrete subsystems with integrated functions and operations:
i) The measurement subsystem comprises of the sensor and the measurement
modules. The sensor module is responsible for capturing and recording the
environmental and plant-specific conditions, e.g. soil temperature, humid-
ity and, salinity, while the measurement module processes the derived data.
More particularly, the micro-controller is the heart of the module which con-
trols all the procedures. The radio module forwards the collected data to a
gateway using an unlicensed low-power and wide-area LoRa interface. The
subsystem is powered by an autonomous battery that is charging by a solar

25
panel and/or a novel RF energy harvesting circuit, ii) The routing subsystem
gathers the measurement data from the remotely deployed sensors (measure-
ment subsystem) and routes them to the next subsystem, operating as a
gateway by interconnecting the field deployment with the main system back-
end, iii) The server subsystem is deployed in the cloud and is responsible for
storing the raw measurement data, performing data processing routines and,
administrating the e-mail notification functionality, iv) The user-interface
subsystem is responsible for the user interaction of different operating levels
of the system through various input forms, such as web-based applications,
v) The access subsystem is liable to interconnect the remotely deployed nodes
in the field (measurement subsystem) with the gateway (routing subsystem)
using the LoRa radio technology, vi) The network subsystem interconnects
the gateway with the main system back-end using the LoRaWAN protocol
and, finally vii) The internet-based network subsystem provides end-to-end
connectivity among overall system and external subsystems.

8. Current Trends and Future Challenges

If we would like to clarify the current state, we would recognize that a
new type of transformation is occurring in the agricultural industry. Agri-
culture has moved on from the legacy decision support systems equipped
with a predefined time scheduling function in most of the cases, to a new
era of cultivation systems that include various innovative technologies, like
IoT, UAV, artificial intelligence, machine learning, and so on. Most of these
systems are in a prototype form (not commercial) and they usually address
to a specific (or a set of) cultivation process. To the best of our knowledge,
none of these systems is integrating a group of cultivation processes or even
the processes of the whole cultivation period (from sowing to harvest). As
also expected, some of the key enabling technologies exhibit more benefits in
various cultivation processes than others; yet all of them are difficult to be
adopted by the end-users (farmers).
The introduction of IoT technology in various farming practices has im-
proved the overall metrics in cultivation with respect to the yield, the quality
and quantity of the cultivated products, and the profit increase. IoT has
started to reveal its potential benefits to the end-users, since it can support
and assist in their decision making. On the contrary, IoT has to overcome
many barriers regarding technological complexity, parameterization, user-
friendliness, installation, performance, and system efficiency. Ultimately, the

26
key issue for the penetration on a large scale of IoT technology in agricul-
ture will be the addressing of improving cultivation practices that limit the
specific goals of the farmers.
UAV technology was firstly introduced in agriculture for remote monitor-
ing and observation. Although UAV has several limitations, mostly regarding
to the power autonomy and communication efficiency, which are still to be
addressed, the benefits of utilizing this technology have early emerged. More-
over, researchers, technology workers, but farmers as well, realize the multiple
advantages of applying UAV technology in various aspects of the agricultural
economy. Firstly, UAV plays (and will continue to play) an important role in
weed detection and management. The nature of this agriculture problem in
conjunction with the aerial capabilities of unmanned vehicles gives the op-
tion to end-users effectively manage weeds in cultivation. The introduction
of machine learning techniques to multi-spectral imagery data collected by
UAS, exploit even further the capabilities of UAV technology. Secondly, the
potential of features extraction of various vegetation indices by utilizing UAV
technology and multi-spectral imagery revealed the comparative advantage
of such a technology in cultivation practices. Another important characteris-
tic of the agricultural industry, that UAV technology contributes effectively,
is field-level phenotyping. With the employment of UAV systems, field-level
phenotyping will allow cultivators to estimate the overall plant growth and
predict the final yield in a more efficient way. Once again, UAV technology
has revealed the comparative advantage of such a technology in the field
against the use of static cameras. Finally, several complex agriculture is-
sues are managed to address (in an early stage) by the utilization of UAV
technology in the field.
Undoubtedly, the agricultural industry, and consequently agricultural
economy, is a highly challenging ecosystem of the global economy with high
potential. Therefore, it is expected that key emerging technologies, like IoT
and UAV will play a pivotal role in the future. Still, there are several agri-
cultural/cultivation issues to be addressed, such as weed intervention and
management, field-level phenotyping and multi- as well as hyper-spectral
imagery to manage diseases, irrigation water, fertilizers, pesticides, growth,
and yield on a plant-basis, 3D plant mapping and management, quality and
quantity improvement of the crop, and various complex agricultural issues.
In this challenging environment, key enabling technologies, such as IoT and
UAV, will efficiently and effectively contribute to smart farming practices
by meeting the following constraints: system simplicity and scalability, user-

27
friendliness, easy installation, and profit increase. As a result, these tech-
nologies will ultimately transform traditional farming practices into an evo-
lutionary agricultural ecosystem, by satisfying human needs in both urban
and rural environments.

9. Conclusion
It is apparent that the agriculture industry is undergoing an important
turning point during the last few years. The traditional practices in agricul-
ture are transforming into a new “intelligent” perspective in the process of
cultivation. The so-called “Agri-Food 4.0” is bringing a revolution in tra-
ditional farming by introducing ICT technologies to the field. The use of
WSNs, IoT sensors, UAS, along with optimization techniques and machine
learning algorithms can introduce a novel approach in precision farming lever-
aging the potential of agricultural crops. These key emerging technologies
can further improve crop yield, quality, reduce cost, and mitigate the ecolog-
ical footprint of traditional farming. Undoubtedly, smart farming technology
has lead cultivators to modern and novel practices by monitoring crops even
at a per plant level.
Irrigation is an essential process that influences crop production by sup-
plying water to the field. The AREThOU5A project will have to address
several challenges of precise water irrigation in two different farms, thus con-
tributing to the smart farming concept. The utilize of 5G-IoT technology
incorporated with energy harvesting and machine learning techniques will
deliver a prototype end-to-end smart irrigation system.
Smart farming has still several agronomic aspects to be properly ad-
dressed. These, among all, include precise irrigation with salts minimization,
efficient and rational fertilization and pesticide utilization by drastically re-
ducing pollution aquifer, adequate weed management, thus improving crop
yield, and efficient management of crop diseases in the field. Furthermore,
the monitoring of crop growth on a plant basis by constructing efficient and
precise 3D modeling algorithms, the efficiency of the nutrients from roots
to plants using non-intrusive techniques, the food traceability with mod-
ern approaches (e.g. blockchain technology), thus delivering quality certified
products to the consumers, and the accurate yield prediction in farms will
bring a novel aspect in future agricultural industry. It is expected that the
IoT technology, the UAV systems and the machine learning algorithms will
significantly contribute to the new era of the agri-food industry.

28
10. Acknowledgment
This research has been co-financed by the European Union and Greek na-
tional funds through the Operational Program Competitiveness, Entrepreneur-
ship and Innovation, under the call RESEARCH - CREATE - INNOVATE
(project code: T1EDK-05274).

References
[1] H. Sundmaeker, C. Verdouw, S. Wolfert, L. Prez Freire, Internet of food
and farm 2020, Digitising the Industry - Internet of Things Connecting
Physical, Digital and Virtual Worlds 2 (2016) 129–151.

[2] S. Wolfert, L. Ge, C. Verdouw, M.-J. Bogaardt, Big data in

smart farming a review, Agricultural Systems 153 (2017) 69 – 80.
doi:10.1016/j.agsy.2017.01.023.

[3] A. Walter, R. Finger, R. Huber, N. Buchmann, Opinion: Smart

farming is key to developing sustainable agriculture, Proceedings
of the National Academy of Sciences 114 (24) (2017) 6148–6150.
doi:10.1073/pnas.1707462114.

[4] R. Nukala, K. Panduru, A. Shields, D. Riordan, P. Doody,

J. Walsh, Internet of things: A review from farm to fork, in: 2016
27th Irish Signals and Systems Conference (ISSC), 2016, pp. 1–6.
doi:10.1109/ISSC.2016.7528456.

[5] S. Wong, Decentralised, Off-Grid Solar Pump Irrigation Systems in

Developing Countries—Are They Pro-poor, Pro-environment and Pro-
women?, Springer International Publishing, Cham, 2019, pp. 367–382.
doi:10.1007/978-3-319-75004-0-21.

[6] L. Atzori, A. Iera, G. Morabito, The internet of things:

A survey, Computer Networks 54 (15) (2010) 2787 – 2805.
doi:10.1016/j.comnet.2010.05.010.

[7] A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, M. Ayyash,

Internet of things: A survey on enabling technologies, protocols, and
applications, IEEE Communications Surveys Tutorials 17 (4) (2015)
2347–2376. doi:10.1109/COMST.2015.2444095.

29
 [8] C. Zhang, J. M. Kovacs, The application of small unmanned aerial
systems for precision agriculture: a review, Precision Agriculture 13 (6)
(2012) 693–712. doi:10.1007/s11119-012-9274-5.
[9] H. S. Abdullahi, F. Mahieddine, R. E. Sheriff, Technology impact on
agricultural productivity: A review of precision agriculture using un-
manned aerial vehicles, in: P. Pillai, Y. F. Hu, I. Otung, G. Giambene
(Eds.), Wireless and Satellite Systems, Springer International Publish-
ing, Cham, 2015, pp. 388–400.
[10] J. Miranda, P. Ponce, A. Molina, P. Wright, Sensing, smart and sus-
tainable technologies for agri-food 4.0, Computers in Industry 108
(2019) 21 – 36. doi:10.1016/j.compind.2019.02.002.
[11] A. T. Balafoutis, B. Beck, S. Fountas, Z. Tsiropoulos, J. Vangeyte,
T. van der Wal, I. Soto-Embodas, M. Gómez-Barbero, S. M. Peder-
sen, Smart Farming Technologies – Description, Taxonomy and Eco-
nomic Impact, Springer International Publishing, Cham, 2017, pp. 21–
77. doi:10.1007/978-3-319-68715-5-2.
[12] C. W. Zecha, J. Link, W. Claupein, Mobile sensor platforms: cate-
gorisation and research applications in precision farming, Journal of
Sensors and Sensor Systems 2 (1) (2013) 51–72. doi:10.5194/jsss-2-51-
2013.
[13] P. K. Freeman, R. S. Freeland, Agricultural uavs in the u.s.: potential,
policy, and hype, Remote Sensing Applications: Society and Environ-
ment 2 (2015) 35 – 43. doi:10.1016/j.rsase.2015.10.002.
[14] D. Pivoto, P. D. Waquil, E. Talamini, C. P. S. Finocchio, V. F. D.
Corte, G. de Vargas Mores, Scientific development of smart farming
technologies and their application in brazil, Information Processing in
Agriculture 5 (1) (2018) 21 – 32. doi:10.1016/j.inpa.2017.12.002.
[15] U. R. Mogili, B. B. V. L. Deepak, Review on application of drone sys-
tems in precision agriculture, Procedia Computer Science 133 (2018)
502 – 509, international Conference on Robotics and Smart Manufac-
turing (RoSMa2018). doi:10.1016/j.procs.2018.07.063.
[16] E. B. Mondino, M. Gajetti, Preliminary considerations about costs and
potential market of remote sensing from uav in the italian viticulture

30
 context, European Journal of Remote Sensing 50 (1) (2017) 310–319.
doi:10.1080/22797254.2017.1328269.

[17] J. Das V., S. Sharma, A. Kaushik, Views of irish farmers on smart

farming technologies: An observational study, AgriEngineering 1 (2)
(2019) 164–187. doi:10.3390/agriengineering1020013.

[18] N. Sabri, S. A. Aljunid, R. B. Ahmad, M. F. Malek, A. Yahya, R. Ka-

maruddin, M. S. Salim, Smart prolong fuzzy wireless sensor-actor net-
work for agricultural application, J. Inf. Sci. Eng. 28 (2012) 295–316.

[19] F. Kiani, A. Seyyedabbasi, Wireless sensor network and in-

ternet of things in precision agriculture, International Jour-
nal of Advanced Computer Science and Applications 9 (6).
doi:10.14569/IJACSA.2018.090614.

[20] S. Middelhoek, J. B. Angell, D. J. W. Noorlag, Microprocessors get

integrated sensors: Sensing devices and signal processing built into one
silicon chip portend a new class of smart sensors, IEEE Spectrum 17 (2)
(1980) 42–46. doi:10.1109/MSPEC.1980.6330262.

[21] O. Elijah, T. A. Rahman, I. Orikumhi, C. Y. Leow, M. N. Hindia, An

overview of internet of things (iot) and data analytics in agriculture:
Benefits and challenges, IEEE Internet of Things Journal 5 (5) (2018)
3758–3773. doi:10.1109/JIOT.2018.2844296.

[22] K. M. Divakar, Archana, K. R. Sushma, Iot technology in smart farm-

ing, International Research Journal of Engineering and Technology (IR-
JET) 5 (6).

[23] M. R. M. Kassi, I. Mat, A. N. Harun, Wireless sensor network in preci-

sion agriculture application, in: 2014 International Conference on Com-
puter, Information and Telecommunication Systems (CITS), 2014, pp.
1–5. doi:10.1109/CITS.2014.6878963.

[24] E. Alreshidi, Smart sustainable agriculture (ssa) solution underpinned

by internet of things (iot) and artificial intelligence (ai), arXiv preprint
arXiv:1906.03106.

[25] T. Lakhankar, H. Ghedira, M. Temimi, M. Sengupta, R. Khanbil-

vardi, R. Blake, Non-parametric methods for soil moisture retrieval

31
 from satellite remote sensing data, Remote Sensing 1 (1) (2009) 3–21.
doi:10.3390/rs1010003.

[26] P. Gaikwad, M. C. Devendrachari, R. Thimmappa, B. Paswan,

A. Raja Kottaichamy, H. Makri Nimbegondi Kotresh, M. O.
Thotiyl, Galvanic cell type sensor for soil moisture analysis, An-
alytical Chemistry 87 (14) (2015) 7439–7445, pMID: 26098202.
doi:10.1021/acs.analchem.5b01653.

[27] R. Ehsani, M. Sullivan, Soil electrical conductivity (ec) sensors, exten-

sion factsheet, aex565-02. (2002).

[28] K. W. T. Goulding, Soil acidification and the importance of liming

agricultural soils with particular reference to the united kingdom, Soil
Use and Management 32 (3) (2016) 390–399. doi:10.1111/sum.12270.

[29] A. Peruzzi, C. Frasconi, L. Martelloni, M. Fontanelli, M. Raffaelli, A

new prototype to perform precision treatments of activated steaming
to kill weed seed before sowing of organic vegetable, in: Proceedings of
the First International Conference on Robotics and Associated High-
technologies and Equipment for Agriculture: Applications of Auto-
mated Systems and Robotics for Crop Protection in Sustainable Preci-
sion Agriculture (RHEA-2011) [i.e. RHEA-2012]: Pisa, Italy, 2012, pp.
49–54.

[30] M. Futagawa, T. Iwasaki, H. Takao, M. Ishida, K. Sawada, H. Takao,

M. Ishida, K. Sawada, Fabrication of a multi-modal sensor with ph, ec
and temperature sensing areas for agriculture application, in: Sensors,
2009 IEEE, 2009, pp. 2013–2016. doi:10.1109/ICSENS.2009.5398294.

[31] W. M. Organization (Ed.), Guide to Meteorological Instruments and

Methods of Observation, Chairperson, Publications Board World Me-
teorological Organization (WMO), 2008, pp. 1.5–1 – 1.5–14.

[32] S. Li, A. Simonian, B. A. Chin, Sensors for agriculture and the food
industry, The Electrochemical Society Interface 19 (4) (2010) 41–46.
doi:10.1149/2.F05104if.

[33] W. Dargie, C. Poellabauer, Fundamentals of wireless sensor networks:

theory and practice, John Wiley and Sons, 2010, pp. 168183, 191192.

32
[34] N. Wang, Naiqian, M. Wang, Wireless sensors in agriculture
and food industryrecent development and future perspective, Com-
puters and Electronics in Agriculture 50 (1) (2006) 1 – 14.
doi:10.1016/j.compag.2005.09.003.
[35] Editorial: This changes everythingmarket observers quantify the rapid
escalation of wireless sensing and explain its effects, Sensors Magazine,
Wireless for Industry, Supplement to Sensors Magazine Summer (2007)
S6S8.
[36] W. W. Manges, G. O. Allgood, S. F. Smith, It’s time for sensors to
go wireless; part 2: Take a good technology and make it an economic
success, Sensors: The Journal of Applied Sensing Technology 16 (5)
(1999) 7080.
[37] P. Ray, A survey on internet of things architectures, Journal of King
Saud University - Computer and Information Sciences 30 (3) (2018)
291 – 319. doi:10.1016/j.jksuci.2016.10.003.
[38] A. Liopa-Tsakalidi, D. Tsolis, P. Barouchas, A.-E. Chantzi,
A. Koulopoulos, N. Malamos, Application of mobile technologies
through an integrated management system for agricultural production,
Procedia Technology 8 (2013) 165 – 170, 6th International Conference
on Information and Communication Technologies in Agriculture, Food
and Environment (HAICTA 2013). doi:10.1016/j.protcy.2013.11.023.
[39] S. K. Goudos, P. I. Dallas, S. Chatziefthymiou, S. Kyriazakos, A survey
of iot key enabling and future technologies: 5g, mobile iot, sematic
web and applications, Wirel. Pers. Commun. 97 (2) (2017) 1645–1675.
doi:10.1007/s11277-017-4647-8.
[40] L. Atzori, A. Iera, G. Morabito, Understanding the internet of things:
definition, potentials, and societal role of a fast evolving paradigm, Ad
Hoc Networks 56 (2017) 122 – 140. doi:10.1016/j.adhoc.2016.12.004.
[41] F. Viani, M. Bertolli, M. Salucci, A. Polo, Low-cost wireless monitoring
and decision support for water saving in agriculture, IEEE Sensors
Journal 17 (13) (2017) 4299–4309. doi:10.1109/JSEN.2017.2705043.
[42] A. Giri, S. Dutta, S. Neogy, Enabling agricultural automation to op-
timize utilization of water, fertilizer and insecticides by implementing

33
 internet of things (iot), in: 2016 International Conference on Informa-
tion Technology (InCITe) - The Next Generation IT Summit on the
Theme - Internet of Things: Connect your Worlds, 2016, pp. 125–131.
doi:10.1109/INCITE.2016.7857603.

[43] R. K. Kodali, V. Jain, S. Karagwal, Iot based smart greenhouse,

in: 2016 IEEE Region 10 Humanitarian Technology Conference (R10-
HTC), 2016, pp. 1–6. doi:10.1109/R10-HTC.2016.7906846.

[44] A. Na, W. Isaac, S. Varshney, E. Khan, An iot based system for remote
monitoring of soil characteristics, in: 2016 International Conference on
Information Technology (InCITe) - The Next Generation IT Summit
on the Theme - Internet of Things: Connect your Worlds, 2016, pp.
316–320. doi:10.1109/INCITE.2016.7857638.

[45] J. Gutirrez Jagey, J. F. Villa-Medina, A. Lpez-Guzmn, M. . Porta-

Gndara, Smartphone irrigation sensor, IEEE Sensors Journal 15 (9)
(2015) 5122–5127. doi:10.1109/JSEN.2015.2435516.

[46] G. Kavianand, V. M. Nivas, R. Kiruthika, S. Lalitha, Smart drip irri-

gation system for sustainable agriculture, in: 2016 IEEE Technological
Innovations in ICT for Agriculture and Rural Development (TIAR),
2016, pp. 19–22. doi:10.1109/TIAR.2016.7801206.

[47] R. Zaier, S. Zekri, H. Jayasuriya, A. Teirab, N. Hamza, H. Al-

Busaidi, Design and implementation of smart irrigation system for
groundwater use at farm scale, in: 2015 7th International Confer-
ence on Modelling, Identification and Control (ICMIC), 2015, pp. 1–6.
doi:10.1109/ICMIC.2015.7409402.

[48] P. Sureephong, P. Wiangnak, S. Wicha, The comparison of soil sensors

for integrated creation of iot-based wetting front detector (wfd) with
an efficient irrigation system to support precision farming, in: 2017
International Conference on Digital Arts, Media and Technology (IC-
DAMT), 2017, pp. 132–135. doi:10.1109/ICDAMT.2017.7904949.

[49] P. Zhang, Q. Zhang, F. Liu, J. Li, N. Cao, C. Song, The construction

of the integration of water and fertilizer smart water saving irrigation
system based on big data, in: 2017 IEEE International Conference on
Computational Science and Engineering (CSE) and IEEE International

34
 Conference on Embedded and Ubiquitous Computing (EUC), Vol. 2,
2017, pp. 392–397. doi:10.1109/CSE-EUC.2017.258.

[50] T. Oksanen, R. Linkolehto, I. Seilonen, Adapting an industrial

automation protocol to remote monitoring of mobile agricultural
machinery: a combine harvester with iot, IFAC-PapersOnLine
49 (16) (2016) 127 – 131, 5th IFAC Conference on Sensing, Con-
trol and Automation Technologies for Agriculture Agricontrol 2016.
doi:10.1016/j.ifacol.2016.10.024.

[51] S. Zhang, X. Chen, S. Wang, Research on the monitoring system of

wheat diseases, pests and weeds based on iot, in: 2014 9th Interna-
tional Conference on Computer Science Education, 2014, pp. 981–985.
doi:10.1109/ICCSE.2014.6926609.

[52] H. Lee, A. Moon, K. Moon, Y. Lee, Disease and pest prediction iot
system in orchard: A preliminary study, in: 2017 Ninth International
Conference on Ubiquitous and Future Networks (ICUFN), 2017, pp.
525–527. doi:10.1109/ICUFN.2017.7993840.

[53] O. Chieochan, A. Saokaew, E. Boonchieng, Iot for smart farm: A case

study of the lingzhi mushroom farm at maejo university, in: 2017 14th
International Joint Conference on Computer Science and Software En-
gineering (JCSSE), 2017, pp. 1–6. doi:10.1109/JCSSE.2017.8025904.

[54] S. Benaissa, D. Plets, E. Tanghe, J. Trogh, L. Martens, L. Van-

daele, L. Verloock, F. A. M. Tuyttens, B. Sonck, W. Joseph, In-
ternet of animals: characterisation of lora sub-ghz off-body wireless
channel in dairy barns, Electronics Letters 53 (18) (2017) 1281–1283.
doi:10.1049/el.2017.1344.

[55] D. Garca-Lesta, D. Cabello, E. Ferro, P. Lpez, V. M. Brea, Wire-

less sensor network with perpetual motes for terrestrial snail ac-
tivity monitoring, IEEE Sensors Journal 17 (15) (2017) 5008–5015.
doi:10.1109/JSEN.2017.2718107.

[56] P. P. Jayaraman, A. Yavari, D. Georgakopoulos, A. Morshed, A. Za-

slavsky, Internet of things platform for smart farming: Experiences and
lessons learnt, Sensors 16 (11). doi:10.3390/s16111884.

35
[57] C. Kamienski, J.-P. Soininen, M. Taumberger, R. Dantas, A. Toscano,
T. Salmon Cinotti, R. Filev Maia, A. Torre Neto, Smart water manage-
ment platform: Iot-based precision irrigation for agriculture, Sensors
19 (2). doi:10.3390/s19020276.
[58] S. Suakanto, V. J. L. Engel, M. Hutagalung, D. Angela, Sensor
networks data acquisition and task management for decision sup-
port of smart farming, in: 2016 International Conference on Infor-
mation Technology Systems and Innovation (ICITSI), 2016, pp. 1–5.
doi:10.1109/ICITSI.2016.7858233.
[59] P. P. Ray, Internet of things for smart agriculture: Technologies, prac-
tices and future direction, Journal of Ambient Intelligence and Smart
Environments 9 (4) (2017) 395–420.
[60] R. S. Sinha, Y. Wei, S.-H. Hwang, A survey on lpwa tech-
nology: Lora and nb-iot, ICT Express 3 (1) (2017) 14 – 21.
doi:10.1016/j.icte.2017.03.004.
[61] J. Lpez-Riquelme, N. Pavn-Pulido, H. Navarro-Helln, F. Soto-Valles,
R. Torres-Snchez, A software architecture based on fiware cloud for
precision agriculture, Agricultural Water Management 183 (2017) 123
– 135, special Issue: Advances on ICTs for Water Management in Agri-
culture. doi:10.1016/j.agwat.2016.10.020.
[62] M. Bacco, A. Berton, E. Ferro, C. Gennaro, A. Gotta, S. Matteoli,
F. Paonessa, M. Ruggeri, G. Virone, A. Zanella, Smart farming: Op-
portunities, challenges and technology enablers, in: 2018 IoT Vertical
and Topical Summit on Agriculture - Tuscany (IOT Tuscany), 2018,
pp. 1–6. doi:10.1109/IOT-TUSCANY.2018.8373043.
[63] C. Anderson, Agricultural drones, mit technology review, 2014, avail-
able from: https://www.technologyreview.com/featuredstory/526491/
agricultural-drones (accessed on june 18th, 2019). (2014).
[64] W. H. Maes, K. Steppe, Perspectives for remote sensing with unmanned
aerial vehicles in precision agriculture, Trends in Plant Science 24 (2)
(2019) 152 – 164. doi:10.1016/j.tplants.2018.11.007.
[65] N. Chebrolu, T. Lbe, C. Stachniss, Robust long-term regis-
tration of uav images of crop fields for precision agriculture,

36
 IEEE Robotics and Automation Letters 3 (4) (2018) 3097–3104.
doi:10.1109/LRA.2018.2849603.

[66] L. Malambo, S. Popescu, S. Murray, E. Putman, N. Pugh, D. Horne,

G. Richardson, R. Sheridan, W. Rooney, R. Avant, M. Vidrine, B. Mc-
Cutchen, D. Baltensperger, M. Bishop, Multitemporal field-based plant
height estimation using 3d point clouds generated from small un-
manned aerial systems high-resolution imagery, International Journal
of Applied Earth Observation and Geoinformation 64 (2018) 31 – 42.
doi:10.1016/j.jag.2017.08.014.

[67] A. Chang, J. Jung, M. M. Maeda, J. Landivar, Crop height mon-

itoring with digital imagery from unmanned aerial system (uas),
Computers and Electronics in Agriculture 141 (2017) 232 – 237.
doi:10.1016/j.compag.2017.07.008.

[68] L. Roth, H. Aasen, A. Walter, F. Liebisch, Extracting leaf area

index using viewing geometry effectsa new perspective on high-
resolution unmanned aerial system photography, ISPRS Journal
of Photogrammetry and Remote Sensing 141 (2018) 161 – 175.
doi:10.1016/j.isprsjprs.2018.04.012.

[69] L. Deng, Z. Mao, X. Li, Z. Hu, F. Duan, Y. Yan, Uav-based mul-

tispectral remote sensing for precision agriculture: A comparison be-
tween different cameras, ISPRS Journal of Photogrammetry and Re-
mote Sensing 146 (2018) 124 – 136. doi:10.1016/j.isprsjprs.2018.09.008.

[70] R. Jannoura, K. Brinkmann, D. Uteau, C. Bruns, R. G. Joergensen,

Monitoring of crop biomass using true colour aerial photographs taken
from a remote controlled hexacopter, Biosystems Engineering 129
(2015) 341 – 351. doi:10.1016/j.biosystemseng.2014.11.007.

[71] X. Wang, H. Sun, Y. Long, L. Zheng, H. Liu, M. Li, Devel-

opment of visualization system for agricultural uav crop growth
information collection, IFAC-PapersOnLine 51 (17) (2018) 631 –
636, 6th IFAC Conference on Bio-Robotics BIOROBOTICS 2018.
doi:10.1016/j.ifacol.2018.08.126.

[72] C. A. Rokhmana, The potential of uav-based remote sensing for sup-

porting precision agriculture in indonesia, Procedia Environmental Sci-

37
 ences 24 (2015) 245 – 253, the 1st International Symposium on LAPAN-
IPB Satellite (LISAT) for Food Security and Environmental Monitor-
ing. doi:10.1016/j.proenv.2015.03.032.

[73] C. Ju, H. I. Son, Multiple uav systems for agricultural applica-

tions: Control, implementation, and evaluation, Electronics 7 (9).
doi:10.3390/electronics7090162.

[74] D. Doering, A. Benenmann, R. Lerm, E. P. de Freitas, I. Muller, J. M.

Winter, C. E. Pereira, Design and optimization of a heterogeneous plat-
form for multiple uav use in precision agriculture applications, IFAC
Proceedings Volumes 47 (3) (2014) 12272 – 12277, 19th IFAC World
Congress. doi:10.3182/20140824-6-ZA-1003.02261.

[75] Z. Zhai, J.-F. Martnez Ortega, N. Lucas Martnez, J. Rodrguez-Molina,

A mission planning approach for precision farming systems based on
multi-objective optimization, Sensors 18 (6). doi:10.3390/s18061795.

[76] Q. Vu, M. Raković, V. Delic, A. Ronzhin, Trends in develop-

ment of uav-ugv cooperation approaches in precision agriculture, in:
A. Ronzhin, G. Rigoll, R. Meshcheryakov (Eds.), Interactive Collab-
orative Robotics, Springer International Publishing, Cham, 2018, pp.
213–221.

[77] A. Hernandez, H. Murcia, C. Copot, R. De Keyser, Towards

the development of a smart flying sensor: Illustration in the
field of precision agriculture, Sensors 15 (7) (2015) 16688–16709.
doi:10.3390/s150716688.

[78] A. K. Saha, J. Saha, R. Ray, S. Sircar, S. Dutta, S. P. Chattopad-

hyay, H. N. Saha, Iot-based drone for improvement of crop quality in
agricultural field, in: 2018 IEEE 8th Annual Computing and Com-
munication Workshop and Conference (CCWC), 2018, pp. 612–615.
doi:10.1109/CCWC.2018.8301662.

[79] L. N. Mascarello, F. Quagliotti, G. Ristorto, A feasibility study of an

harmless tiltrotor for smart farming applications, in: 2017 International
Conference on Unmanned Aircraft Systems (ICUAS), 2017, pp. 1631–
1639. doi:10.1109/ICUAS.2017.7991374.

38
[80] P. Horstrand, R. Guerra, A. Rodrguez, M. Daz, S. Lpez, J. F. Lpez,
A uav platform based on a hyperspectral sensor for image captur-
ing and on-board processing, IEEE Access 7 (2019) 66919–66938.
doi:10.1109/ACCESS.2019.2913957.

[81] O. Barrero, S. A. Perdomo, Rgb and multispectral uav image fusion

for gramineae weed detection in rice fields, Precision Agriculture 19 (5)
(2018) 809–822. doi:10.1007/s11119-017-9558-x.

[82] P. Lottes, R. Khanna, J. Pfeifer, R. Siegwart, C. Stachniss, Uav-based

crop and weed classification for smart farming, in: 2017 IEEE Inter-
national Conference on Robotics and Automation (ICRA), 2017, pp.
3024–3031. doi:10.1109/ICRA.2017.7989347.

[83] A. I. De Castro, J. Torres-Snchez, J. M. Pea, F. M. Jimnez-Brenes,

O. Csillik, F. Lpez-Granados, An automatic random forest-obia algo-
rithm for early weed mapping between and within crop rows using uav
imagery, Remote Sensing 10 (2). doi:10.3390/rs10020285.

[84] I. Sa, Z. Chen, M. Popovi, R. Khanna, F. Liebisch, J. Nieto, R. Sieg-

wart, weednet: Dense semantic weed classification using multispectral
images and mav for smart farming, IEEE Robotics and Automation
Letters 3 (1) (2018) 588–595. doi:10.1109/LRA.2017.2774979.

[85] I. Sa, M. Popovi, R. Khanna, Z. Chen, P. Lottes, F. Liebisch, J. Ni-

eto, C. Stachniss, A. Walter, R. Siegwart, Weedmap: A large-scale
semantic weed mapping framework using aerial multispectral imaging
and deep neural network for precision farming, Remote Sensing 10 (9).
doi:10.3390/rs10091423.

[86] M. D. Bah, A. Hafiane, R. Canals, Deep learning with unsupervised

data labeling for weed detection in line crops in uav images, Remote
Sensing 10 (11). doi:10.3390/rs10111690.

[87] M. D. Bah, E. Dericquebourg, A. Hafiane, R. Canals, Deep learning

based classification system for identifying weeds using high-resolution
uav imagery, in: K. Arai, S. Kapoor, R. Bhatia (Eds.), Intelligent
Computing, Springer International Publishing, Cham, 2019, pp. 176–
187.

39
[88] M. Hassanein, N. El-Sheimy, An efficient weed detection procedure us-
ing low-cost uav imagery system for precision agriculture applications,
2018.

[89] A. Mateen, Z. Qingsheng, Legion based weed extraction from uav im-
agery., Pakistan Journal of Agricultural Sciences 56 (4) (2019) 1057–
1064.

[90] M. Fawakherji, C. Potena, D. D. Bloisi, M. Imperoli, A. Pretto,

D. Nardi, Uav image based crop and weed distribution estimation on
embedded gpu boards, in: M. Vento, G. Percannella, S. Colantonio,
D. Giorgi, B. J. Matuszewski, H. Kerdegari, M. Razaak (Eds.), Com-
puter Analysis of Images and Patterns, Springer International Publish-
ing, Cham, 2019, pp. 100–108.

[91] X. Zhou, H. Zheng, X. Xu, J. He, X. Ge, X. Yao, T. Cheng, Y. Zhu,

W. Cao, Y. Tian, Predicting grain yield in rice using multi-temporal
vegetation indices from uav-based multispectral and digital imagery,
ISPRS Journal of Photogrammetry and Remote Sensing 130 (2017)
246 – 255. doi:10.1016/j.isprsjprs.2017.05.003.

[92] D. Stroppiana, M. Migliazzi, V. Chiarabini, A. Crema, M. Musanti,

C. Franchino, P. Villa, Rice yield estimation using multispectral data
from uav: A preliminary experiment in northern italy, in: 2015 IEEE
International Geoscience and Remote Sensing Symposium (IGARSS),
2015, pp. 4664–4667. doi:10.1109/IGARSS.2015.7326869.

[93] M. A. Hassan, M. Yang, A. Rasheed, G. Yang, M. Reynolds, X. Xia,

Y. Xiao, Z. He, A rapid monitoring of ndvi across the wheat growth cy-
cle for grain yield prediction using a multi-spectral uav platform, Plant
Science 282 (2019) 95 – 103, the 4th International Plant Phenotyping
Symposium. doi:10.1016/j.plantsci.2018.10.022.

[94] T. Duan, S. Chapman, Y. Guo, B. Zheng, Dynamic monitor-

ing of ndvi in wheat agronomy and breeding trials using an un-
manned aerial vehicle, Field Crops Research 210 (2017) 71 – 80.
doi:10.1016/j.fcr.2017.05.025.

[95] T. Zhang, J. Su, C. Liu, W.-H. Chen, Bayesian calibration of

aquacrop model for winter wheat by assimilating uav multi-spectral

40
 images, Computers and Electronics in Agriculture 167 (2019) 105052.
doi:10.1016/j.compag.2019.105052.

[96] J. Su, C. Liu, M. Coombes, X. Hu, C. Wang, X. Xu, Q. Li, L. Guo,

W.-H. Chen, Wheat yellow rust monitoring by learning from multi-
spectral uav aerial imagery, Computers and Electronics in Agriculture
155 (2018) 157 – 166. doi:10.1016/j.compag.2018.10.017.

[97] A. Verger, N. Vigneau, C. Chron, J.-M. Gilliot, A. Comar, F. Baret,

Green area index from an unmanned aerial system over wheat and
rapeseed crops, Remote Sensing of Environment 152 (2014) 654 – 664.
doi:10.1016/j.rse.2014.06.006.

[98] X. Jin, S. Liu, F. Baret, M. Hemerl, A. Comar, Estimates of plant

density of wheat crops at emergence from very low altitude uav
imagery, Remote Sensing of Environment 198 (2017) 105 – 114.
doi:10.1016/j.rse.2017.06.007.

[99] R. R. Shamshiri, I. A. Hameed, S. K. Balasundram, D. Ahmad,

C. Weltzien, M. Yamin, Fundamental research on unmanned aerial
vehicles to support precision agriculture in oil palm plantations, in:
J. Zhou, B. Zhang (Eds.), Agricultural Robots, IntechOpen, Rijeka,
2019, Ch. 6. doi:10.5772/intechopen.80936.

[100] P. Spachos, S. Gregori, Integration of wireless sensor networks and

smart uavs for precision viticulture, IEEE Internet Computing (2019)
1–1doi:10.1109/MIC.2018.2890234.

[101] H. J. Escalante, S. Rodrguez-Snchez, M. Jimnez-Lizrraga, A. Morales-

Reyes, J. D. L. Calleja, R. Vazquez, Barley yield and fertiliza-
tion analysis from uav imagery: a deep learning approach, In-
ternational Journal of Remote Sensing 40 (7) (2019) 2493–2516.
doi:10.1080/01431161.2019.1577571.

[102] P. Nevavuori, N. Narra, T. Lipping, Crop yield prediction with deep

convolutional neural networks, Computers and Electronics in Agricul-
ture 163 (2019) 104859. doi:10.1016/j.compag.2019.104859.

[103] J. Jung, M. Maeda, A. Chang, J. Landivar, J. Yeom, J. McGinty,

Unmanned aerial system assisted framework for the selection of high

41
 yielding cotton genotypes, Computers and Electronics in Agriculture
152 (2018) 74 – 81. doi:10.1016/j.compag.2018.06.051.

[104] F. Gndinger, U. Schmidhalter, Digital counts of maize plants

by unmanned aerial vehicles (uavs), Remote Sensing 9 (6).
doi:10.3390/rs9060544.

[105] I. Burud, G. Lange, M. Lillemo, E. Bleken, L. Grimstad, P. J. From,

Exploring robots and uavs as phenotyping tools in plant breeding,
IFAC-PapersOnLine 50 (1) (2017) 11479 – 11484, 20th IFAC World
Congress. doi:10.1016/j.ifacol.2017.08.1591.

[106] M. Maimaitijiang, A. Ghulam, P. Sidike, S. Hartling, M. Maimaitiy-

iming, K. Peterson, E. Shavers, J. Fishman, J. Peterson, S. Kadam,
J. Burken, F. Fritschi, Unmanned aerial system (uas)-based pheno-
typing of soybean using multi-sensor data fusion and extreme learning
machine, ISPRS Journal of Photogrammetry and Remote Sensing 134
(2017) 43 – 58. doi:10.1016/j.isprsjprs.2017.10.011.

[107] N. Yu, L. Li, N. Schmitz, L. F. Tian, J. A. Greenberg, B. W.

Diers, Development of methods to improve soybean yield estima-
tion and predict plant maturity with an unmanned aerial vehicle
based platform, Remote Sensing of Environment 187 (2016) 91 – 101.
doi:10.1016/j.rse.2016.10.005.

[108] C. Carl, D. Landgraf, M. Van der Maaten-Theunissen, P. Biber,

H. Pretzsch, Robinia pseudoacacia l. flower analyzed by us-
ing an unmanned aerial vehicle (uav), Remote Sensing 9 (11).
doi:10.3390/rs9111091.

[109] L. Quebrajo, M. Perez-Ruiz, L. Prez-Urrestarazu, G. Martnez,

G. Egea, Linking thermal imaging and soil remote sensing to en-
hance irrigation management of sugar beet, Biosystems Engineer-
ing 165 (2018) 77 – 87, sensing and Control of Crop Water Status.
doi:10.1016/j.biosystemseng.2017.08.013.

[110] B. S. Faial, F. G. Costa, G. Pessin, J. Ueyama, H. Freitas, A. Colombo,

P. H. Fini, L. Villas, F. S. Osrio, P. A. Vargas, T. Braun, The use of
unmanned aerial vehicles and wireless sensor networks for spraying

42
 pesticides, Journal of Systems Architecture 60 (4) (2014) 393 – 404.
doi:10.1016/j.sysarc.2014.01.004.

[111] B. S. Faial, H. Freitas, P. H. Gomes, L. Y. Mano, G. Pessin,

A. C. de Carvalho, B. Krishnamachari, J. Ueyama, An adaptive ap-
proach for uav-based pesticide spraying in dynamic environments,
Computers and Electronics in Agriculture 138 (2017) 210 – 223.
doi:10.1016/j.compag.2017.04.011.

[112] A. Segun, E. O. Ogunti, F. K. Akingbade, O. I. Sunday, Solution to

bird pest on cultivated grain farm: A vision controlled quadcopter
system approach, International Journal of Engineering Research and
Technology (IJERT) 07 (10).

43