agriculture

Review
Smart Farming: Internet of Things (IoT)-Based
Sustainable Agriculture
Muthumanickam Dhanaraju 1, *, Poongodi Chenniappan 2 , Kumaraperumal Ramalingam 1 ,
Sellaperumal Pazhanivelan 3 and Ragunath Kaliaperumal 3

1 Department of Remote Sensing and GIS, Tamil Nadu Agricultural University,

Coimbatore 641 003, Tamilnadu, India
2 Department of Electronics and Communication Engineering, Bannari Amman Institute of Technology,
Sathyamangalam 638 401, Tamilnadu, India
3 Water Technology Centre, Tamil Nadu Agricultural University, Coimbatore 641 003, Tamilnadu, India
* Correspondence: muthumanickam.d@tnau.ac.in

Abstract: Smart farming is a development that has emphasized information and communication
technology used in machinery, equipment, and sensors in network-based hi-tech farm supervision
cycles. Innovative technologies, the Internet of Things (IoT), and cloud computing are anticipated
to inspire growth and initiate the use of robots and artificial intelligence in farming. Such ground-
breaking deviations are unsettling current agriculture approaches, while also presenting a range of
challenges. This paper investigates the tools and equipment used in applications of wireless sensors
in IoT agriculture, and the anticipated challenges faced when merging technology with conventional
farming activities. Furthermore, this technical knowledge is helpful to growers during crop periods
from sowing to harvest; and applications in both packing and transport are also investigated.

Citation: Dhanaraju, M.; Keywords: crop management; sustainable agriculture; smart farming; internet-of-things (IoT); advanced
Chenniappan, P.; Ramalingam, K.; agriculture practices; issues and problems
Pazhanivelan, S.; Kaliaperumal, R.
Smart Farming: Internet of Things
(IoT)-Based Sustainable Agriculture.
Agriculture 2022, 12, 1745. 1. Introduction
https://doi.org/10.3390/
Sustainable agriculture is a measure of the endurance and sustenance of food grains
agriculture12101745
produced in an eco-friendly manner [1]. Sustainable agriculture helps in the encourage-
Academic Editors: Gniewko ment of farming practices and approaches to help sustain farmers and resources. It is
Niedbała and Sebastian Kujawa economically feasible and maintains soil quality, reduces soil degradation, saves water
Received: 7 September 2022
resources, improves land biodiversity, and ensures a natural and healthy environment [2].
Accepted: 12 October 2022
Sustainable agriculture plays a significant role in preserving natural resources, halting
Published: 21 October 2022
biodiversity loss, and reducing greenhouse gas emissions [3].
Sustainable agriculture farming is a method of preserving nature without compromis-
Publisher’s Note: MDPI stays neutral
ing the future generation’s basic needs, whilst also improving the effectiveness of farming.
with regard to jurisdictional claims in
The basic accomplishments of smart farming in terms of sustainable agriculture are crop ro-
published maps and institutional affil-
tation, the control of nutrient deficiency in crops, the control of pests and diseases, recycling,
iations.
and water harvesting, leading to an overall safer environment. Living organisms depend
on the nature of biodiversity, and are contaminated by waste emissions, the use of fertilizers
and pesticides, degraded dead plants, etc. The emission of greenhouse gases affects plants,
Copyright: © 2022 by the authors.
animals, humans, and the environment; hence, it necessitates a better environment for
Licensee MDPI, Basel, Switzerland. living things [4] (Figure 1).
This article is an open access article Agriculture is the largest contributor in India, with an 18% gross domestic product
distributed under the terms and involving approximately 57% of people in rural areas. Over the years, although India’s
conditions of the Creative Commons total agronomic output has increased, the number of growers has fallen from 71.9% in 1951
Attribution (CC BY) license (https:// to 45.1% in 2011 [5]. The Economic Survey 2018 revealed that the number of agricultural
creativecommons.org/licenses/by/ workers in the total workforce will drop to 25.7% in 2050. In rural areas, farming families
4.0/). gradually lose the next generation of farmers, overwhelmed by higher costs of cultivation,

Agriculture 2022, 12, 1745. https://doi.org/10.3390/agriculture12101745 https://www.mdpi.com/journal/agriculture

Agriculture 2022, 12, 1745 2 of 26

low per capita productivity, inadequate soil maintenance, and migrations to a non-farming
or higher remunerative occupation. Presently, the world is on the verge of a digital
revolution, and so it is the appropriate time to connect the agricultural landform with
wireless technology to introduce and accommodate digital connectivity with farmers.

Figure 1. Factors of sustainable agriculture.

Regrettably, not all parts of the Earth’s surface are suitable for agriculture due to
various restrictions, such as: soil quality, topography, temperature, climate, and most
relevant cultivable areas are also not homogenous [6]. Further, existing farming land is
fragmented by political and fiscal features, and rapid urbanization, which consistently
increases pressure on arable land availability (Figure 2). Recently, total agricultural land
used for food production has declined [7]. Furthermore, every crop field has different
critical characteristics, such as soil type, flow of irrigation, presence of nutrients, and pest
resistance, which are all measured separately both in quality and quantity regarding a
specific crop. Both spatial and temporal differences are necessary for optimizing crop
production in the same field by crop rotation and an annual crop growth development
cycle [8].

Figure 2. Key issues of technology in the agriculture industry.

In most cases, variations in characteristics occur within a single crop, or the same
crop is grown on the whole farm and requires site-specific analyses for optimum yield
production. New technology-based approaches are needed to produce more from less land,
and to address these various issues. In traditional farming practices, farmers frequently
Agriculture 2022, 12, 1745 3 of 26

visit their fields throughout the crop’s life in routine farming activities to better understand
the crop conditions [9]. The current sensor and communication technologies offer an precise
view of the field, from which farmers can detect ongoing field activities without being in
the field in person. Wireless sensors monitor the crops with higher accuracy and detect
issues at early stages, often facilitating the use of smart tools from initial sowing to the
harvest of crops [10].
The timely use of sensors has made the entire farming operation smart and cost-
effective, due to precise monitoring. The various autonomous harvesters, robotic weeders,
and drones have sensors attached to collect data over short intervals. However, the vastness
of agriculture puts extreme demands on technological solutions for sustainability with
minimum ecological impact. Sensor technology through wireless communication helps
farmers to know the various needs and requirements of crops without being in the fields,
and they are then able to take remote action [11].

2. Smart Farming
Historically, ancient agriculture practices were related to the production of food in
cultivated lands for the survival of humans and the breeding of animals [12], and was
called the traditional agricultural era 1.0. This mainly resorted to using manpower and
animals. Simple tools were used for farming activities, such as sickles and shovels. Work
was mainly conducted through manual labor, and subsequently, productivity continued at
a low level (Figure 3).

Figure 3. Agricultural decision support system framework.

During the 19th Century, new types of machinery appeared in the agricultural indus-
tries, in the form of steam engines. The wide use of agricultural machinery and abundant
chemicals by farmers signaled the start of the agricultural era 2.0, and outwardly improved
effectiveness and productivity of farmers and farms. However, considerably harmful impli-
cations, such as chemical pollution, environmental devastation, waste of natural resources,
and excess utilization of energy, simultaneously developed.
The agricultural era 3.0 emerged during the 20th Century, due to the rapid growth of
computation and electronics. Robotic techniques, programed agricultural machinery, and
other technologies enhanced the agricultural processes efficiently. The issues that had arisen
during agricultural era 2.0 were solved, and policies were readapted to the agricultural era
Agriculture 2022, 12, 1745 4 of 26

3.0 through work distribution, precise irrigation, the reduced use of chemicals, site-specific
nutrient application, and efficient pest control technologies, etc.
The next agricultural era is also the current iteration of agriculture, the agricultural
era 4.0, involving the engagement of recent technologies, such as the Internet of Things, big
data analysis, artificial intelligence, cloud computing and remote sensing, etc. The adop-
tion of new technologies has significantly improved agricultural activities by developing
low-cost sensor and network platforms, aimed towards the optimization of production
efficiency, along with reductions in the usage of water resources and energy with minimum
environmental effects [13]. Big data in smart farming provides extrapolative overviews of
real-time agricultural situations, allowing farmers to make effective decisions [14]. Real-
time programming is developed with artificial intelligence concepts and embedded in IoT
devices, helping farmers make the most suitable decisions [15].
Smart farming promotes precision agriculture with modern, sophisticated technology
and enables farmers to remotely monitor the plants. Smart farming helps agricultural pro-
cesses, such as harvesting and crop yields, as the automation of sensors and machinery has
made the farming workforce more efficient [16]. The technologies convert traditional farm-
ing methods to automatic devices, causing a technological revolution in agriculture. Today,
the technology in agriculture has altered the way farming is conducted, and conventional
techniques have been transformed by the Internet of Things [17].
In terms of optimizing farm labor requirements and increasing the quantity and
quality of products, smart farming is an emerging modern technique implemented with
information and communication technologies (ICT) [16]. Modern ICT technologies, such
as the Internet of Things, GPS (Global Positioning Systems), sensors, robotics, drones,
precision equipment, actuators, and data analytics, are used to identify the farmers’ needs
and select suitable solutions to their problems. These innovations increase the accuracy
and timeliness of decisions taken, and improve crop productivity. Several multilateral
organizations and developing countries around the world have proposed smart farming
technologies to increase agricultural output [18].
Sensors are constantly monitoring crops with greater accuracy, detecting any undesir-
able conditions during the early stages of the crop’s lifecycle. Current farming incorporates
smart tools from crop sowing to harvest, storing, and conveyance. The appropriate use of a
wide variety of sensors has made the entire operation both more efficient and profitable,
due to its accurate monitoring competencies. In addition, sensors that collect data quickly
are directly available online for further evaluation, and they provide crop and site-specific
agriculture for every site.
The many issues related to crop production are addressed by smart agriculture and
monitoring, particularly regarding changes in soil characteristics, climate factors, soil mois-
ture, etc., to improve the spatial management practices that increase crop production and
avoid the excess use of fertilizers and pesticides [19]. The ANN models in smart irrigation
water management (SIWM) regulate irrigation scheduling support systems (DSS) and offer
data on irrigation efficiency, water productivity index, and irrigation water demand and
supply on a real-time basis. Climate-smart agriculture (CSA) is an upcoming technology,
especially in developing countries, due to its potential to improve food security, farm
system resilience, and lower greenhouse gas emissions [20]. Smart agriculture technology
based on IoT technologies has many advantages in all agricultural processes and practices
in real-time, including irrigation, plant protection, improving product quality, fertilization,
disease prediction, etc. [21]. The benefit of smart agriculture lies in its collection of real-time
data on crops, the precise assessment of soil and crops, remote monitoring by farmers,
supervising water and other natural resources, and improving livestock and agricultural
production. Therefore, smart agriculture is considered to be the progression of precision
agriculture through modernization and smart methods to attain various information of
farm activities that are then remotely managed, and reinforced by suitable alternative
real-time farm maintenance solutions.
Agriculture 2022, 12, 1745 5 of 26

3. Internet of Things
The Internet of Things (IoT) is a new technology that allows devices to connect
remotely to achieve smart farming [22]. The IoT has begun to influence a vast range
of industries, from health, trade, communications, energy and agriculture, to enhance
efficiency and performance across all markets [23–25].
Current applications provide information on the IoT’s effects, and its practices that are
yet to be observed. However, by considering the advancement of technologies, one can
envisage the IoT technologies perform a crucial role in numerous activities of farming, such
as the utilization of communication infrastructure, data acquisition, smart objects, sensors,
mobile devices, cloud-based intelligent information, decision-making, and the automation
of agricultural operations (Figure 4).

Figure 4. Barriers in the implementation of smart agriculture technology.

The IoT technology monitors plants and animals and remotely retrieves information
from mobile phones and devices. Sensors and instruments empower farmers to assess
the weather and to anticipate production levels. The IoT plays a role in water harvesting,
monitoring and controlling the flow amount, assessing crops’ water requirements, time of
supply, and the saving of water, more than ever before [26]. Sensors and cloud connectivity
through the gateway can remotely monitor the status and water supply based on soil
and plant needs [27]. To correct nutrient deficiencies, pests, and diseases, farmers cannot
monitor and observe every plant manually, but IoT technology is still beneficial and has
led farmers to a new milestone in modern agriculture [28].
Recently, the development of IoT technologies has played a major role throughout the
farming sector, particularly through its communication infrastructure. This has included
connecting smart objects, remote data acquisition, using vehicles and sensors through
mobile devices and the internet, cloud-based intelligent analysis, interfacing, decision
formation, and the automation of agricultural operations. These proficiencies have revo-
lutionized the agriculture industry in terms of resource optimization, controlling climate
effects, and improving crop yields.
Researchers have proposed different methods, architectures, and various equipment to
monitor and convey crop information at different growth stages, based on several crop and
field types. Many manufacturers provide communication devices, multiple sensors, robots,
heavy machinery, and drones to collect and then distribute data. Food and agriculture
organizations, along with other government organizations, develop guidelines and policies
for regulating the use of technologies to preserve food and environment safety [29,30].
Agriculture 2022, 12, 1745 6 of 26

Fundamentals of IoT Applications in Agriculture

The accessible, inexpensive and interactive tracking platform provides consolidated
information on traditional agricultural methods, techniques, implements, crop pests and
diseases, etc., collected from various sources for sustainable agriculture. Interactive agricul-
ture allows easy access to the data by users through multiple devices, such as computers
and mobile phones [31].
1. Robust Models: The distinctive features of the agriculture sector are diversity, com-
plexity, spatio-temporal variability, and uncertainties of the right types of harvests
and facilities.
2. Scalability: The variation in farm size from smaller to larger; hence, the results should
be scalable. The placement and testing planning should be progressively scaled up
with fewer expenses.
3. Affordability: Affordability is vital to farming achievement, and therefore price should
be suitable with significant assistance. Standardized platforms, products, tools, and
facilities could obtain a satisfactory price.
4. Sustainability: The problem of sustainability is a vital issue due to strong economic
pressure and intense competition worldwide.

4. Technologies Used in Smart Farming

4.1. Global Positioning System (GPS)
GPS accurately records latitude, longitude, and elevation information [32]. Global
Positioning System satellites transmit signals and permit GPS receivers to compute their
location in real-time, and provide continuous positions while moving. The exact location
information offers farmers the opportunity to discover the precise position of field data,
such as pest occurrence, type of soil, weeds, and other barriers. The system facilitates the
recognition of various field locations in order to then apply the necessary inputs (seed,
fertilizer, herbicide, pesticide, and water) to a particular field [33].

4.2. Sensor Technologies

Technics, such as photo electricity, electromagnetics, conductivity, and ultrasound, are
used to estimate soil texture and structure, nutrient level, vegetation, humidity, vapor, air,
temperature, etc. Remote sensing data can differentiate between crop types, categorize
pests and weeds, locate stress in soil and plant conditions, and monitor drought [34].
Plant health is affected by many factors, such as soil moisture, nutrient availability,
exposure to light, humidity, the amount of rainfall, the color of leaves, etc. The plants are
monitored by maintaining the optimum temperature and light intensity, and conserving
water and energy through micro-irrigation. Different sensors are used to detect many
parameters. If they cross a threshold, the sensor senses the changes and transmits them
to the microcontroller to perform the required actions until the parameter returns to its
optimum level [1].
The temperature, humidity, soil pattern monitoring, airflow sensor, location, CO2 ,
pressure, light, and moisture sensors are generally used in sensing technologies. Prominent
sensor characteristics include reliability, memory, portability, durability, coverage, and
computational efficiency, and make them suitable for agriculture [35]. Currently available
wireless sensors play a vital role in collecting data on crop conditions and providing other
information. These sensors are standalone types and can be integrated with advanced
agricultural tools and heavy machinery, based on application necessities.
The major sensor types with their corresponding working procedure and purpose are
represented in Table 1.
Agriculture 2022, 12, 1745 7 of 26

Table 1. Sensor types and their applications.

Sensors Applications Working Procedure

Measuring the variations in noise level
Pest monitoring and detection classifying
Acoustic sensors when intermingling with other materials,
seed varieties, fruit harvesting [36].
i.e., soil particles [37].
Measuring soil air permeability, moisture,
Based on various soil properties, unique
Airflow sensors and structure in a static position or
identifying signatures [38].
mobile mode [38].
Quantifying exchanges of CO2 , water
vapor, methane, or other gases.
Measuring continuous flux over large
Eddy covariance-based sensors Measuring surface atmosphere and trace
areas [40].
gas fluxes in various agricultural
ecosystems [39].
To analyze soil nutrient levels and pH Nutrients in soil, salinity, and pH are
Electrochemical sensors
[41]. measured using sensors [42]
Recording electrical conductivity, Electrical circuits measure the capability
Electromagnetic sensors electromagnetic responses, residual of soil particles to conduct or accumulate
nitrates, and organic matter in soil [43]. electrical charge [44].
Programmable silicon chips and logic
Field programmable gate array (FAAA) Measuring real-time plant transpiration, blocks are surrounded together by
based sensors irrigation, and humidity [45]. programmable interconnected resources
of the digital circuit [46].
Sensors emit pulsed light waves and
Land mapping, soil type determination, bounce off when colliding with objects
Light detection and ranging (LIDAR) farm 3D modelling, erosion monitoring and are returned to the sensor. The time
and soil loss, and yield forecasting [47]. taken for each pulse to return is used for
assessment [47].
Sensing the mass flow of grain with
Yield monitoring based on the
modules, e.g., grain moisture sensor, data
Mass flow sensors amount of grain flow through a combine
storage device, and an internal software
harvester [48].
[48]
Sensors record the force assessed by
Mechanical sensors Soil compaction or mechanical resistance
strain gauges or load cells [48].
Soil organic substances, soil moisture,
color, minerals, composition, clay content,
etc. Fluorescence-based optical sensors Sensors use light reflectance phenomena
Optical sensors are used to supervise fruit maturation to measure changes in wave reflections
[49]. Integrating optical sensors with [44].
microwave scattering to characterize
orchard canopies [50]
Differentiate plant types to detect weeds Sensors differentiate based on reflection
Optoelectronic sensors spectra [51].
in wide-row crops [51].
Used in catchments to characterize Measuring rainfall, stream flow, and
Soft water level-based (SWLB) sensors hydrological behaviors (water level and
flow, time-step acquisitions) [52] other water presence options [52].

Assessing location, travel routes, and

Telecommunication between places
Telematics sensors machine and farm operation activities
(especially inaccessible points) [53].
[53].
Tank monitoring, spray distance An ultrasonic sensor uses a transducer to
measurement, uniform spray coverage, send and receive ultrasonic pulses that
Ultrasonic ranging sensors relay information about an object’s
object detection, monitoring crop canopy
[54], and weed detection [55]. proximity [56].
Crop assessment, yield modeling,
Satellite-based sensor systems collect,
forecasting yield date, land cover and
process, and disseminate environmental
Remote sensing degradation mapping, forecasting, the
data from fixed and mobile platforms
identification of plants and pests,
[57].
etc. [57].
Agriculture 2022, 12, 1745 8 of 26

4.3. Variable-Rate of Technology (VRT) and Grid Soil Sampling

Variable-rate technologies (VRT) are used in farming to predict the delivery rate of
inputs based on a predetermined map extrapolated from GIS for the placement of inputs at
variable amounts in the right place and at the right time [16,33]. Grid soil sampling is soil
collection from a systematic grid to establish a map for every parameter. These maps are
the basis for VRT and are loaded into a variable-rate applicator. The computer and GPS
receiver direct and control the changes in the delivery amount or fertilizer product, based
on map features [58,59].
New technologies, such as variable rate technology and associated practices (grid soil
sampling), potentially improve soil fertility management and assess the spatial distribution
of nutrients and yields [60]. In grid sampling, samples are collected from sampled sections
based on the subdivision of a field into small areas, or cells, by superimposing the grid
lines onto the field. Composite samples represent an entire area of each much smaller area
(grid-point sampling) at the intersections of grid lines. Soil-test values from grid sampling
are mapped by interpolating methods from non-measured locations between sampled
points. The variability of phosphorus and potassium is field-specific, and each field should
be fertilized differently to improve nutrient management practices by uniform applications
of fertilizers and manure for better precision agriculture [61].

4.4. Geographic Information System (GIS)

The GIS comprises hardware and software designed to provide compilation, storage,
retrieval, attributes analysis, and location data to generate maps and analyze characters and
geography for statistics and spatial methods [62]. The GIS database provides information
on field soil types, nutrient status, topography, irrigation, surface and subsurface drainage,
quantity of chemical applications, and crop production, and also establishes the relationship
between elements that affect a crop on a particular farming field [63]. Apart from data
storage and display, the GIS is used to assess present and alternative management by
compounding and altering data layers for decision-making.

4.5. Crop Management

Satellite images provide information on variations in soil conditions, as well as crop
performances affected by topography within the field. Therefore, farmers can exactly
monitor production factors, such as seeds, fertilizers, and pesticides, that are responsible
for yield increase and efficiency.
The spatial coverage and temporal revisit frequency of satellite images provide the
information in near real-time at a regional scale. The relationship between the spectral prop-
erties of crops and their biomass/yield experiments [64] is predicted by spectral reflectance
properties of vegetation, especially in red and near-infrared combinations (vegetation
indices) to monitor green foliage. Among the different indices, the normalized difference
vegetation index (NDVI) is the most popular indicator to assess vegetation health and crop
production, due to the closely related leaf area index (LAI) and photosynthetic activity
of green vegetation [25]. Crop monitoring methods are based on the interpretation of
remote-sensing-derived indicators by comparing actual crop status to previous or normal
seasons [65]. The relationship between vegetation indices and biomass permits early crop
yield estimation in certain periods before harvest [66]. The automated data acquisition, pro-
cessing, monitoring, decision-making, and management of farm operations [67], including
the basic functions of crop production (yields), profits and losses, farm weather prediction,
field mapping, soil nutrients tracking, are the more complicated functionalities available
through automated field management.

4.6. Soil and Plant Sensors

Sensor technology, a significant constituent of precision agriculture, provides soil
properties information, fertility, and water status. Hence, new sensors have been developed
based on desirable features and established apart from currently available sensors [68].
Agriculture 2022, 12, 1745 9 of 26

Soil sensors and plant wearables monitor real-time physical and chemical signals
in soil, such as moisture, pH, temperature, and pollutants, and provide information to
optimize crop growth conditions, fight against biotic and abiotic stresses, and increase
crop yields. Soil organic matters (SOMs), nitrogen (N), phosphorus (P), and potassium
(K) are the most important nutrients for crop production. The NIR reflectance-based
sensors measure the spatial variation of surface and subsurface soil nitrogen [69]. SOM is
predicted based on optimal wavelengths by assessing soil spectral reflectance in IR and
visible wavelength regions [70]. The soil nitrogen and phosphorus are predicted using
NIR spectrophotometry technology [71–73]. The soil apparent electrical conductivity (ECa)
sensors collect information continuously on the field surface, since ECa is sensitive to
changes in soil texture and salinity. Soil insects/pests are detected using optoelectronic,
acoustic, impedance sensors, and nanostructured biosensors [74].

4.7. Rate Controllers

Rate controllers are designed to control the delivery rate of inputs by monitoring the
speed of vehicles across the field, and altering the flow rate of material on a real-time basis
at the target rate. Rate controllers are commonly used as stand-alone systems [75].

4.8. Precision Irrigation in Pressurized Systems

Recent developments in irrigation systems have introduced irrigation machines, de-
voted to motion control, GPS-based controllers, sensor technologies, and wireless commu-
nication to monitor soil and climatic conditions together with an assessment of irrigation
parameters, i.e., flow and pressure, to attain greater water utilization efficiency by crop.
These technologies show significant potential; however, further progress is required before
they can become commercially available [76].

4.9. Yield Monitor

Yield monitors are the combination of sensors and components, including a data
storage device, a computer, and user interface, that control integration and interaction
components. The sensor measures yield continuously by evaluating the force of mass or
volume of grain flow. The mass flow sensor was based on the principle of transmitting
microwave energy beams and measuring the energy that bounces back after hitting. In
yield monitors, GPS receivers create yield maps based on the location yield data [77].
The yield monitor is mounted on a harvester and connected with the mobile app for
displaying live harvest data, and automatically uploads to the web-based platform. The
app can generate and share high-quality yield maps with an agronomist, and farmers
can export other farm management data for analysis. In horticultural crops, to precisely
determine the yield quantity and quality of produce, fruit growth is considered one of
the most relevant parameters in the crop progressing period [78]. Color images are used
to track fruit conditions for estimating fruit maturation, making decisions for harvesting,
and targeting the right market [79]. Satellite images are one of the options for real-time
monitoring of the yield of crops over vast areas; for example, Sentinel-1A images are used
to map the rice yield and crop intensity in Myanmar [80].
The crop yield estimation system was designed using both software and hardware
components. Based on a Bluetooth terminal android application and yield estimator
software program, crop yield is estimated using a mathematical calculation through a
mobile application [81]. Satellite-based crop yield predictions based on spectral signatures
reveal the estimated yields are as reliable as actual yields. The maize yield predictions
were successfully carried out under varying environments using machine learning and
satellite-derived data assimilation in crop models [82].

4.10. Software
The software has multiple tasks, such as mapping, display controller interfacing, data
processing, analysis, and interpretation, etc. Most commonly, software is used to generate
Agriculture 2022, 12, 1745 10 of 26

the maps for soil properties and nutrient status, yield maps, variable rate applications
maps for inputs, and overlaying different kinds of maps with advanced geostatistical
features [83].

5. Applications in Agriculture
By adopting the current sensor and IoT technologies in agriculture, each characteristic
of conventional farming practices is rehabilitated. The incorporation of wireless sensors
and IoT in smart farming answers many of the issues facing conventional agriculture; for
example, land suitability, drought monitoring, irrigation, pest control, and yield maximiza-
tion. Figure 5 demonstrates the order of main applications, facilities, and devices for smart
agriculture applications. Using advanced technologies at various stages in the following
few applications enhances efficiency and revolutionizes agriculture.

Figure 5. Hierarchy of probable applications, facilities and devices for smart agriculture.
Agriculture 2022, 12, 1745 11 of 26

5.1. Soil Mapping and Plant Monitoring

Soil analysis estimates the nutrient status of the field based on GPS position and
field-specific information, and critical decisions are then taken according to the nutrient
deficiencies at different stages of the crop. The factors controlling soil fertility status are
topography, type and texture, cropping pattern, application of fertilizer, irrigation, etc. [84].
Soil mapping is useful for assessing crop suitability or varieties in a specific field, as well
as planting depth, the physical, chemical and biological properties of soil, in order to
best utilize resources. Presently, a wide range of sensors and tools are used to monitor
soil properties, such as water-holding capacity, texture, and absorption rate, which assists
farmers in tracking the soil quality and adopting suitable remedies to avoid soil degradation
such as erosion, alkalization, acidification, salinization, and pollution. Drought is another
concern that affects plant productivity and crop yield. Remote sensing techniques that
can obtain soil moisture data frequently assist in analyzing agricultural drought in remote
regions. Soil moisture maps generated from satellite data are used to estimate the soil water
deficit index (SWDI), which enables the development of prediction models based on soil
physical properties [85,86].
Various factors, such as soil type, soil nutrients, irrigation, and pests, affect rice yield
and quality. The IoT-based mobile application aids crop management and provides real-
time information on soil nutrition and characteristics. The system consists of electrical
conductivity (EC), temperature sensors with a T-Beam microcontroller, and IoT connectivity,
and the estimated EC value near the calibration solution is 12.88 mS/cm, and 150 mS/cm
is less than 2% of the calibration solution’s value. The measured EC values are linearly
proportional to temperature and depth, and values of 1.04 and 3.86 mS/cm were noticed
with and without fertilizer at 5 cm depth, while it was 0.656 and 420 mS/cm at 10 cm depth,
respectively [87].
Plant monitoring conducted through the IoT ADCON-based station, with sensors
and mobile devices (smartphones and tablets), farmers are able to collect data on soil and
ambient parameters, such as leaf wetness, air and soil temperature, soil and air humidity to
improve the grape productivity, and crop quality from seeding to harvest. Further, the data
transmission system highlights the soil-plant-atmosphere interactions needed to optimize
agricultural production [88]. By analyzing the data from soil moisture, carbon dioxide,
light, and temperature sensors in bell peppers grown in a greenhouse were compared with
day and night CO2 , rolling the doors and windows of the greenhouse open and closed,
based on soil moisture [89].

5.2. Irrigation
According to the UN Convention to Combat Desertification (UNCCD), 168 countries
will be inundated with desertification by 2030, and nearly 50% of the world population
lives in high water shortage areas [90]. Considering the water crises and increasing demand
for farming and other activities, it must be provided to regions with water quantities. Water
resources are conserved by adopting more controlled and efficient irrigation systems; for
example, drip and sprinkler irrigations. Water demand estimation for crops is controlled
by soil type, precipitation, irrigation method, crop type, and requirement, as well as soil
moisture retention. Using air and soil moisture control systems with wireless sensors
optimizes water resources and improves crop health. In the current scenario, a substantial
increase in crop productivity is anticipated using IoT techniques, namely CWSI (crop water
stress index)-based water management [91], calculated from the crop canopy at varying
crop growth stages and air temperatures. The information from climate data, sensors, and
satellite imaging are related to the CWSI model for water requirement calculation, and
predictions using the irrigation index values can be used for every field based on slope or
soil variability to improve water usage efficiency.
Agriculture 2022, 12, 1745 12 of 26

5.3. Site-Specific Nutrient Management

Fertilizer is a either natural or synthetic chemical substance that provides nutrients for
plant growth and soil fertility. Both nutrient deficiency and excessive fertilizer use harms
soil, plant health, and the environment [92]. The site-specific soil nutrient fertilization under
smart agriculture estimates the required quantity of nutrients precisely, and minimizes
their negative effects through excessive use on soil and in the environment. The site-
specific soil, nutrient measurements are influenced by soil types, crop type, yield targets,
exchange capacity, use efficiency, the type of fertilizer, weather conditions, etc. The IoT-
based fertilizing technique estimates the nutrient’s spatial patterns of distribution [93,94].
The normalized difference vegetation index (NDVI) was obtained from satellite images to
observe crop nutrient status [95,96], crop health, vegetation vigor, and plant density, as well
as soil nutrient level. Recent technologies, like GPS [97], geo mapping [98], variable rate
technology (VRT) [99,100], and autonomous vehicles [101] strongly contribute to IoT-based
smart fertilization. Apart from these, fertigation [102] and chemigation [103,104], i.e., the
use of water-soluble fertilizers in soil amendments and pesticides, are considered effective
management practices to improve fertilization efficiency.

5.4. Crop Pest and Disease Management

The Food and Agriculture Organization (FAO) concluded that an annual global crop
yield loss of 20- 40% was only due to pests and diseases [105], and these losses are controlled
by the use of pesticides and other agrochemicals [106]. Most of them are harmful to human
and animal health, and ultimately cause contamination of environmental systems [107,108].
The IoT-based devices, such as robots, wireless sensors, and drones, precisely spot and
control the crop opponents by real-time monitoring, modelling, and disease forecasting,
increasing overall effectiveness [109,110] more than traditional pest control procedures.
The IoT-based disease and pest management process depends on detection and image
processing. The remote sensing imagery and field sensors are used to collect data, such
as plant health and pest incidence, in every field for the entire crop period. IoT-based
automated traps [111,112] capture, count, and describe insect types, and further upload
data to the Cloud for complete analysis. Due to advancements in robotic technology,
an agricultural robot with multispectral image sensing devices and precision spraying
nozzles is utilized to detect and control pest problems more accurately under the IoT
management system.

5.5. Yield Monitoring and Forecasting

The yield monitoring mechanism conforms to yield, moisture content, and quality of
produce. The quality depends on pollination with good pollen, especially under changing
environmental circumstances [113–115]. Crop forecasting predicts the yield before the crop
harvest, and assists the farmer in future planning, decision-making, and further analysis of
the yield quality. Maturity determines the right harvesting time by monitoring the crop at
different development stages, including factors such as fruit color, size, etc. Predictions of
the correct harvesting time aids in maximizing crop quality and production, and regulates
market management strategies. Therefore, farmers should know the exact harvest time of
crops to obtain profit. Figure 6 outlines the idea of a farm area network, representing the
whole farm in real-time conditions.
The development and installation of a yield monitor [116] on a harvester, connected
with a mobile app, shows real-time crop harvest, and automatically transmits data to
the manufacturer’s web-based platform. To estimate crop production and monitoring,
satellite images are exploited to cover vast areas [80]. For fruit crops, multicolor (RGB)
satellite images [79] are utilized to track the diverse fruit conditions, especially fruit size
and color, and plays a major role in estimating its maturation, making decisions on harvest,
and market opportunities. Similarly, multiple optical sensors are used [117] to monitor
shrinking fruits during drying conditions.
Agriculture 2022, 12, 1745 13 of 26

Figure 6. An Internet-of-Things-based network for smart farming.

6. Role of IoT in Advanced Farming Practices

Adopting the new methods based on sensor and IoT-based technologies improved
the yield of crops more than conventional agriculture processes. The involvement of new
sophisticated sensor-based technologies in controlled environments plays an important
role in enhancing the quality and quantity of produce.

6.1. Greenhouse Farming and Protected Cultivation

Growing plants in a controlled environment gained popularity in the 19th Century,
and is considered one of the oldest methods of smart farming. These practices further
accelerated during the 20th Century in countries facing severe weather conditions [118].
Crops grown in indoor conditions are less affected by the environment. As a result,
crops grown traditionally under suitable conditions are today being raised at anytime and
anywhere by the use of sensors and communication devices. The success of crop production
under a controlled environment depends on various factors, such as shed structures and
material for controlling wind effects, aeration systems, accuracy of monitoring parameters,
decision support system, etc. [119]. One of the greatest challenges in greenhouses is the
precise monitoring of environmental parameters; hence, it requires several measurement
points to predict the various parameters for controlling and ensuring the local climate. In
an IoT-based greenhouse, sensors are used to measure and monitor the internal parameters,
such as humidity, temperature, light, and pressure [120].
The smart greenhouse has helped farmers automatically conduct farm work, without
manual inspection, and protects the plants from hailstorms, winds, ultraviolet radiation,
and insect and pest attacks. Hibiscus plants are grown with the required wavelength during
the night using lights, temperature, and air humidity sensors. A study revealed a reduction
in 70–80% water requirement, and the IoT enables direct contact between the farmer and
consumer to make farming as efficient and profitable as possible [121]. The IoT-enabled
automated system increased the productivity of rose plants grown in a greenhouse by
Agriculture 2022, 12, 1745 14 of 26

monitoring and controlling various parameters, such as humidity, mist, CO2 level, UV light
intensity, pH and EC value, water nutrients solution level, temperature, and amount of
pesticides, through sensors for further efficient detection and diagnosis [122].

6.2. Hydroponics
Hydroponics, a subdivision of hydroculture, is growing plants without soil to improve
greenhouse farming benefits. Hydroponic-based irrigation systems enable a balanced rate
of application of dissolved nutrients in the water to crop roots as a solution. Presently,
the available systems and sensors [123] detect a wide range of parameters and perform
data analysis at predetermined intervals. Precise measurement and monitoring of nutrient
content in solution is crucial for plant growth and considers its demands. On a real-
time basis, the wireless-sensor-based prototype [124] has delivered a solution for soilless
cultivation, and measures the concentration of numerous nutrients and water levels [125].
An automated smart hydroponics system integrated with IoT consists of three major
components: input data, cloud server and output data. These monitor lettuce cultivation
from anywhere through the internet by analyzing parameters, such as pH level, water,
nutrient-rich water-based solution, room temperature, and humidity, on a real-time ba-
sis [126]. The hydroponic system of the deep flow technique is a method for cultivating
plants by placing roots in deep water layers, and ensuring the continuous circulation of
plant nutrient solution. The plant growth elements data, such as pH, temperature, humid-
ity, and water level in the hydroponic reservoir, are acquired by sensors integrated into
Raspberry Pi, and data are processed and monitored automatically on a real-time basis to
ensure proper water circulation [127].

6.3. Vertical Farming

The industrial-based agricultural farming practices damage soil quality at a faster
rate than nature can reconstruct. The alarming erosion rate and use of fresh water for
agriculture has led to the reduction of arable land, and increased the overburden on present
water reservoirs [128]. Vertical farming (VF) offers an opportunity to keep the plants in a
precisely controlled environment, significantly reducing resource consumption and, at the
same time, increasing production at varied times; and only a portion of the ground surface
is needed depending on the number of stacks. VF is also extremely effective in higher
yields and reducing water consumption compared to traditional farming [129]. The carbon
dioxide measurement is the most critical parameter; hence, nondispersive infrared (NDIR)
CO2 sensors play a vital part in tracking and controlling the conditions in vertical farms.

6.4. Phenotyping
Phenotyping is an emerging crop engineering technique, relating plant genomics with
ecophysiology and agronomy. The advancement of genetic and molecular tools is signifi-
cant for crop breeding; however, quantitative analysis of crop behaviors, such as pathogen
resistance, grain weight, etc., is inadequate due to the absence of effective technologies
and efficient techniques. In this condition, [130] reported that plant phenotyping is highly
useful in investigating the quantitative characteristics responsible for growth, resistance
to various stresses, yield quality, and quantity. The sensing technologies and image-based
phenotyping describe screening of biostimulants and an understanding of their mode
of action [131]. IoT-based phenotyping is intended to observe the crop and related trait
measurements, and offer facilities for the breeding of crops and digital agriculture [132].
The trait analysis algorithms and modelling support determine the relationships among
genotypes, phenotypes, and their growing condition.

7. The Role of the Engineer in Smart Farming

Farmers face many issues when they adopt IoT-based agriculture. Therefore, engi-
neers must develop solutions for specific problems related to smart farming techniques. An
engineering role concerns the application and use of innovative technologies and methods
Agriculture 2022, 12, 1745 15 of 26

for precision agricultural machinery, and smart farming is a creative way to mechanize
agricultural engineering through means different from conventional mechanization [133].
The concepts and synergy-based information are obtained from different technology areas,
such as agricultural mechanization, mechatronics, instrumentation, control systems, and
knowledge in artificial and computational intelligence [134]. Big data, satellite, and aerial
images have revolutionized precision agriculture, and these new technologies increase
production efficiency by creating a balance between productivity and environmental pro-
tection. As a system integrator, engineering combines technical experience and strong
business skills in both the public and private sectors [135].
At the same time, engineering exploits the rewards of digital transformation in the
entire agri-food chain, from day-to-day farming activities to supporting sales operations,
logistics, and the maintenance of farm assets. For example, knowledge of the IoT, AI,
mobile, precision farming technologies, remote sensing, advanced analytics, the Cloud,
RPA, and blockchain technologies are necessary [136]. The data collected from the various
types of machinery through sensors and other devices generates responses concerning
cereals, viticulture, fruit, and vegetables, as well as soil and monitoring [137].
The use of digital technologies and control systems to automate production processes
also reduces manual human intervention. The production process, from field to final
product, is carried out by planning, organizing, and analyzing data received from machines.
The data acquired are stored in historical archives and correlated with each other to
retrieve useful information for products through traceable systems working based on
radio-frequency signals [138].

7.1. Purpose
Purpose is based on the user’s final requirement, and influences the monitoring of
crops during the growth period. Sensors provide the IoT solutions to their problems.
For example, the end-user is a corn farmer, faced by problems mainly concerning water
usage and ensuring that a crop gets adequate water; therefore, water level and moisture
monitoring sensors are accommodated to prevent water wastage.

7.2. Technology
Distance plays an important role in technology selection because the sensors collect
data and send to the server; hence, similar technology cannot be used for varying distances.
For example, radio frequency identification (RFID) or near field communication (NFC) and
low power, wide area network (LPWAN) technologies could send data over a distance of
hundreds or even thousands of meters.

7.3. Power Requirements

Most IoT solutions are spread across a large farm, so it is better to develop low-
power applications. On the other hand, more data transmission requires huge data costs
and power consumption; hence, designers need to consider developing cost-effective IoT
solutions for farmers. Usually, engineers save costs with customized IoT-based farming
solutions, and develop apps for sending the data less frequently.

7.4. Data Frequency

The end user’s necessities are critical in deciding the number of sensors and data
packets. Sometimes, a farmer does not require information frequently, but developer design
an IoT application to function on a continual and real-time basis, with very high data
frequency.

7.5. Placement of Sensors

Sensors are placed in such a way that they provide optimal performance, even if the
farm has all the essential sensors with proper placement.
Agriculture 2022, 12, 1745 16 of 26

8. Barriers to Implementing Smart Farming Technologies

Technology adoption is a method with a certain level of heterogeneity factors that
are affective [139]. Technology implemented in farming systems has provided accuracy,
efficiency, and eased time pressures. Although smart farming increases the productivity of
crops, there are still problems in adopting these technologies

8.1. Cost of Technology

Existing technologies minimize the workforce and perform extremely fast with high
accuracy. Therefore, it is anticipated that machines would probably replace a human work-
force in the near future. However, it is impossible, since many countries have experienced
poverty wherever the workforce was the main source for the agriculture sector. The imple-
mentation of devices and technologies requires a huge amount of money; therefore, farmers
face difficulties in terms of affordability when they look beyond conventional tools.

8.2. Lack of Financial Resources

Financial supporters could provide adequate loans to farmers if farmers did not get
the anticipated yield, perhaps because unexpected calamities like drought, flood, pests,
and diseases impacted the crops.

8.3. Literacy Status of Farmers

The education level among the farmers is one of the greater challenges in implementing
technologies in developing countries. The knowledge needed encompasses educational and
technical abilities to manage the tools. The level of education increases a farmers’ aptitude
to process information, and thus make decisions using smart farming technologies [140],
facilitating farmers’ use of computers [141]. Farmers in developing nations are mostly
uneducated and unskilled because of a lack of desire to gain knowledge, or any new
technology awareness [142]. Hence, it is a reason for farmers in choosing traditional
farming over smart farming [143]. Farmers have considered that usage is too complex,
sometimes incapable of recognizing the icons used in a mobile application as the farmers
use general icons based on traditional understanding. Farmers need to be digitally literate
to reinforce the advantages of smart farming technologies and, simultaneously, agri-tech
companies should ensure farmers easily understand the limitations of the technology.

8.4. Lack of Integration between the Systems

Integration across systems is one of the areas where smart farming technologies needs
to be advanced further by incorporating production, property management, and decision-
making tools. The communication between academics and interdisciplinary groups must
overcome the gap between agricultural and information science. More emphasis has
been given to increasing user effectiveness during the development of an information
system [144]. The basis for improved decision-making is based on the timely obtain-
ability of superior quality data; hence, data must be integrated to generate information
and knowledge.

8.5. Telecommunications Infrastructure

Farming activities mostly occur in rural areas more effectively in arable land than
contaminated land. However, poor telecommunication infrastructure makes data transmis-
sion unreliable, especially through mobile phones and tablets. Smart farming necessitates
a real-time connection with the internet to enable the use of information. In addition,
various operation control systems, such as fertilizers, pesticides, and seed volume, requires
high-quality internet connection to produce outcomes. Recently, with the expansion of
mobile phones, rural producers have gained to access mobile internet; however, signal
quality and input speed are limited.
Agriculture 2022, 12, 1745 17 of 26

8.6. Data Management

Farmers are facing problems in organizing and manipulating data obtained by the
sensors. The weather stations are generating data; however, farmers do not recognize how
to use the information and how to change the data into a more available form. Its complex
systems, alongside issues of acceptability and usability, lead to incorrect calculations.
Farmers, consultants, and others involved in the production process must provide greater
accessibility to data and information in productive systems.

9. Current Challenges and Future Expectations

In the 2030 Agenda for Sustainable Development, the United Nations and international
community established a goal to end hunger by 2030. Currently, the World Health Organi-
zation reports that more than 800 million people are facing food shortages worldwise [145].
In addition, the increasing global population is increasing the demand for quality food;
therefore, food and cash crops could improve overall crop production.
Figure 7 represents the future challenges agriculture is anticipated to face in 2050. This
illustration offers three major problems: (1) feeding 10 billion people, (2) limitations in the
expansion of land, and (3) the reduction of greenhouse gases emissions. These challenges
lead to new thinking about water scarcity, shrinking arable land, rural labor, climate condi-
tions, and much more. The diminishment in rural populations due to urbanization is not
only shrinking communities, but is also leading to ageing populations; therefore, younger
growers must step forward to take responsibility. The generation shift and population
imbalance create further implications for the workforce and production.

Figure 7. Challenges in sustainable future agriculture.

The further shrinking of arable land and the suitability of particular crops in specific
regions are due to geographic and ecological conditions. Abrupt weather changes enhance
the intensity of environmental issues, such as drought, groundwater depletion, and soil
degradation, affecting crop production. Moreover, traditional agricultural methods have
historically met food demands by employing fertilizers and pesticides; however, it increases
food production only to a certain level and negligent use of chemical deteriorate the envi-
ronment. In developing countries, various problems facing the agricultural sector include
no suitable crop selection, soil testing, efficient irrigation systems, weather forecasting,
animal husbandry, etc. Technological advancements have proved beneficial in developed
countries, both quantitively and qualitatively, but, in developing countries, 50% of the
population is already engaged in agriculture.
Agriculture 2022, 12, 1745 18 of 26

The future of agriculture is expected to interconnect with artificial intelligence and

big data services. As a result, the systems will converge into a single unit, where farm
machinery and management start from seeding to production forecasting. Few of the key
technologies and methods are focused on achieving sustainable future agriculture.

9.1. Communication
The achievement of the IoT in agriculture mostly depends on connectivity between
devices [146]. Most telecom operators provide connectivity services, but represent a small
percentage of smart farming as a whole. Cellular operators offer new services to target
growers and enhance market facilities, especially in rural areas. The success of cellular
technology is feasible when service providers guarantee its benefits, such as flexibility,
portability, and extravagance, of both-way communication at low cost. In developing
countries, mobile services and smartphone technology offer a hopeful future for farmers
to enhance their crop yields. The low power wide area technology (LPWA) is anticipated
to play a major role in smart farming agriculture, due to its improved facilities, efficient
coverage, low power consumption, and cost economics. The cellular operators with robust
IoT create significant returns by offering smart agriculture facilities in collaboration with
LPWA technology.

9.2. Wireless Sensors and IoT

Placing wireless sensors around the field provides timely information on a real-time
basis to farmers in order to make decisions and act in order to obtain higher crop yields.
Wireless sensor networks (WSNs) with GPS technology update all information on crop
growth and terrain features. Recently, digital images and signal processing offer additional
competencies to WSN, and precisely ascertain crop quality and health. The IoT technology
can streamline tasks in a predictable manner by diagnosing crop requirements at each
stage to maximize their effectiveness. In the future, IoT will be upgraded to the fifth-
generation (5G) cellular mobile communication technologies, to provide real-time data
to farmers at any time and everywhere. Based on this achievement, around 29 billion
IoT-based components are expected to operate in the agriculture sector by the end of 2022.
Furthermore, it is expected to create 4.1 million data points daily from farms by 2050 [147].

9.3. Drones and Unarmed Vehicles

Farmers widely use drones for crop growth monitoring, spraying nutrient solutions
and water, and pesticides in tough terrains and for different crop heights. Drones have
proven their value for spraying speed, area coverage, and precision, compared to tradi-
tional machinery. Due to advancements in technology, drones are equipped with various
sensors, and 3D cameras provide comprehensive capabilities in land management by
farmers. With the addition of UAVs in agriculture, many challenges, particularly the in-
corporation of technologies and use in inclement weather conditions, are addressed by
farmers. Other than drones, robotics in agriculture has also enhanced productivity due to
higher yields achieved by spraying and weeding without human intervention. The seeding,
transplanting, and fruit harvest/picking robots have recently added a new efficiency level
to traditional methods.
The UAV technology in smart agriculture provides information on fertilization, ir-
rigation, use of pesticides, plant growth monitoring, weed management, crop disease
management, and field-level phenotyping to enhance cultivation practices. A new method
of 3D modeling has been used to monitor crop growth parameters to determine the height
of maize and sorghum plants under field conditions using UAV, and the average root mean
square error (RMSE) of sorghum height with hand sampling field data was 0.33 m [148]. The
UAV and 3D models were also restored to extract leaf area index (LAI) in soybean plants,
the measured LAI predicted accuracy corresponding to the handheld device (R2 = 0.92)
was correlated with destructive LAI measurements (R2 = 0.89) [149].
Agriculture 2022, 12, 1745 19 of 26

Weed detection and management were assessed by integrating low-resolution multi-

spectral high-resolution RGB images [150] using the Random Forest (RF) technique in
field-grown rice and sugar beet crops [151]. Multi-spectral digital images obtained by
UAVs are used for evaluating vegetation indices (VIs) and multi-temporal VIs to predict
grain yield in wheat [152]. The indices, including the normalized difference vegetation
index (NDVI), spectral vegetation index (SVI), and green area index (GAI), are evaluated in
wheat crops to predict grain yield [153], monitor breeding [154], detect plant stress caused
by yellow rust disease [155], and quantify plant density [156]. The usage of pesticides in
agriculture is crucial for crop yields and the environment, and efforts have been made to
develop and evaluate an algorithm to self-adjust UAV routes during chemical spraying in a
crop field to reduce the waste of pesticides and fertilizers [157].

9.4. Vertical Farming and Hydroponics

The shrinking of arable land and rapid urbanization results in greater pressure on the
present resources [158], which causes hardships for food production with current agricul-
ture practices. Vertical farming (VF) navigates land and water shortage challenges, and
is highly suitable for adoption in nearby cities. Hydroponics plays a key role in lowering
water requirements. Hydroponics, along with VF, increases available arable land without
distressing forests and other natural habitats. The presence of advanced technologies,
especially the IoT, makes the agriculture industry highly remunerative with a reduction in
labor requirements and other resources, in addition to minimizing environmental impact.

9.5. Performance Analysis Using Machine Learning

Data analytics and machine learning concepts are applied to analyze the real-time
data. In crop production, identifying the best genes is an important process that can be
conducted using machine learning techniques. In agriculture, machine learning is used to
envisage the best genes suited for crop production, especially for selecting seed varieties
that are highly suitable to specific climate conditions and locations. Machine learning
algorithms identify high demand products and currently unavailable products. Recent
developments in machine learning and analytics allow farmers to correctly categorize their
harvests before it is processes and delivered to customers.
Machine learning (ML) in big data systems solves the issues related to farmers’
decision-making, crops, animal research, land, food availability and security, weather
and climate change, and weeds [159]. ML-based applications accommodate a large number
of agricultural activities, such as yield prediction based on a deep memory model for
maize [160], binary classification model with logistic regression technique to assess rainfall
intensity [161], and a short-term memory model to predict soil water content with data
parameters of rainfall, temperature, water diversion, evaporation, and time for the next
1, 2, and 7 days with greater R2 compared to artificial neural networks [162]. As a result,
the agricultural sector is increasing farmers’ incomes, and so communities are further
integrated into the agricultural value chain to reduce poverty and provide access to health
care, education, and nutritious food for their families [163].

9.6. Renewable Energy, Microgrids and Smart Grids

Smart farming requires extensive energy due to power consumption by long-standing
sensor placement, use of GPS, and data transmission. Traditionally, using renewable energy
sources in remote areas solves long-term power issues. Smart grids and microgrids are
integrated into distributed energy sources (DERs). Recent advances in storage devices
combine electricity and heat systems to stock energy and use the heat produced.
Globally, smart grid technology enables a smooth transition from traditional to smart
energy systems, ensuring energy security. In developing countries, power-strengthening
systems integrated with renewable sources have enhanced the transport sector, and in-
creased bioenergy use in the power sector through profuse renewable energy sources
identified using smart technologies, such as, energy storage devices, smart appliances,
Agriculture 2022, 12, 1745 20 of 26

computational intelligence, and the IoT. For example, the smart grid provides a broad
range of opportunities for power sector reform in Nepal, alleviating the rural electricity
problem by implementing smart microgrids, and subsequently, connecting to the national
grid [164]. The Dayalbagh renewable energy smart microgrid in India is a small-scale
electricity system comprising distributed loads and renewable energy resources, acting as a
single controllable entity in the grid. The smart microgrids are integrated into renewable
resources and form building blocks of smart grids, especially for the dairy plant to produce
various dairy products [165].
The mixed integer linear programme (MILP) systematically and efficiently managed
energy consumption and subsequently lowered the cost, especially in residential areas,
by scheduling the use of smart appliances and charging/discharging electric vehicles
(EVs). The model generates its own energy from a microgrid containing solar panels
and wind turbines, and forecasts wind speed and solar radiation for effective energy
management. MILP-based energy planning sustains the effectiveness and productiveness
of energy-efficient techniques [166].

10. Conclusions
Smarter and more efficient crop production methodologies are needed to address the
issues of shrinking arable land and the food demands of an increasing world population.
There is a necessity for everyone to be aware of food security in terms of sustainable
agriculture. The growth of new technologies for increasing crop yield and encouraging
the adoption of farming by innovative young people as a legitimate profession. This
paper emphasized the role of many technologies used for farming, particularly the IoT,
in making agriculture smarter and more effective in meeting future requirements. The
current challenges faced by the industry and future prospects are noted to guide scholars
and engineers. Hence, every piece of farmland is important to enhance crop production by
dealing with every inch of land using sustainable IoT-based sensors and communication
technologies.

Author Contributions: Conceptualization, M.D.; investigation, P.C., K.R.; methodology, M.D., S.P.;
resources, K.R., R.K.; supervision, S.P.; visualization, R.K.; writing—original draft, M.D.; writing—
review & editing, P.C.; funding acquisition, S.P., validation, R.K. All authors have read and agreed to
the published version of the manuscript.
Funding: This research and APC were funded by GIZ, Germany by Deutsche Gesellschaft für
Internationale Zusammenarbeit (Grant number 81278637).
Conflicts of Interest: The authors declare that no competing financial interests or personal relation-
ships could have appeared to influence the work reported in this paper.

References
1. Srisruthi, S.; Swarna, N.; Ros, G.M.S.; Elizabeth, E. Sustainable agriculture using eco-friendly and energy efficient sensor technol-
ogy. In Proceedings of the 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication
Technology (RTEICT), Bangalore, India, 20–21 May 2016; IEEE: Bangalore, India, 2016; pp. 1442–1446. [CrossRef]
2. Brodt, S.; Six, J.; Feenstra, G.; Ingels, C.; Campbell, D. Sustainable Agriculture. Nat. Educ. Knowl. 2011, 3, 1.
3. Obaisi, A.I.; Adegbeye, M.J.; Elghandour, M.M.M.Y.; Barbabosa-Pliego, A.; Salem, A.Z.M. Natural Resource Management and
Sustainable Agriculture. In Handbook of Climate Change Mitigation and Adaptation; Lackner, M., Sajjadi, B., Chen, W.Y., Eds.;
Springer: Cham, Switzerland, 2022. [CrossRef]
4. Latake, P.T.; Pawar, P.; Ranveer, A.C. The Greenhouse Effect and Its Impacts on Environment. Int. J. Innov. Res. Creat. Technol.
2015, 1, 333–337.
5. Reddy, T.; Dutta, M. Impact of Agricultural Inputs on Agricultural GDP in Indian Economy. Theor. Econ. Lett. 2018, 8, 1840–1853.
[CrossRef]
6. World Agriculture: Towards 2015/2030: An FAO Perspective and Summary Report; FAO: Rome, Italy, 2002; Available online: www.fao.
org/3/a-y4252e.pdf (accessed on 1 August 2022).
7. Roser, M.; Ritchie, H.; Ortiz-Ospina, E. World Population Growth. 2013. Available online: https://ourworldindata.org/world-
population-growth (accessed on 1 August 2022).
Agriculture 2022, 12, 1745 21 of 26

8. Hernández-Ochoa, I.M.; Gaiser, T.; Kersebaum, K.C.; Webber, H.; Seidel, S.J.; Grahmann, K.; Ewert, F. Model-based design of crop
diversification through new field arrangements in spatially heterogeneous landscapes. A review. Agron. Sustain. Dev. 2022, 42, 74.
[CrossRef]
9. Navulur, S.; Sastry, A.S.C.S.; Giri Prasad, M.N. Agricultural Management through Wireless Sensors and Internet of Things. Int. J.
Electr. Comput. Eng. 2017, 7, 3492–3499. [CrossRef]
10. Ayaz, M.; Ammad-uddin, M.; Baig, I.; Aggoune, E.M. Wireless Sensor‘s Civil Applications, Prototypes, and Future Integration
Possibilities: A Review. IEEE Sens. J. 2018, 18, 4–30. [CrossRef]
11. Lin, J.; Yu, W.; Zhang, N.; Yang, X.; Zhang, H.; Zhao, W. A Survey on Internet of Things: Architecture, Enabling Technologies,
Security and Privacy, and Applications. IEEE Internet Things J. 2017, 4, 1125–1142. [CrossRef]
12. Tekinerdogan, B. Strategies for Technological Innovation in Agriculture 4.0. Reports; Wageningen University: Wageningen, The
Netherlands, 2018.
13. Ferrandez-Pastor, F.J.; Garcia-Chamizo, J.M.; Nieto-Hidalgo, M.; Mora-Pascual, J.; MoraMartinez, J. Developing ubiquitous sensor
network platform using Internet of Things: Application in precision agriculture. Sensors 2016, 16, 1141. [CrossRef]
14. Wolfert, S.; Ge, L.; Verdouw, C.; Bogaardt, M.J. Big data in smart farming—A review. Agric. Syst. 2017, 153, 69–80. [CrossRef]
15. Liakos, K.G.; Busato, P.; Moshou, D.; Pearson, S.; Bochtis, D. Machine learning in agriculture: A review. Sensors 2018, 18, 2674.
[CrossRef]
16. O’Grady, M.J.; O’Hare, G.M.P. Modelling the smart farm. Inf. Process. Agric. 2017, 4, 179–187. [CrossRef]
17. Quy, V.K.; Hau, N.V.; Anh, D.V.; Quy, N.M.; Ban, N.T.; Lanza, S.; Randazzo, G.; Muzirafuti, A. IoT-Enabled Smart Agriculture:
Architecture, Applications, and Challenges. Appl. Sci. 2022, 12, 3396. [CrossRef]
18. Raj Kumar, G.; Chandra Shekhar, Y.; Shweta, V.; Ritesh, R. Smart agriculture—Urgent need of the day in developing countries.
Sustain. Comput. Inform. Syst. 2021, 30, 100512.
19. El Nahry, A.H.; Mohamed, E.S. Potentiality of land and water resources in African Sahara: A case study of south Egypt. Environ.
Earth Sci. 2011, 63, 1263–1275. [CrossRef]
20. Palombi, L.; Sessa, R. Climate-Smart Agriculture: Source Book; Food and Agriculture Organization: Rome, Italy, 2013.
21. Adamides, G.; Kalatzis, N.; Stylianou, A.; Marianos, N.; Chatzipapadopoulos, F.; Giannakopoulou, M.; Papadavid, G.; Vassiliou,
V.; Neocleous, D. Smart Farming Techniques for Climate Change Adaptation in Cyprus. Atmosphere 2020, 11, 557. [CrossRef]
22. Patil, K.A.; Kale, N.R. A model for smart agriculture using IoT. In Proceedings of the 2016 International Conference on Global
Trends in Signal Processing, Information Computing and Communication, Jalgaon, India, 22–24 December 2016; IEEE: Jalgaon,
India, 2016; pp. 543–545. [CrossRef]
23. Sisinni, E.; Saifullah, A.; Han, S.; Jennehag, U.; Gidlund, M. Industrial Internet of Things: Challenges, Opportunities, and
Directions. IEEE Trans. Ind. Inform. 2018, 14, 4724–4734. [CrossRef]
24. Shi, X.; An, X.; Zhao, Q.; Liu, H.; Xia, L.; Sun, X.; Guo, Y. State- of- the- Art Internet of Things in Protected Agriculture. Sensors
2019, 19, 1833. [CrossRef]
25. Elijah, O.; Rahman, T.A.; Orikumhi, I.; Leow, C.Y.; Hindia, M.N. An Overview of Internet of Things (IoT) and Data Analytics in
Agriculture: Benefits and Challenges. IEEE Internet Things J. 2018, 5, 3758–3773. [CrossRef]
26. Yong, W.; Shuaishuai, L.; Li, L.; Minzan, L.; Ming, L.; Arvanitis, K.G.; Grorgieva, C.; Sigrimis, N. Smart Sensors from Ground to
Cloud and Web Intelligence. IFAC Pap. OnLine 2018, 51, 31–38. [CrossRef]
27. Mekala, M.S.; Viswanathan, P. A Survey: Smart agriculture IoT with cloud computing. In Proceedings of the 2017 International
Conference on Microelectronic Devices, Circuits and Systems (ICMDCS), Vellore, India, 10–12 August 2017; IEEE: Vellore, India,
2017; pp. 1–7. [CrossRef]
28. Mittal, A.; Singh, A. Microcontroller based pest management system. In Proceedings of the Second International Conference on
Systems (ICONS’07), Martinique, France, 22–28 April 2007; IEEE: Martinique, France, 2007; p. 43. [CrossRef]
29. Bonneau, V.; Copigneaux, B. Industry 4.0 in Agriculture: Focus on IoT Aspects, European Commission, Digital Transformation
Monitor. 2017. Available online: https://ec.europa.eu/growth/tools-databases/dem/monitor/content/industry-40-agriculture-
focus-iot-aspects (accessed on 30 December 2020).
30. King, T.; Cole, M.; Farber, J.M.; Eisenbrand, G.; Zabaras, D.; Fox, E.M.; Hill, J.P. Food safety for food security: Relationship
between global megatrends and developments in food safety. Trends Food Sci. Technol. 2017, 68, 160–175. [CrossRef]
31. Chandhini, K. A Literature Study on Agricultural Production System Using IoT as Inclusive Technology. Int. J. Innov. Technol. Res.
2016, 4, 2727–2731.
32. Lang, L. GPS + GIS + remote sensing: An overview. Earth Obs. Mag. 1992, 1, 23–26.
33. Batte, M.T.; VanBuren, F.N. Precision farming—Factor influencing productivity. In Proceedings of the Northern Ohio Crops Day
Meeting, Wood County, OH, USA, 21 January 1999.
34. Chen, F.; Kissel, D.E.; West, L.T.; Adkin, W.; Clark, R.; Rickman, D.; Luvall, J.C. Field Scale Mapping of Surface Soil Clay
Concentration. Precis. Agric. 2004, 5, 7–26. [CrossRef]
35. Muhammad, S.F.; Shamyla, R.; Adnan, A.; Tariq, U.; Yousaf, B.Z. Role of IoT Technology in Agriculture: A Systematic Literature
Review. Electronics 2020, 9, 319. [CrossRef]
36. Srivastava, N.; Chopra, G.; Jain, P.; Khatter, B. Pest Monitor and Control System Using Wireless Sensor Network (With Special
Reference to Acoustic Device Wireless Sensor). In Proceedings of the International Conference on Electrical and Electronics
Engineering, Khartoum, Sudan Goa, 26–28 August 2013. ISBN: 978-93-82208-58-7.
Agriculture 2022, 12, 1745 22 of 26

37. Kong, Q.; Chen, H.; Mo, Y.L.; Song, G. Real-time monitoring of water content in sandy soil using shear mode piezoceramic
transducers and active sensing-A feasibility study. Sensors 2017, 17, 2395. [CrossRef]
38. García-Ramos, F.J.; Vidal, M.; Boné, A.; Malón, H.; Aguirre, J. Analysis of the Air Flow Generated by an Air-Assisted Sprayer
Equipped with Two Axial Fans Using a 3D Sonic Anemometer. Sensors 2012, 12, 7598–7613. [CrossRef]
39. Moureaux, C.; Ceschia, E.; Arriga, N.; Béziat, P.; Eugster, W.; Kutsch, W.L.; Pattey, E. Eddy covariance measurements over
crops. In Eddy Covariance: A Practical Guide to Measurement and Data Analysis; Aubinet, M., Vesala, T., Papale, D., Eds.; Springer:
Dordrecht, The Netherlands, 2012.
40. Kumar, A.; Bhatia, A.; Fagodiya, R.K. Eddy covariance flux tower: A promising technique for greenhouse gases measurement.
Adv. Plants Agric. Res. 2017, 7, 337–340.
41. Yew, T.K.; Yusoff, Y.; Sieng, L.K.; Lah, H.C.; Majid, H.; Shelida, N. An electrochemical sensor ASIC for agriculture applica-
tions. In Proceedings of the 37th International Convention on Information and Communication Technology, Electronics and
Microelectronics (MIPRO), Opatija, Croatia, 26–30 May 2014; pp. 85–90.
42. Cocovi-Solberg, D.J.; Rosende, M.; Miro, M. Automatic kinetic bioaccessibility assay of lead in soil environments using flow-
through micro dialysis as a front end to electrothermal atomic absorption spectrometry. Environ. Sci. Technol. 2014, 48, 6282–6290.
[CrossRef]
43. Yunus, M.A.M.; Mukhopadhyay, S.C. Novel Planar Electromagnetic Sensors for Detection of Nitrates and Contamination in
Natural Water Sources. IEEE Sens. J. 2011, 11, 1440–1447. [CrossRef]
44. Millan-Almaraz, J.R.; Romero-Troncoso, R.J.; Guevara-Gonzalez, R.G.; Contreras-Medina, L.M.; Carrillo-Serrano, R.V.; Osornio
Rios, R.A.; Duarte-Galvan, C.; Rios-Alcaraz, M.A.; Torres Pacheco, I. FPGA-based fused smart sensor for real-time plant
transpiration dynamic estimation. Sensors 2010, 10, 8316–8331. [CrossRef]
45. Weiss, U.; Biber, P. Plant detection and mapping for agricultural robots using a 3D-LIDAR sensor. Robot. Auton. Syst. 2011, 59,
265–273. [CrossRef]
46. Montagnoli, A.; Fusco, S.; Terzaghi, M.; Kirschbaum, A.; Pflugmacher, D.; Cohen, W.B.; Scippa, G.S.; Chiatante, D. Estimating
forest aboveground biomass by low-density LiDAR data in mixed broad-leaved forests in the Italian Pre-Alps. For. Ecosyst. 2015,
2, 10. [CrossRef]
47. Schuster, J.N.; Darr, M.J.; McNaull, R.P. Performance benchmark of yield monitors for mechanical and environmental influences.
In Agricultural and Biosystems Engineering Conference Proceedings and Presentations; IOWA State University: Ames, IA, USA, 2017.
48. Hemmat, A.; Binandeh, A.R.; Ghaisari, J.; Khorsandi, A. Development and field testing of an integrated sensor for on-the-go
measurement of soil mechanical resistance. Sens. Actuators A Phys. 2013, 198, 61–68. [CrossRef]
49. Murray, S.C. Optical Sensors Advancing Precision In Agricultural Production. Photonics Spectra 2018, 51, 48.
50. Molina, I.; Morillo, C.; García-Meléndez, E.; Guadalupe, R.; Roman, M.I. Characterizing olive grove canopies by means of
ground-based hemispherical photography and spaceborne RADAR data. Sensors 2011, 11, 7476–7501. [CrossRef]
51. Andújar, D.; Ribeiro, Á.; Fernández-Quintanilla, C.; Dorado, J. Accuracy and feasibility of optoelectronic sensors for weed
mapping in wide row crops. Sensors 2011, 11, 2304–2318. [CrossRef]
52. Crabit, A.; Colin, F.; Bailly, J.S.; Ayroles, H.; Garnier, F. Soft water level sensors for characterizing the hydrological behaviour of
agricultural catchments. Sensors 2011, 11, 4656–4673. [CrossRef]
53. Mark, T.; Griffin, T. Defining the Barriers to Telematics for Precision Agriculture: Connectivity Supply and Demand. In
Proceedings of the SAEA Annual Meeting, San Antonio, TX, USA, 6–9 February 2016.
54. Dvorak, J.S.; Stone, M.L.; Self, K.P. Objct Detection for Agricultural and Construction Environments Using an Ultrasonic Sensor. J.
Agric. Saf. Health 2016, 22, 107–119.
55. Pajares, G.; Peruzzi, A.; Gonzalez-de-Santos, P. Sensors in agriculture and forestry. Sensors 2013, 13, 12132–12139. [CrossRef]
56. Zhmud, V.A.; Kondratiev, N.O.; Kuznetsov, K.A.; Trubin, V.G.; Dimitrov, L.V. Application of ultrasonic sensor for measuring
distances in robotics. J. Phys. Conf. Ser. 2018, 1015, 032189. [CrossRef]
57. Yalew, S.G.; van Griensven, A.; Mul, M.L.; van der Zaag, P. Land suitability analysis for agriculture in the Abbay basin using
remote sensing, GIS and AHP techniques. Model Earth Syst. Environ. 2016, 2, 101. [CrossRef]
58. Berntsen, J.; Thomsen, A.; Schelde, K.; Hansen, O.M.; Knudsen, L.; Broge, N.; Hougaard, H.; Horfarter, R. Algorithms for
sensor-based redistribution of nitrogen fertilizer in winter wheat. Precis. Agric. 2006, 7, 65–83. [CrossRef]
59. Ferguson, R.B.; Hergert, G.W.; Schepers, J.S.; Gotway, C.A.; Cahoon, J.E.; Peterson, T.A. Site-specific nitrogen management of
irrigated maize; Yield and soil residual nitrate effects. Soil Sci. Soc. Am. J. 2002, 66, 544–553.
60. Fleming, K.L.; Westfall, D.G.; Bausch, W.C. Evaluating management zone technology and grid soil sampling for variable rate
nitrogen application. In Proceedings of the 5th International Conference on Precision Agriculture, Bloomington, MN, USA, 16–19
July 2000; pp. 1–13.
61. Mallarino, A.P.; Wittry, D.J. Use of DGPS, yield monitors, soil testing and variable rate technology to improve phosphorus and
potassium management. In Proceedings of the Integrated Crop Management Conference; Iowa State University Extension and
Outreach: Ames, IA, USA, 1997; pp. 267–275.
62. Ehlers, M. Geoinformatics and digital earth initiatives: A German perspective. Int. J. Digit. Earth 2008, 1, 17–30. [CrossRef]
63. Ojo, O.I.; Ilunga, M.F. Geospatial Analysis for Irrigated Land Assessment Modeling and Mapping. In Multi-Purposeful Application
of Geospatial Data; Rustamov, R.B., Ed.; IntechOpen: London, UK, 2018; pp. 65–84. [CrossRef]
Agriculture 2022, 12, 1745 23 of 26

64. Tucker, C.J.; Holben, B.N.; Elgin, J.H., Jr.; McMurtrey, J.E., III. Relationship of spectral data to grain yield variation. Photogramm.
Eng. Remote Sens. 1980, 46, 657–666.
65. Muthumanickam, D.; Kannan, P.; Kumaraperumal, R.; Natarajan, S.; Sivasamy, R.; Poongodi, C. Drought assessment and
monitoring through remote sensing and GIS in western tracts of Tamil Nadu, India. Int. J. Remote Sens. 2011, 32, 5157–5176.
[CrossRef]
66. Felix, R.; Clement, A.; Igor, S.; Oscar, R. Using Low Resolution Satellite Imagery for Yield Prediction and Yield Anomaly Detection.
Remote Sens. 2013, 5, 1704–1733.
67. Chowdhury, M.E.H.; Khandakar, A.; Ahmed, S.; Al-Khuzaei, F.; Hamdalla, J.; Haque, F.; Reaz, M.B.I.; Shafei, A.A.; Emadi, N.A.
Design, Construction and Testing of IoT Based Automated Indoor Vertical Hydroponics Farming Test-Bed in Qatar. Sensors 2020,
20, 5637. [CrossRef]
68. Adamchuk, V.I.; Hummel, J.W.; Morgan, M.T.; Upadhyaya, S.K. On-the-go soil sensors for precision agriculture. Comput. Electron.
Agric. 2004, 44, 71–91. [CrossRef]
69. Sudduth, K.A.; Hummel, J.W. Soil Organic Matter, CEC, and Moisture Sensing with a Portable NIR Spectrophotometer. Trans.
ASAE 1993, 36, 1571–1582. [CrossRef]
70. Daniel, K.; Tripathi, N.K.; Honda, K.; Apisit, E. Analysis of spectral reflectance and absorption patterns of soil organic matter. In
Proceedings of the 22nd Asian Conference on Remote Sensing, Singapore, 5–9 November 2011.
71. Kuang, B.; Mouazen, A.M. Non-biased prediction of soil organic carbon and total nitrogen with vis-NIR spectroscopy, as affected
by soil moisture content and texture. Biosyst. Eng. 2013, 114, 249–258. [CrossRef]
72. Maleki, M.R.; Van Holm, L.; Ramon, H.; Merckx, R.; De Baerdemaeker, J.; Mouazen, A.M. Phosphorus Sensing for Fresh Soils
using Visible and Near Infrared Spectroscopy. Biosyst. Eng. 2006, 95, 425–436. [CrossRef]
73. Lvova, L.; Nadporozhskaya, M. Chemical sensors for soil analysis: Principles and applications. In Series Nanotechnology in the
Agri-Food Industry; New Pesticides and Soil Sensors; Grumezescu, A.M., Ed.; Elsevier: Amsterdam, The Netherlands, 2017;
Volume 10, pp. 637–678. [CrossRef]
74. Potamitis, I.; Rigakis, I.; Tatlas, N.A.; Potirakis, S. In-Vivo Vibroacoustic Surveillance of Trees in the Context of the IoT. Sensors
2019, 19, 1366. [CrossRef]
75. Sushil, S.; Radha Mohan, S.; Manhas, S.S.; Shiv Kumar, L. Potential of Variable Rate Application Technology in India. AMA Agric.
Mech. Asia Afr. Lat. Am. 2014, 45, 74–89.
76. Hassan, A.; Aitazaz, A.F.; Farhat, A.; Bishnu, A.; Travis, E. Precision Irrigation Strategies for Sustainable Water Budgeting of
Potato Crop in Prince Edward Island. Sustainability 2020, 12, 2419. [CrossRef]
77. Naorem, A.; Rani, A.; Roy, D.; Kundu, S.; Rao, N.S.; Sreekanth, P.D.; Kumar, A.; Manjaiah, A.M.; Rao, C.S. Frontier Soil
Technologies for Sustainable Development Goals (SDGs) in India. In Challenges and Emerging Opportunities in Indian Agriculture;
Rao, C.S., Senthil, V., Meena, P.C., Eds.; National Academy of Agricultural Research Management: Hyderabad, India, 2019; pp.
113–152.
78. Luigi, L.M.; Emanuele, E.P.; Zibordi, M.; Morandi, B.; Muzzi, E.; Losciale, P.; Corelli, L.; Grappadelli, L.C. Monitoring Strategies
for Precise Production of high quality Fruit and Yield in Apple in Emilia Romagna. Chem. Eng. Trans. 2015, 44, 301–306.
79. Wang, Z.; Walsh, K.B.; Verma, B. On-tree mango fruit size estimation using RGB-D images. Sensors 2017, 17, 2738. [CrossRef]
80. Torbick, N.; Chowdhury, D.; Salas, W.; Qi, J. Monitoring Rice Agriculture across Myanmar Using Time Series Sentinel-1 Assisted
by Landsat-8 and PALSAR-2. Remote Sens. 2017, 9, 119. [CrossRef]
81. Mishachandar, B.; Vairamuthu, S. Crop Yield Estimation Using the Internet of Things. J. Inf. Knowl. Manag. 2021, 20, 2140006.
[CrossRef]
82. Olipa, N.L.; Lydia, M.C.; Chabala1, S.; Chizumba, S. Satellite-Based Crop Monitoring and Yield Estimation—A Review. J. Agric.
Sci. 2021, 13, 180–194.
83. Ferrández-Pastor, F.J.; García-Chamizo, J.M.; Nieto-Hidalgo, M.; Mora-Martínez, J. Precision Agriculture Design Method Using a
Distributed Computing Architecture on Internet of Things Context. Sensors 2018, 18, 1731. [CrossRef]
84. Dinkins, C.P.; Jones, C. Interpretation of Soil Test Results for Agriculture; MontGuide. Publication no. MT200702AG; Montana State
University Extension: Bozeman, MT, USA, 2013.
85. Martínez-Fernández, J.; González-Zamora, A.; Sánchez, N.; Gumuzzio, A.; Herrero-Jiménez, C.M. Satellite soil moisture for
agricultural drought monitoring: Assessment of the SMOS derived Soil Water Deficit Index. Remote Sens. 2016, 177, 277–286.
[CrossRef]
86. Vågen, T.G.; Winowiecki, L.A.; Tondoh, J.E.; Desta, L.T.; Gumbricht, T. Mapping of soil properties and land degradation risk in
Africa using MODIS reflectance. Geoderma 2016, 263, 216–225. [CrossRef]
87. Othaman, N.N.C.; Md Isa, M.N.; Hussin, R.; Zakaria, S.M.M.S.; Isa, M.M. IoT Based Soil Nutrient Sensing System for Agriculture
Application. Int. J. Nanoelectron. Mater. 2021, 14, 279–288.
88. Ioana, M.; George, S.; Cristina, M.B.; Ana-Maria, D.; Marius, A.D. IoT Solution for Plant Monitoring in Smart Agriculture.
In Proceedings of the IEEE 25th International Symposium for Design and Technology in Electronic Packaging, Cluj-Napoca,
Romania, 23–26 October 2019; pp. 194–197.
89. Pallavi, S.; Mallapur, J.D.; Bendigeri, K.Y. Remote sensing and controlling of greenhouse agriculture parameters based on IoT.
In Proceedings of the International Conference on Big Data, IoT and Data Science (BID), Pune, India, 20–22 December 2017;
pp. 44–48.
Agriculture 2022, 12, 1745 24 of 26

90. Rubio, V.S.; Ma, F.R. From Smart Farming towards Agriculture 5.0: A Review on Crop Data Management. Agronomy 2020, 10, 207.
[CrossRef]
91. Yuan, G.; Luo, Y.; Sun, X.; Tang, D. Evaluation of a crop water stress index fordetecting water stress in winter wheat in the North
China Plain. Agric. Water Manag. 2004, 64, 29–40. [CrossRef]
92. Köksal, Ö.; Tekinerdogan, B. Architecture design approach for IoT-based farm management information systems. Precis. Agric.
2019, 20, 926–958. [CrossRef]
93. Xue, J.; Su, B. Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications. J. Sens. 2017, 2017,
1353691. [CrossRef]
94. Lavanya, G.; Rani, C.; Ganeshkumar, P. An automated low cost IoT based Fertilizer Intimation System for smart agriculture.
Sustain. Comput. Inform. Syst. 2020, 28, 100300. [CrossRef]
95. Benincasa, P.; Antognelli, S.; Brunetti, L.; Fabbri, C.; Natale, A.; Sartoretti, V.; Vizzari, M. Reliability of NDVI Derived by High
Resolution Satellite and UAV Compared to In-Field Methods for the Evaluation of Early Crop N Status and Grain Yield in Wheat.
Exp. Agric. 2018, 54, 604–622. [CrossRef]
96. Pinheiro Lisboa, I.; Melo Damian, J.; Roberto Cherubin, M.; Silva Barros, P.P.; Ricardo Fiorio, P.; Cerri, C.C.; Eduardo Pellegrino
Cerri, C. Prediction of Sugarcane Yield Based on NDVI and Concentration of Leaf Tissue Nutrients in Fields Managed with Straw
Removal. Agronomy 2018, 8, 196. [CrossRef]
97. Sishodia, R.P.; Ray, R.L.; Singh, S.K. Applications of Remote Sensing in Precision Agriculture: A Review. Remote Sens. 2020, 12,
3136. [CrossRef]
98. Suradhaniwar, S.; Kar, S.; Nandan, R.; Raj, R.; Jagarlapudi, A. Geo-ICDTs: Principles and Applications in Agriculture. In Geospatial
Technologies in Land Resources Mapping, Monitoring and Management; Obi Reddy, G.P., Singh, S.K., Eds.; Geotechnologies and the
Environment; Springer: Cham, Switzerland, 2018; Volume 21, pp. 75–99. [CrossRef]
99. Colaço, A.F.; Molin, J.P. Variable rate fertilization in citrus: A long term study. Precis. Agric. 2017, 18, 169–191. [CrossRef]
100. Bruno, B.; Benjamin, D.; Davide, C.; Andrea, P.; Francesco, M.; Luigi, S. Environmental and Economic benefits of variable rate
nitrogen fertilization in a nitrate vulnerable zone. Sci. Total Environ. 2016, 545–546, 227–235.
101. Khan, N.; Medlock, G.; Graves, S.; Anwar, S. GPS Guided Autonomous Navigation of a Small Agricultural Robot with Automated
Fertilizing System; SAE Technical Paper 2018-01-0031; SAE International: Warrendale, PA, USA, 2018. [CrossRef]
102. Raut, R.; Varma, H.; Mulla, C.; Pawar, V.R. Soil Monitoring, Fertigation, and Irrigation System Using IoT for Agricultural
Application. In Intelligent Communication and Computational Technologies; Springer: Singapore, 2017; pp. 67–73.
103. Briones, A.G.; Castellanos-Garzón, J.A.; Martín, Y.M.; Prieto, J.; Corchado, J.M. A Framework for Knowledge Discovery from
Wireless Sensor Networks in Rural Environments: A Crop Irrigation Systems Case Study. Wirel. Commun. Mob. Comput. 2018,
2018, 6089280. [CrossRef]
104. Villarrubia, G.; De Paz, J.F.; De La Iglesia, D.H.; Bajo, J. Combining Multi-Agent Systems and Wireless Sensor Networks for
Monitoring Crop Irrigation. Sensors 2017, 17, 1775. [CrossRef]
105. Newlands, N.K. Model-Based Forecasting of Agricultural Crop Disease Risk at the Regional Scale, Integrating Airborne Inoculum,
Environmental, and Satellite-Based Monitoring Data. Front. Environ. Sci. 2018, 6, 63. [CrossRef]
106. Khattaba, A.S.; Habiba, E.D.; Ismail, H.; Zayanc, S.; Fahmya, Y.; Khairya, M.M. An IoT-based cognitive monitoring system for
early plant disease forecast. Comput. Electron. Agric. 2019, 166, 105028. [CrossRef]
107. Carvalho, F.P. Pesticides, environment, and food safety. Food Energy Secur. 2017, 6, 48–60. [CrossRef]
108. Ramalingam, B.; Mohan, R.E.; Pookkuttath, S.; Gómez, B.F.; Sairam Borusu, C.S.C.; Wee Teng, T.W.; Tamilselvam, Y.K. Remote
Insects Trap Monitoring System Using Deep Learning Framework and IoT. Sensors 2020, 20, 5280. [CrossRef]
109. Kim, S.; Lee, M.; Shin, C. IoT-Based Strawberry Disease Prediction System for Smart Farming. Sensors 2018, 18, 4051. [CrossRef]
[PubMed]
110. Venkatesan, R.; Kathrine, G.; Jaspher, W.; Ramalakshmi, K. Internet of Things Based Pest Management Using Natural Pesticides
for Small Scale Organic Gardens. J. Comput. Theor. Nanosci. 2018, 15, 2742–2747. [CrossRef]
111. Ennouri, K.; Kallel, A. Remote Sensing: An Advanced Technique for Crop Condition Assessment. Math. Probl. Eng. 2019, 2019,
9404565. [CrossRef]
112. Marinelli, M.C.; Scavuzzo, C.M.; Giobellina, B.L.; Scavuzzo, C.M. Geoscience and Remote Sensing on Horticulture as Support for
Management and Planning. J. Agron. Res. 2019, 2, 43–54. [CrossRef]
113. Wietzke, A.; Westphal, C.; Gras, P.; Kraft, M.; Pfohl, K.; Karlovsky, P.; Pawelzik, E.; Tscharntke, T.; Smit, I. Insect pollination as a
key factor for strawberry physiology and marketable fruit quality. Agric. Ecosyst. Environ. 2018, 258, 197–204. [CrossRef]
114. Chung, S.O.; Choi, M.C.; Lee, K.H.; Kim, Y.J.; Hong, S.J.; Li, M. Sensing Technologies for Grain Crop Yield Monitoring Systems: A
Review. J. Biosyst. Eng. 2016, 41, 408–417. [CrossRef]
115. Talaei, G.H.T.H.; Gholami, S.; Pishva, Z.K.; Dehaghi, M.A. Effects of Biological and Chemical Fertilizers Nitrogen on Yield Quality
and Quantity in Cumin (Cuminum cyminum L.). J. Chem. Health Risks 2014, 4, 55–64.
116. Singh, R.; Singh, G.S. Traditional agriculture: A climate-smart approach for sustainable food production. Energy Ecol. Environ.
2017, 2, 296–316. [CrossRef]
117. Udomkun, P.; Nagle, M.; Argyropoulos, D.; Mahayothee, B.; Müller, J. Multi-sensor approach to improve optical monitoring of
papaya shrinkage during drying. J. Food Eng. 2016, 189, 82–89. [CrossRef]
Agriculture 2022, 12, 1745 25 of 26

118. Theopoulos, A.; Boursianis, A.; Koukounaras, A.; Samaras, T. Prototype wireless sensor network for real-time measurements
in hydroponics cultivation. In Proceedings of the 7th International Conference on Modern Circuits and Systems Technologies
(MOCAST), Thessaloniki, Greece, 7–9 May 2018. [CrossRef]
119. Shamshiri, R.R.; Kalantari, F.; Ting, K.C.; Thorp, K.R.; Hameed, I.A.; Weltzien, C.; Ahmad, D.; Shad, Z. Advances in greenhouse
automation and controlled environment agriculture: A transition to plant factories and urban agriculture. Int. J. Agric. Biol. Eng.
2018, 11, 1–22. [CrossRef]
120. Akkaş, M.A.; Sokullu, R. An IoT-based greenhouse monitoring system with Micaz motes. Procedia Comput. Sci. 2017, 113, 603–608.
[CrossRef]
121. Kodali, R.K.; Jain, V.; Karagwal, S. IoT based smart greenhouse. In Proceedings of the 2016 IEEE Region 10 Humanitarian
Technology Conference (R10-HTC), Agra, India, 21–23 December 2016. [CrossRef]
122. Tripathy, P.K.; Tripathy, A.K.; Agarwal, A.; Mohanty, S.P. MyGreen: An IoT-Enabled Smart Greenhouse for Sustainable Agriculture.
IEEE Consum. Electron. Mag. 2021, 10, 57–62. [CrossRef]
123. Sambo, P.; Nicoletto, C.; Giro, A.; Pii, Y.; Valentinuzzi, F.; Mimmo, T.; Lugli, P.; Orzes, G.; Mazzetto, F.; Astolfi, S.; et al. Hydroponic
Solutions for Soilless Production Systems: Issues and Opportunities in a Smart Agriculture Perspective. Front. Plant Sci. 2019, 10,
923. [CrossRef] [PubMed]
124. Yang, W.; Feng, H.; Zhang, X.; Zhang, J.; Doonan, J.H.; Batchelor, W.D.; Xiong, L.; Yan, J. Crop Phenomics and High-Throughput
Phenotyping: Past Decades, Current Challenges, and Future Perspectives. Mol. Plant 2020, 13, 187–214. [CrossRef]
125. Rouphael, Y.; Spíchal, L.; Panzarová, K.; Casa, R.; Colla, G. High-Throughput Plant Phenotyping for Developing Novel
Biostimulants: From Lab to Field or From Field to Lab? Front. Plant Sci. 2018, 9, 1197. [CrossRef]
126. Lakshmanan, R.; Djama, M.; Selvaperumal, S.; Abdulla, R. Automated smart hydroponics system using internet of things. Int. J.
Electr. Comput. Eng. 2020, 10, 6389–6398. [CrossRef]
127. Usman, N.; Arief, P.; Gilang, L.; Erfan, R.; Hendra, P. Implementation IoT in System Monitoring Hydroponic Plant Water
Circulation and Control. Int. J. Eng. Technol. 2018, 7, 122–126.
128. Pimentel, D.; Burgess, M. Soil erosion threatens food production. Agriculture 2013, 3, 443–463. [CrossRef]
129. Benke, K.; Tomkins, B. Future food-production systems: Vertical farming and controlled-environment agriculture. Sustain. Sci.
Pract. Policy 2017, 13, 13–26. [CrossRef]
130. Tripodi, P.; Massa, D.; Venezia, A.; Cardi, T. Sensing Technologies for Precision Phenotyping in Vegetable Crops: Current Status
and Future Challenges. Agronomy 2018, 8, 57. [CrossRef]
131. Paul, K.; Sorrentino, M.; Lucini, L.; Rouphael, Y.; Cardarelli, M.; Bonini, P.; Reynaud, H.; Canaguier, R.; Trtílek, M.; Panzarová, K.;
et al. Understanding the Biostimulant Action of Vegetal-Derived Protein Hydrolysates by High-Throughput Plant Phenotyping
and Metabolomics: A Case Study on Tomato. Front. Plant Sci. 2019, 10, 47. [CrossRef]
132. Zhou, J.; Reynolds, D.; Websdale, D.; Le Cornu, T.; Gonzalez Navarro, O.; Lister, C.; Orford, S.; Laycock, S.; Finlayson, G.; Stitt, T.;
et al. Cropquant: An automated and scalable field phenotyping platform for crop monitoring and trait measurements to facilitate
breeding and digital agriculture. bioRxiv 2017. [CrossRef]
133. Bochtis, D.; Sørensen, C.A.G.; Kateris, D. Operations Management in Agriculture; Elsevier: Amsterdam, The Netherlands, 2019; pp.
1–18. [CrossRef]
134. Terence, S.; Purushothaman, G. Systematic review of Internet of Things in smart farming. Trans. Emerg. Telecommun. Technol. 2020,
31, e3958. [CrossRef]
135. James, A.; Saji, A.; Nair, A.; Joseph, D. CropSense–A Smart Agricultural System using IoT. J. Electron. Des. Eng. 2019, 5, 1–7.
136. Bacco, M.; Barsocchi, P.; Ferro, E.; Gotta, A.; Ruggeri, M. The digitization of agriculture: A survey of research activities on smart
farming. Array 2019, 3–4, 100009. [CrossRef]
137. Ahmed, A.T.; El Gohary, F.; Tzanakakis, V.A.; Angelakis, A.N. Egyptian and Greek Water Cultures and Hydro-Technologies in
Ancient Times. Sustainability 2020, 12, 9760. [CrossRef]
138. Adebayo, S.; Ogunti, E.O.; Akingbade, F.K.; Oladimeji, O. A review of decision support system using mobile applications in the
provision of day-to-day information about farm status for improved crop yield. Period. Eng. Nat. Sci. 2018, 6, 89–99. [CrossRef]
139. Foster, A.D.; Mark, R.R. Microeconomics of technology adoption. Annu. Rev. Econ. 2010, 2, 395–424. [CrossRef]
140. Feder, G.; Just, R.E.; Zilberman, D. Adoption of agricultural innovations in developing countries: A survey. Econ. Dev. Cult.
Chang. 1985, 33, 255–298. [CrossRef]
141. Alvarez, J.; Peter, N. Adoption of computer based information systems: The case of dairy farmers in Canterbury, NZ, and Florida,
Uruguay. Comput. Electron. Agric. 2006, 50, 48. [CrossRef]
142. Kimiti, J.M.; Odee, D.W.; Vanlauwe, B. Area under Grain Legumes Cultivation and Problems Faced by Smallholder Farmers in Legume
Production in the Semi-Arid Eastern Kenya; Academic Press: Cambridge, MA, USA, 2009.
143. Khan, A.R.; Dubey, M.K.; Bisen, P.K.; Saxena, K.K. Constraints faced by farmers of Narsing Kheda village of Sihore district. Young
2007, 8, 16.
144. Abdul Hakkim, V.M.; Abhilash Joseph, E.; Ajay Gokul, A.J.; Mufeedha, K. Precision Farming: The Future of Indian Agriculture. J.
Appl. Biol. Biotechnol. 2016, 4, 068–072. [CrossRef]
145. Fróna, D.; Szenderák, J.; Rákos, M.H. The Challenge of Feeding the World. Sustainability 2019, 11, 5816. [CrossRef]
146. Tzounisa, A.; Katsoulasa, N.; Bartzanasb, T.; Kittas, C. Internet of Things in agriculture, recent advances and future challenges.
Biosyst. Eng. 2017, 164, 31–48. [CrossRef]
Agriculture 2022, 12, 1745 26 of 26

147. Henriksen, A.V.; Edwards, T.C.G.; Pesonen, L.A.; Green, O.; Sørensen, C.A.G. Internet of Things in arable farming: Implementa-
tion, applications, challenges and potential. Biosyst. Eng. 2019, 191, 60–84. [CrossRef]
148. Roth, L.; Aasen, H.; Walter, A.; Liebisch, F. Extracting leaf area index using viewing geometry effects new perspective on
high-resolution unmanned aerial system photography. ISPRS J. Photogramm. Remote Sens. 2018, 141, 161–175. [CrossRef]
149. Chang, A.; Jung, J.; Maeda, M.; Landivar, J. Crop height monitoring with digital imagery from unmanned aerial system (UAV).
Comput. Electron. Agric. 2017, 141, 232–237. [CrossRef]
150. Barrero, O.; Perdomo, S.A. RGB and multispectral UAV image fusion for Gramineae weed detection in rice fields. Precis. Agric.
2018, 19, 809–822. [CrossRef]
151. Lottes, P.; Khanna, R.; Pfeifer, J.; Siegwart, R.; Stachniss, C. UAV-based crop and weed classification for smart farming. In
Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 29 May–3 June 2017;
pp. 3024–3031.
152. Stroppiana, D.; Migliazzi, M.; Chiarabini, V.; Crema, A.; Musanti, M.; Franchino, C.; Villa, P. Rice yield estimation using
multispectral data from UAV: A preliminary experiment in northern Italy. In Proceedings of the 2015 IEEE International
Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy, 26–31 July 2015; pp. 4664–4667.
153. Hassan, M.A.; Yang, M.; Rasheed, A.; Yang, G.; Reynolds, M.; Xia, X.; Xiao, Y.; He, Z. A rapid monitoring of NDVI across the
wheat growth cycle for grain yield prediction using a multi-spectral UAV platform. Plant Sci. 2019, 282, 95–103. [CrossRef]
154. Duan, T.; Chapman, S.; Guo, Y.; Zheng, B. Dynamic monitoring of NDVI in wheat agronomy and breeding trials using an
unmanned aerial vehicle. Field Crops Res. 2017, 210, 71–80. [CrossRef]
155. Su, J.; Liu, C.; Coombes, M.; Hu, X.; Wang, C.; Xu, Z.; Li, Q.; Guo, L.; Chen, W.H. Wheat yellow rust monitoring by learning from
multispectral UAV aerial imagery. Comput. Electron. Agric. 2018, 155, 157–166. [CrossRef]
156. Jin, X.; Liu, S.; Baret, F.; Hemerl, M.; Comar, A. Estimates of plant density of wheat crops at emergence from very low altitude
UAV imagery. Remote Sens. Environ. 2017, 198, 105–114. [CrossRef]
157. Faial, B.S.; Costa, F.G.; Pessin, G.; Ueyama, J.; Freitas, H.; Colombo, A.; Fini, P.H.; Villas, L.; Osrio, F.S.; Vargas, P.A.; et al. The use
of unmanned aerial vehicles and wireless sensor networks for spraying pesticides. J. Syst. Archit. 2014, 60, 393–404.
158. Al-Kodmany, K. The Vertical Farm: A Review of Developments and Implications for the Vertical City. Buildings 2018, 8, 24.
[CrossRef]
159. Cravero, A.; Pardo, S.; Sepúlveda, S.; Muñoz, L. Challenges to Use Machine Learning in Agricultural Big Data: A Systematic
Literature Review. Agronomy 2022, 12, 748. [CrossRef]
160. Kaneko, A.; Kennedy, T.W.; Mei, L.; Sintek, C.; Burke, M.; Ermon, S.; Lobell, D.B. Deep Learning for Crop Yield Prediction in
Africa. In Proceedings of the International Conference on Machine Learning AI for Social Good Workshop, LongBeach, CA, USA,
10–15 June 2019.
161. Oswal, N. Predicting rainfall using Machine Learning Techniques. arXiv 2019, arXiv:1910.13827.
162. Zhang, J.; Zhu, Y.; Zhang, X.; Ye, M.; Yang, J. Developing a Long Short-Term Memory (LSTM) based model for predicting water
table depth in agricultural areas. J. Hydrol. 2018, 561, 918–929. [CrossRef]
163. Ouyang, H.; Wei, X.; Wu, Q. Agricultural commodity futures prices prediction via long- and short-term time series network. J.
Appl. Econ. 2019, 22, 468–483. [CrossRef]
164. Bhattarai, T.N.; Ghimire, S.; Mainali, B.; Gorjian, S.; Treiche, H.; Paudel, S.R. Applications of smart grid technology in Nepal:
Status, challenges, and opportunities. Environ. Sci. Pollut. Res. 2022, 1–25. [CrossRef] [PubMed]
165. Kedri, J. Simulation and Validation of SPV Micro Grid Comprising 518.2 KWp Distributed Solar Power Plants at Dayalbagh
Educational Institute. Ph.D. Thesis, Dayalbagh Educational Institute, Dayalbagh, Agra, India, 2014.
166. Aslam, S.; Khalid, A.; Javaid, N. Towards Efficient Energy Management in Smart Grids Considering Microgrids with Day-ahead
Energy Forecasting. Electr. Power Syst. Res. 2020, 182, 106232. [CrossRef]