IOT Weather

Received: 19 October 2021 Revised: 10 January 2022 Accepted: 24 January 2022 IET Communications
DOI: 10.1049/cmu2.12352
ORIGINAL RESEARCH PAPER
LoRa based intelligent soil and weather condition monitoring

with internet of things for precision agriculture in smart cities
Dushyant Kumar Singh1 Rajeev Sobti1 Anuj Jain1 Praveen Kumar Malik1
Dac-Nhuong Le2,3
1
School of Electronics and Electrical Engineering, Abstract
Lovely Professional University, Punjab, India
Urbanization is expected to hold about 50% of the world population by 2050 and there
2
School of Computer Science, Duy Tan University, will be stress on available resources including food and freshwater. Further, inefficient uti-
Danang, Vietnam
lization of irrigation water possesses additional challenges and it is predicted that by 2050,
3
Institute of Research and Development, Duy Tan India will face shortage of freshwater resources. Urban agriculture and Precision Agricul-
University, Danang, Vietnam
ture are the possible solutions in smart cities for the predicted challenges providing food
Correspondence
security and safety, sustainable life in cities. Internet of Things (IoT) and Machine Learn-
Dac-Nhuong Le, School of Computer Science, Duy ing (ML) are the possible solutions to smart cities’ farming. Agricultural activities such as
Tan University, Danang 550000, Vietnam. irrigation of plants, rain and drought conditions monitoring supported by IoT and ML suc-
Email: [email protected]
cour farmers to righteous decision on agriculture activities. A detailed study is carried out
on the role, opportunities, and different aspects of smart cities, urban farming, communi-
Funding information
Lovely Professional University cation technologies, IoT and ML with respect to agriculture. The article presents the design
of intelligent irrigation system based on soil and weather conditions. The soil and weather
parameters are selected through various research articles in Agriculture 4.0 and ML. The
article also juxtapositions the designed weather station with the various patents developed.
The system developed in this article provides a cost-effective and state-of-the-art solution
to local weather monitoring.
1 INTRODUCTION labor. Urban farming is one of the solutions to provide food and
lessen load on rural agriculture and provide locally grown food
Agriculture is the use of land for the cultivation of crops and to citizens and reduce cost of transportation [3]. Urban agricul-
breeding of animals in a created ecosystem to provide food, ture includes aquaculture, livestock, and plants newly developed
medicinal plants and other products to sustain and enhance concept of agriculture, that is, urban agriculture applies to both
life. Nowadays, agricultural practices are not only limited to rural and urban areas [4].
rural areas. Due to urbanization and shift of population towards Precision Agriculture is the use of technology in agriculture
cities, urban agriculture is providing food security and sustain- so as to provide better solution to monitoring and controlling of
able life in cities. As the cities are becoming smart cities, smart agriculture parameters and thus improving overall production
solution for urban agriculture is also required. Urban agriculture of agriculture products. It involves monitoring of plants, crops,
includes all agricultural activities like breeding animal, fertiliza- soil and weather parameters, livestock etc. Precision Agriculture
tion and most importantly irrigation. Urban agriculture includes helps in efficient utilization of agricultural resources. For exam-
all the sited for food production including the green spaces ple, irrigation, an important aspect of Precision Agriculture and
of gardens, universities and home plantation. Proper irrigation plays an important role in agricultural sector. About 40% of the
practices are required at these sites for efficient utilization of global irrigation water is supplied by ground water and in India
irrigation water. The trend of urbanization in recent years [1, around 39 million hectares of land is irrigated by ground water.
2] has put much stress on agriculture due to loss of land and India only 4% of world’s fresh water resources, out of which
This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided
the original work is properly cited and is not used for commercial purposes.
© 2022 The Authors. IET Communications published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology
604 wileyonlinelibrary.com/iet-com IET Commun. 2022;16:604–618.

17518636, 2022, 5, Downloaded from https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/cmu2.12352 by Cochrane Philippines, Wiley Online Library on [18/05/2023]. See the Terms and Conditions (https://onlinelibrary.wiley.com/terms-and-conditions) on Wiley Online Library for rules of use; OA articles are governed by the applicable Creative Commons License
SINGH ET AL. 605
80% is used for agriculture. So, the efficient utilization of irri- 1.1 Motivation of this paper
gation water through Precision Agriculture is very crucial for
profitable and sustainable agriculture practices [5, 6]. IoT and ML are the leading technologies of the time. Many
Monitoring of soil, weather and plants is important for effi- of the areas like health care, image processing, Wireless Sensor
cient usage of agricultural resources. The important compo- Networks (WSN), cyber and network security are getting ben-
nents of agricultural monitoring are: data collection sensors, efitted from these technologies. The need of improvement in
data transfer using IoT modules, IoT cloud services, application the Precise Water management, due to inefficient conventional
server for data analysis and monitoring device [7]. IoT provides irrigation practices, has forced the authors to study and work
the advanced way to make devices smarter and enable then to on various technologies available to propose a unique effective
communicate and share the information. IoT has been devel- solution. The Agriculture 4.0 motivates the researchers to pro-
oping by utilizing the various technologies and being deployed pose different futuristic ideas based on IoT and ML to improve
by several applications. The IoT application areas and hence- the sector as the need increases day by day. The IoT based
forth the number of devoices connected through IoT are rising Weather station and ML based prediction system to initiate a
exponentially. According to various IT reports, IoT market is IoT based irrigation system would cause an effective change in
going to increase by $14.4 trillion by 2022. IoT implementation implementation is predicted and the work is carried out. The
works with the objective of providing simple end user inter- various research questions intended to be explored thought the
face for data visualization, mor and more deployment of web present article are
enable devices and lowering the barrier in connecting things to
one another. Wi-Fi is the main technology behind the IoT and ∙ RQ1: What is urban farming and role of urban farming in
Wi-Fi based WSNs are the core of IoT. ML typically aims to smart cities
learn from past experience, that is, training data set and once ∙ RQ2: What are the primary soil and weather conditions
the training is completed is capable of classifying or predicting affecting the irrigating planning, and prediction?
things based on training and unknown dataset [8–11]. LPWAN ∙ RQ3: What are commercially available solutions to monitor-
is being increasingly used in IoT applications. LPWAN offers ing soil and local weather conditions?
the low power solution for IoT applications and is important as ∙ RQ4. What are the different agricultural aspects adapting ML
sensing nodes being deployed in open fields. With the advance- actively?
ment in LPWAN, many promising technologies are offered to ∙ RQ5. What role does ML play in water management?
agriculture IoT like NB-IoT, Sigfox, Long Range Wide Area ∙ RQ5. Are the commercially available solutions to monitor-
Netwok-LoRaWAN. LoRaWAN offers good service for IoT ing local weather conditions feasible for deployment by the
solutions to Precision Agriculture due to its long-range commu- farmers?
nication at low power consumption. LPWAN LoRaWAN tech-
nology has been utilized for monitoring of various agriculture
parameter like moisture, humidity, temperature, pH [12, 13]. ML 2 RELATED WORKS
and IoT are the most advanced and proposed ideas in this paper.
ML is a special way of teaching the system or machine to learn Smart cities are the topic of interest amongst researchers and
things and take a wise decision later based on the learnt data. development of IoT is providing many opportunities in smart
The ML has a list of algorithms and classifiers that works based cities. But on of the aspect in smart cities is being neglected is
on the situation and data. For a better efficiency of system, one urban farming and minimal research in available on urban farm-
has to choose appropriate algorithm and classifier. There lie the ing. This section explores the state-of-the-art literature for smart
ways in improving the model performance. The collection of cities, Urban farming, IoT and use of in agriculture.
data and transmission of data is done through IoT technolo-
gies. Connecting the devices through internet and the commu-
nication is held over internet in most of the cases in this new 2.1 Smart cities
era. IoT has brought a great impact on society making people
understand the need of technology in different fields. The IoT The major supporting element for smart cities is communica-
and ML have combined today in most of the fields in giving tion mainly wireless communication technologies like informa-
a valuable and worthy solutions. The weather station and data tion system, monitoring of devices, and control over offered ser-
transmission system is done using IoT and prediction system is vices, etc. The importance of Information and Communication
done using ML in the proposed idea, which gives a strength and Technology (ICT) is elaborated and stressed in many of the lit-
value to the invention on technology point of view. Comparative erature [4, 14–17]. In [18–20], smart cities have been defined as:
study of different weather stations based on the pre-requisites A smart city can be described as an urban locality that
of the smart irrigation is elaborated. The irrigation scheduling employs digital data and technology to create efficiencies for
based on ML is the motive of the paper. The paper is intended boosting the economic development, enhancing the quality of
to find the list of parameters that an innovative irrigation system life, and improving the sustainability of a city
needs. The weather station is built with the parameters and the Smart cities have many definitions, ranging from those focus-
value is logged into cloud platform (ThingSpeak). ing on the technical aspects like what technologies are important
606 SINGH ET AL.
FIGURE 1 Smart city application areas
to those focusing on social aspects like enabling citizens and

communities to act smarter
A smart sustainable city is an innovative city that uses
information and communication technologies (ICTs) and other
means to improve quality of life, the efficiency of urban oper-
ations and services, and competitiveness, while ensuring that it
meets the needs of present and future generations concerning
economic, social and environmental aspects.
The conception of smart cities includes the city organiza-
tion and management as a whole through technology. It is con-
structed and maintained by using integrated technologies, such
as sensors, electronics, and networks.
There are many aspect of smart cities where smart solution
are possible like education, homes, manufacturing, transporta-
tion, farming etc. Each application area of smart city is o associ-
ated with many of the sub-aspects and are elaborated in Figure 1
adapted from [21–24].
FIGURE 2 Urban farming benefits

2.2 Urban agriculture and IoT
Urban farming is d or livestock growth or process that are utilizing IoT are steeply increasing [26]. Industrialization and
undertaken within an urban a or around the urban centers with intensification of agriculture is required to improve the quality
the purpose to generate income, as defined in [25]. Urban farm- and quality of agricultural products to meet increased demand
ing is possible on rooftops, in city grounds, and also on ver- and efficient utilization of agriculture resources. IoT provides
tical walls. Three types of urban farming have been identified propitious solutions for agriculture modernization by providing
namely community farming, vertical farming, and rooftop farm- remote methods for agricultural monitoring and control. Agri-
ing. Urban farming in addition to providing food and source culture application using IoT are livestock management, pre-
of income also contributes towards the city’s green space, gar- cision farming and greenhouse management. Different WSN
den for recreational purpose and conserve the environment and wireless technologies used for agriculture monitoring are Zig-
ecology of the city. The four potential benefits of urban agricul- bee [27–31], LoRaWAN [26, 27, 32–36], Sigfox, NB-IoT [27,
ture have been identified and elaborated in Figure 2 [25]. 33, 37], Wi-Fi [27, 38–42]. Bluetooth [27, 38, 43–45], RFID [27,
IoT provided the mechanism for devices to communicate 29, 46], nRF24l01 [27, 28]. Farm land with IoT based sensors
with each other and makes the devices smarter. IoT is developed and Wireless Sensors Networks (WSNs) gathers relevant infor-
by utilizing various technologies like Embedded Systems, Wire- mation and communicates it to framers. Some of the IoT setups
less Sensor Networks (WSN), communication technologies, for agriculture do analysis the data and suggestions are made
cloud computing and hence being deployed in many applica- to farmer for better planning of agriculture related activities.
tions. The application areas and thereby the number of devices IoT implementations work with the objective of giving end user
SINGH ET AL. 607
TABLE 1 Data and range capacity of LPWAN technologies
Communication
technology Range Data rate
Bluetooth Short Low

BLE Short Low
Zigbee Short Low
6LowPan Short Low
NFC/RFID Short Low
LPWAN Long Low
FIGURE 3 Urban farming benefits
VSAT Long Low
Wi-Fi vLow High
5G Moderate High In Precision Agriculture, WiFi protocol was used to collect
4G Moderate High agriculture data like soil moisture, soil temperature, air tempera-
3G Moderate High ture and humidity, sunlight intensity, Carbon Dioxide. The agri-
2G Moderate High cultural information so obtained is sent to a gateway for storage
before being transmitted to server system through Wi-Fi net-
work. Global Packet Radio Service (GPRS) is GSM – based
data packet service and with WSN is utilized for automatic
simple interface for data visualization, more and more deploy- crop irrigation system. A prototype for drip irrigation system
ment of web-enabled devices, and lowering the barrier in con- was developed and evaluated for soil moisture measurement.
necting things to one another. Wi-Fi based WSNs node are the For transmitting the soil, plant and weather information GPRS
important elements in IoT technology. Different radio commu- was equipped with various wireless sensor nodes. WSN - GPRS
nication technologies are classified on the basis on their range forms a gateway between WSN and GSM for transmitting the
(short, long, moderate) and data rate (low, high), as summarized information from WSN to data management centre where fur-
in Table 1. [11, 47]. ther analysis of data can be done using mobile phones, tablets
WSN is gaining much popularity mainly due to development or computers. SigFox is a wireless cellular network for low data
of IoT based applications and 5G systems. In IoT infrastruc- rate applications and was used to develop geo location system to
ture, WSN is considered to be as one of the main contribut- localize animals in mountain pastures during summer. A system
ing elements. With the continuous demand and penetration to locate cattle and enhance their productivity was implemented
of WSN in different applications, mainly due to steep rise in using SigFox. Next and the latest contender in WSN is LoRa
IoT enabled devices, power efficient and effective communi- alliance established in 2015 and Low PowerWide Area Network
cation between sensor and network sink is required. There are -LoRaWAN is a low power, wide area IoT communication pro-
many WSN parameters which contributes towards the effective tocol. LoRa network basically consists of LoRa end devices,
deployment of WSN technology such as signal strength, access LoRa gateway and LoRa network service. LoRa end devices
technologies, battery life, energy consumption. In WSN, energy is used for communicating with LoRa gateway which employs
consumption can be improved through scheduled data trans- LoRa with LoRaWAN. The raw LoRaWAN data packets are
mission and by using direction antennas [48]. Power efficient passed to LoRa network server by LoRa gateway. LoRa protocol
and long range WSN solutions are also required in Precision was utilised in monitoring of soil moisture, soil temperature, air
Agriculture as the sensor nodes, to gather information about temperature, air humidity and light intensity inside greenhouse
soil and weather conditions, are installed at very remote loca- using different sensors and microcontrollers. Further compar-
tions and frequent service or requirement of frequent replace- ing the various WSN protocols, as shown in Figure 3, LoRa is
ment of battery will not be feasible. Zigbee, Bluetooth, WiFi found as one of the most power efficient solution for long dis-
and GPRS/3G/4G technology, Long Range Radio (LoRa) pro- tant communication. By using Wireless Sensor Network Mon-
tocol, Sigfox are the various wireless protocols available and can itoring system in precision irrigation, the water saving of 90%
be exploited for Precision Agriculture. Zigbee is considered as water using Zigbee [49], 33% of water saving using Zigbee [50],
one of the best members for Precision Agriculture (PA) wire- 90% of water saving using Bluetooth [51] is achieved in compar-
less sensor networks. Zigbee provides communication range up ison to tradition irrigation systems [37, 52–62, 65] (see Figure 3).
to 100 m and as minimum as 30 m for indoor applications. Zig-
bee wireless protocol is adopted in many applications such as
water quality management, irrigation automation, greenhouse 2.3 Machine learning in agriculture 4.0
monitoring and livestock monitoring. Bluetooth is used for the
short-range communication upto 10 m and with BLE range A novel Collaborative Filtering (CF) method algorithm is pro-
can be extended up to 100 m. Bluetooth technology is being posed in the literature [35] and is claimed to be outperformed
used in monitoring weather, soil moisture, temperature and the conventional algorithms for Deep Learning based collab-
sprinkler positioning using Global Positioning System (GPS). orative filtering algorithms. CF is used in various electronic
608 SINGH ET AL.
commerce application like YouTube, Amazon for recom- tant weather parameters measures are temperature, humidity
mendation systems. User preference is predicted by CF after and wind conditions [8, 9, 28, 45, 67–70].
observing the preference history of other similar users. There Agriculture withdraws 70% of the worldwide water and Pre-
are two classes of CF cision Agriculture is an effective tool for efficient utilization
of irrigation water. The advantage of Precision Agriculture is
∙ Nearest neighbor methods which predict the user prefer- profitability, good productivity, precise selection of fertilizers,
ences by considering the rating given by some other similar decrease chemical bills and fuel cost and systemically structured
users. irrigation planning. Remote sensing is a low cost and less labor-
∙ Model based method developed with ML and uses training intensive strategy for farm monitoring. Remote sensing is help-
data to find the pattern for prediction used preference. ing farmers in various applications like classification of crops,
forecasting crop yield, disease detection and management, har-
The proposed CF in [66] is based on supervisor machine vest arrangement and crop water stress detection. ML is an
meaning technique. Learning of the machine can be done effective tool for classification of systems. By applying ML to
through supervised or unsupervised methods. Supervise ML remote sensing data, a real time farm management solution to
method requires a distinct training data but in unsupervised ML farmers can be provided. The article [9] demonstrate that the
there is no difference between test and training data. Some of irrigation scheduling based on crop water stress management
the learning models not limited to are regression, Clustering, not only uses the irrigation water efficiently but also improves
Bayesian, Instance based, Decision tree and Artificial Neural the agriculture yield. Various applications of ML algorithms
Network. ML has been used in different fields of agriculture used for water stress determination is reviewed. Various meth-
as shown in Figure 1 [8]. ods for crop water stress measurement as highlighted in the arti-
Learning of machine is an iterative process and performance cle are shown in Figure 6.
of system under training ameliorate over the time. Once the The article has also provided the important ML algorithms
training is completed the model so trained can be employed which are employed in agriculture and summarized in Figure 6.
for classification, prediction and creating new testing data. Support vector machine, Random Forest classifier, eXtreme
Typical ML approach consists of training dataset fed to ML gradient boosting (XGBoost), Rotation Forest, Oblique ran-
algorithm for training. Once the training is completed, the dom forest and Artificial Neural Networks are some of the
trained algorithm is deployed for prediction and classifica- widely used ML algorithms for crop water stress management
tion of unknown data. Digital agriculture has emerged as a in agriculture. Weather monitoring is the new area of interest
new field aiming to improve the conventional less efficient amongst the researchers due to global climatic changes. Global
agricultural practices, most importantly irrigation. Pressure climatic changes like drought and heavy rain are also affect-
on agriculture will be increasing as a result on continuous ing the utilization of irrigation water. Evapotranspiration is an
increase in world population. Agriculture utilizes technology important factor in determining the irrigation demand or in
called precision agriculture or also termed as digital agriculture. irrigation scheduling. Sensing evapotranspiration using remote
For efficient utilization of agriculture resources like fertilizers, sensing devices and estimating evapotranspiration using ML to
pesticides and most importantly irrigation water new methods the received data offers an efficient way for irrigation plan-
need to be adapted. Now machine leaning in agriculture has ning. For estimating evapotranspiration, it is important to gather
provided opportunities for understanding the data intensive weather temperature, humidity and wind condition informa-
processes related to livestock, soil, crop and water manage- tion. Weather station is a setup, used to collect weather data
ment involved with agricultural environment. ML provided and provides the information to the user. The classification
the machines with the capability to learn. Researches and of weather station present in various literatures is provided in
literatures punished reveals that ML has been used in Precision Table 2. The table has classified the weather monitoring devices
Agriculture for soil management, livestock management, crop on the basis of the way data is collected, transmission technol-
management and water management. ML algorithms use for ogy, deployment of ML and irrigation scheduling. Most of the
soil management, livestock management, crop management researches/literatures have considered evapotranspiration pre-
and water management in precision Agriculture is given in diction using ML for irrigation scheduling [9, 71].
Figure 4.
Water management or precision irrigation is of paramount
importance as fresh water resources in the world are limited and 2.4 Study on various irrigation models
less efficient conventional irrigation methods lead to wastage of
irrigation water along with change in soil properties and reduc- The ignition system of irrigation is automated through IoT
tion in crop yield quality and quality. ML with IoT not only and the decision taken using ML algorithms. The prediction is
provides the proper monitoring and control tools for irrigation done using ML or different process. Different models are devel-
but also assists farmers in irrigation planning by predicting the oped for irrigation scheduling by using weather station and ML
crop water demand for proper irrigation. Figure 5 give the dif- algorithms. The weather station models developed in different
ferent ML algorithms used for water management in agriculture researches/literatures is discussed in Table 3. The most of the
based on parameters evapotranspiration and dew point temper- ML algorithms consider Temperature, wind speed, wind direc-
ature, as shown in Figure 5. For water management the impor- tion, humidity weather conditions.
SINGH ET AL. 609
FIGURE 4 ML algorithms deployed for agricultural application
TABLE 2 Classification of weather station
Parts Functionalities References Key points Conclusion
Data collection Weather stations are built [72–88] [89] Data collection from Sensor node is Data collection is done from a single node
or data is taken from proposed. The station is proposed to in most of the times. The need of
some online site and be Automatic Weather Station-AWS collection from multiple nodes for
fed to the system. where the system sends the data to processing makes the system efficient.
remote user.
Transmission The transmission of data [72, 74] NB IoT, Thing speak, Fog and Edge The efficient use of different systems was
technology from the sensor node [77–81] computing, Zigbee, Lora, Wi-Fi, proposed. The work on Lo-Ra is not
to the central hub. [90, 91] cloud, email, twitter are different ways widely seen in the proposed
proposed. application.
ML Predicting the [73, 80, 84] ML based predictions were done in a Building a system with feature with a real
functionality based on [91–94] better way. The prediction accuracy time data is proposed earlier. The
the received data was mentioned to be above 90 in these actuator and sensor system connected
papers. to a single ML based system where the
actuator is actuated using ML decision
is not widely seen in the research.
Irrigation Scheduling the irrigation [70, 79, 90] The irrigation system includes of The real-time data that is used to evoke
scheduling based on ML results [91–99] actuator based on the IoT signal is the ML system to predict and actuate
and initiating IoT proposed and, in some cases, the the system is not seen in most of the
services to enable decision from pre-loaded data is data is studies. The complexity of merging up
irrigation system. fed as a control signal. the technologies in giving an efficient
solution isn’t seen in most of the cases.
TABLE 3 ML algorithms applied to weather datas
Year/reference Weather station measured parameters ML technique for irrigation scheduling
2015 [72] Temperature, humidity, wind velocity, atmospheric pressure, rain NEN and ANN
2020 [92] Wind speed, wind direction, temperature, rain, humidity, light TCN
2020 [93] Temperature, humidity, solar radiation, wind speed Boost regressing model
2020 [98] Based on soil conditions VAR and RNN-LSTM
2019 [99] Air temperature, humidity, wind speed, precipitation, Radiation Fuzzy logic
610 SINGH ET AL.
FIGURE 8 Soil monitoring sensor node
FIGURE 5 ML algorithms deployed for agricultural application

3 SOIL AND WEATHER
MONITORING SYSTEM
The various element of urban farming is elaborated in Figure 7

[2, 25 84]. The proposed system for soil and weather condi-
tion monitoring consists of two modules namely LoRa based
soil sensor node and Weather monitoring local weather station.
Weather station is connected to weather station through LoRa
wireless communication module and to IoT cloud. Weather sta-
tion uploads the soil and weather conditions to IoT cloud for
monitoring and assisting in irrigation scheduling.
FIGURE 6 Crop water stress measurement methods 3.1 Soil monitoring

The important soil parameters to be monitored for irrigation
planning are soil temperature and soil moisture. Soil mois-
ture estimation is the direct way of irrigation scheduling and
FIGURE 7 Components of urban farming

SINGH ET AL. 611
FIGURE 9 Block diagram of developed system
temperature of soil helps in predicting the irrigation require-

ment. The soil condition monitoring smart sensor node consist
of temperature sensor, soil moisture sensor, processing unit
and LoRa module for communication. Figure 8 shows the
onsite deployed sensor node. Soil sensor node provides the soil
condition sense data to weather station.
3.2 Weather station design
Weather station is a provision, equipped with sensors for mea-

suring environmental conditions. Already mentioned, due to cli-
matic changes environmental monitoring is becoming an active
research area. Climatic conditions do affect and influence the
irrigation planning. Evaluation and advances in IoT have created
new paradigm for environmental monitoring. IoT has provided
the possible solution for expansion of current weather monitor- FIGURE 10 Weather station
ing infrastructure [37]. After evaluating various researches and
literatures for irrigation planning based on weather conditions,
oped weather station is designed to be low cost, for this free IoT
the weather parameters affecting the irrigation scheduling and
cloud server Thingspeak has been selected for data storage and
its prediction using ML are:
visualization. Figure 9 provides the developed weather station
block diagram.
∙ wind speed,
∙ wind direction,
∙ air temperature and
∙ humidity. 4 RESULT AND DISCUSSION
The weather conditions to be sensed by the weather station The system so developed is tested and the data is monitored for
are specifically selected to aid in utilizing ML algorithms for more than a month in November-December, 2020. The local
irrigation prediction and scheduling. The weather station devel- weather station developed for farm land employees DH22 for
oped gathers the required weather information with the help of gathering and temperature and relative humidity. DHT22 is a
suitable sensors. The gathered information is provided to the digital sensor and is much precise and has more range than its
user via IoT. IoT enables the user to monitor field weather con- counterpart DHT11. Figure 5 shows the installed weather sta-
dition as and when required without physically visiting the farm tion for measuring weather conditions and measured weather
land. Weather station developed aims to provide cost effective conditions Thingspeak visualization of air temperature, rela-
solution to local weather monitoring by the farmers. The devel- tive humidity and wind speed is shown through Figures 10–13,
612 SINGH ET AL.
information. The system developed is much cost effective (less

than 50% of the commercially available weather stations with-
out IoT) with IoT technology in comparison to most of the
commercially available weather station. The commercially avail-
able weather station lacks in IoT technology. They either use
local display or GSM for data visualization and transmission
that too at heavy cost addition. Table 4 provides the cost com-
parison (in INR) of different commercially available weather
stations.
Normally the commercial weather stations start from
70,000/- and hence quite high cost is involved in the devel-
opment of commercially available weather station. Moreover,
the commercially available solutions for weather monitoring
are expensive, require specific Information and Communication
FIGURE 11 Air temperature data visualization (ICT) skills to operate, extensive infrastructure and resources.
This makes the commercially available weather stations infea-
sible for operation by farmers. Owing to high cost and diffi-
culty in operating commercial weather stations, farmers avoid
their deployment in farm lands and continues with the conven-
tion less efficient agricultural practices. By making them aware
of the advantages of deploying the technological solutions in
agriculture and providing them accessible low-cost solutions,
farmer can be motivated to shift from conventional farming
to Agriculture 4.0. Using state-of-the-art IoT technology makes
the developed system more reachable; smart and data visualized
on Thingspeak cloud helps in irrigation related decision quickly
and precisely. Apart from offering advantage in terms of cost,
the developed system is adapted with the most suitable weather
parameters, selected after thorough and detailed literature sur-
vey, which are of paramount importance in irrigation planning,
scheduling and prediction via ML. Table 5 compares the devel-
FIGURE 12 Relative humidity data visualization oped weather station with the published patents on weather sta-
tion. The patents so selected are searched using Google patent
search engine with the string weather station and weather sta-
tion WSN.
5 CONCLUSIONS
Role of IoT, remote sensing, ML in agriculture is explored.
The papers summarize the various WSN technologies for IoT,
agriculture applications using IoT and ML. The article also
discussed the importance of soil and weather conditions in
irrigation panning and environmental conditions affecting
the irrigation planning the most. IoT with ML assist farm-
ers in planning agriculture activities precisely. Different ML
algorithms employed in soil monitoring, livestock management,
FIGURE 13 Wind speed data visualization
crop and water management are summarized. The literature
review summarizes the various methods for crop water stress
estimation and also discloses that evapotranspiration estimation
respectively. Figure 14 gives the mobile interface of Things- plays a vital role in crop water stress management. Irrigation
peak cloud. planning based on crop water stress helps in planning irriga-
The weather station developed is a cost-effective system for tion affectively. In the end the article presents the design of IoT
efficient utilization of agricultural irrigation water. Along with enabled weather station with test results. The developed weather
the irrigation water efficient utilization, agricultural yield qual- station is compared with the commercially available weather
ity and quantity can also be increased through predictive irri- station and the patent available on weather station for its
gation by applying the ML algorithms to the provided weather novelty.
SINGH ET AL. 613
TABLE 4 Cost comparison of commercial weather stations
S. no. Weather station product Cost/unit Make IoT feature
1 Automatic weather Station, for industrial: ATM1136a 70,000 Advance Tec India Private Limited No
2 V Tech ultrasonic weather station for agriculture: VT- UWS01b 120,000 V TECH No
3 Portable weather station: 110-WS-18c 325,000 Auro Electronics Private Limited No
4 Automatic weather station, usage: Industrial: RK900-01d 143,000 Infinity Enterprise Private Limited No
5 Automatic weather Station, for officiale 500,000 Nevco Engineer Private Limited No
a
https://www.indiamart.com/proddetail/automatic-weather-station-12477572848.html
b
https://www.indiamart.com/proddetail/ultrasonic-weather-station-19054403862.html
c
https://www.indiamart.com/proddetail/portable-weather-station-4539296991.html
d
e
TABLE 5 Developed weather station comparison with patents
Patent ID Patent Title Year Description Developed System
US10638675B2 Irrigation controller 2020 The invention is irrigation controller The present system is weather station design with IoT
with weather based on local weather station data technology. The weather parameter is such that can
station help in predicting irrigation demand by using ML.
CN203465825U Farmland 2014 The invention provides the information Discussed invention uses Zigbee, suitable for short
environment about soil moisture, soil temperature, distance communication only and GPRS which is a
weather wind speed, wind direction, very infrastructure-oriented resource. The weather
information illumination intensity, Carbon-di-oxide data of farmland is not user friendly. The developed
collection system and air temperature fo the farmland system is a centralized weather station, uses latest
based on Zigbee under observation. Zigbee and GPRS IoT technology for data transmission to cloud. IoT
and GPRS communication technology is used for enables the user to visualize the data in different
data transmission to terminal server. formats like text or graphs fr analysis manually to
tools like ML.
US7171308B2 Weather station 2007 Weather information provided by The discussed system provides the weather
present invention are thunderstorm information like wind speed, wind direction,
and lightning strike. humidity and air temperature for irrigation
planning. The developed weather station used IoT
technology and data is analysis ready for advanced
tool like ML.
US7088221B2 Weather station 2006 The invention discusses the weather The developed system is IoT based with no local
station design with microprocessor display. The data available on cloud can be utilized
unit, atmospheric sensors, memory to for prediction of irrigation requirement with
store weather data and local display advanced ML tools.
unit.
US6967900B2 Combination clock 2005 Weather station in present invention The weather system developed consists of sensor
radio, weather consist of temperature sensor, required to monitor weather conditions for
station and pressure sensor and local display for irrigation scheduling. System is IoT enable not
message organizer data visualization. requiring any local memory for data storage and
ML like advance analysis tool can be applied to data
set from weather station for irrigation demand
prediction.
US5920827A Wireless weather 1999 Weather parameters are measure and The system developed uses IoT technology enabling
station transmitted using radio transmitter. user to visualize data as and when required. Also,
Also used local display for data display. irrigation prediction (using Machen Learning)
along with irrigation planning is possible with
available data from the developed weather station
Due to the climatic change worldwide, environmental mon- concerns in deploying the low-cost sensor like frequent
itoring is day by day becoming one of the active research calibration requirement and their reliability, in field applica-
areas. The commercially available IoT sensors for weather bility and performance. For providing reliable and accurate
monitoring are very costly and complex. IoT low-cost sensors data low-cost sensors requires to be calibrated frequently as
can be used for weather monitoring but there are certain they are affected by environmental conditions. Studies has
614 SINGH ET AL.
FIGURE 14 Mobile IoT interface
confirmed that IoT low-cost sensors are affected by envi- For modeling of environmental factor affecting the sensor
ronmental condition and for calibration of such sensor it is output and applying those models for data correction require
necessary to ML tools. This study has been carried out to understand the
environmental factors contributing to the data quality of low-
∙ Determine environmental factors affecting that data quality cost sensors in IoT. In the study performance of FS, FFS,
of sensor BE, and EFS is evaluated in identifying the factors affecting
∙ Model the those factor that effects sensor data and the sensor data quality [71]. In [94] the challenges related to
∙ Apply the model to sensor data for its correction Precision Irrigation and the identified opportunities for the
SINGH ET AL. 615
DATA AVAILABILITY STATEMENT

The data that support the findings of this study are available
from the corresponding author, upon reasonable request.
ORCID
Praveen Kumar Malik https://orcid.org/0000-0003-3433-
8248
Dac-Nhuong Le https://orcid.org/0000-0003-2601-2803
REFERENCES
1. Ahvenniemi, H., Huovila, A., Pinto-Seppä, I., Airaksinen, M.: What are
the differences between sustainable and smart cities? Cities, 60, 234–245
(2017)
2. Orsini, F., Kahane, R., Nono-Womdim, R., Gianquinto, G.: Urban agri-
FIGURE 15 Precision irrigation challenges and opportunities culture in the developing world: A review. Agron. Sustainable Dev. 33(4),
695–720 (2013). https://doi.org/10.1007/s13593-013-0143-z
3. Martin, M., Molin, E.: Environmental assessment of an urban vertical
hydroponic farming system in Sweden. Sustainability 11(15), 4124 (2019)
mentioned challenges are elaborated and is summarized in 4. De Bon, H., Parrot, L., Moustier, P.: Sustainable urban agriculture in devel-
oping countries: A review. Agron. Sustainable Dev. 30(1), 21–32 (2010).
Figure 15. https://doi.org/10.1051/agro:2008062
5. Department of Agriculture, Cooperation & Farmers Welfare Ministry of
Agriculture & Farmers Welfare Government of India (2018): Krishi Report
LIST OF ABBREVIATIONS 2017-2018. http://www.agricoop.nic. Accessed 30 April 2021
6. Dhawan, V.: Water and Agriculture in India: “Status, Challenges and Pos-
sible Options for Action”. Water and Agriculture in India: Background
6 LoWPAN Low -Power Wireless Personal Area Networks Paper for the South Asia Expert Panel During the Global Forum for Food
ANN Artificial Neural Network and Agriculture. German Asia-Pacific Business Association, Hamburg
ANN Artificial Neural Network (2017). https://www.oav.de/fileadmin/user_upload/5_Publikationen/5_
BE Backward Elimination Studien/170118_Study_Water_Agriculture_India.pdf
BLE Bluetooth Low Energy 7. Abioye, E.A., Abidin, M.S.Z., Mahmud, M.S.A., Buyamin, S., Ishak,
M.H.I., Abd Rahman, M.K.I., … & Ramli, M.S.A.: A review on moni-
CP Counter Propagation toring and advanced control strategies for precision irrigation. Comput.
CWSI Crop Water Stress Index Electron. Agric. 173, 105441 (2020). https://doi.org/10.1016/j.compag.
DNN Deep Neural Networks 2020.105441
DT Decision Trees 8. Liakos, K.G., Busato, P., Moshou, D., Pearson, S., Bochtis, D.: ML in agri-
EFS Exhaustive Feature Selection culture: A review. Sensors 18(8), 2674 (2018)
9. Virnodkar, S.S., Pachghare, V.K., Patil, V.C., Jha, S.K.: Remote sensing and
ELM Extreme Learning Machine ML for crop water stress determination in various crops: a critical review.
FFS Forward Feature Selection Precis. Agric. 21(5), 1121–1155 (2020)
FS Feature Selection 10. Park, H., Kim, H., Joo, H., Song, J.: Recent advancements in the Internet-
GRNN Generalized Regression Neural Network of-Things related standards: A one M2M perspective. ICT Exp. 2(3), 126–
ICT Information and Communication Technology 129 (2016). https://doi.org/10.1016/j.icte.2016.08.009
11. Davoli, L., Belli, L., Cilfone, A., Ferrari, G.: Integration of Wi-Fi mobile
IoT Internet of Things nodes in a Web of Things Testbed. ICT Exp. 2(3), 96–99 (2016).
LPWAN Low-Power Wide-Area Network https://doi.org/10.1016/j.icte.2016.07.001
MARS Multivariate Adaptive Regression Splines 12. Miles, B., Bourennane, E.B., Boucherkha, S., Chikhi, S.: A study of
NFC Near Field Communication LoRaWAN protocol performance for IoT applications in smart agricul-
RFID Radio-Frequency Identification ture. Comput. Commun. 164, 148–157 (2020)
13. Prakosa, S.W., Faisal, M., Adhitya, Y., Leu, J.S., Köppen, M., Avian, C.:
SVM Support Vector Machines Design and implementation of LoRa based IoT scheme for Indone-
VSAT Very Small Aperture Terminal sian rural area. Electronics 10(1), 77 (2021). https://doi.org/10.3390/
electronics10010077
14. Mohanty, S.P., Choppali, U., Kougianos, E.: Everything you wanted to
ACKNOWLEDGEMENTS know about smart cities: The internet of things is the backbone. IEEE
Consum. Electron. Mag. 5(3), 60–70 (2016). https://doi.org/10.1109/
This paper and the research behind it would not have been pos- MCE.2016.2556879
sible without the exceptional support of our supervisor. His 15. Ibarra-Esquer, J.E., González-Navarro, F.F., Flores-Rios, B.L., Burtseva,
enthusiasm, knowledge, and exacting attention to detail have L., Astorga-Vargas, M.A.: Tracking the evolution of the internet of things
been an inspiration and kept our work on track. This research concept across different application domains. Sensors 17(6), 1379 (2017)
was partially supported by Lovely Professional University, Phag- 16. Longo, F., Padovano, A., Umbrello, S.: Value-oriented and ethical technol-
ogy engineering in industry 5.0: A human-centric perspective for the design
wara, Punjab, India. of the factory of the future. Appl. Sci. 10(12), 4182 (2020)
17. Zhang, L., Dabipi, I.K., Brown Jr, W.L.: Internet of Things applications
CONFLICT OF INTEREST for agriculture. Internet of things A to Z: Technologies and Applications
All the authors hereby declare no conflict of interest of any type 507–528 (2018). https://doi.org/10.1002/9781119456735.ch18
616 SINGH ET AL.
18. Yigitcanlar, T., Kankanamge, N., Vella, K.: How are smart city concepts 2015 IEEE International Conference on Industrial Technology (ICIT),
and technologies perceived and utilized? A systematic geo-Twitter analysis pp. 2420–2425. IEEE, Piscataway (2015). https://doi.org/10.1109/ICIT.
of smart cities in Australia. J. Urban Technol. 28(1–2), 135–154 (2021). 2015.7125454
https://doi.org/10.1080/10630732.2020.1753483 38. Muangprathub, J., Boonnam, N., Kajornkasirat, S., Lekbangpong, N.,
19. Patel, Y., Doshi, N.: Social implications of smart cities. Procedia Comput. Wanichsombat, A., Nillaor, P.: IoT and agriculture data analysis for smart
Sci. 155, 692–697 (2019). https://doi.org/10.1016/j.procs.2019.08.099 farm. Comput. Electron. Agric. 156, 467–474 (2019). https://doi.org/10.
20. Al-Smadi, A.M., Alsmadi, M.K., Baareh, A., Almarashdeh, I., Abouelmagd, 1016/j.compag.2018.12.011
H., Ahmed, O.S. S.: Emergent situations for smart cities: a survey. Int. J. 39. Ofori-Dwumfuo, G. O., Salakpi, S.V.: WiFi and WiMAX deployment at
Electr. Comput. Syst. Eng. 9(6), 2088–8708 (2019) the Ghana Ministry of Food and Agriculture. Res. J. Appl. Sci. Eng. Tech-
21. Alavi, A.H., Jiao, P., Buttlar, W.G., Lajnef, N.: Internet of Things-enabled nol. 3(12), 1374–1383 (2011). https://maxwellsci.com/jp/abstract.php?
smart cities: State-of-the-art and future trends. Measurement 129, 589–606 jid=RJASET&no=155&abs=05
(2018). https://doi.org/10.1016/j.measurement.2018.07.067 40. Gonzãlez-Amarillo, C.A., Corrales-Muñoz, J.C., Mendoza-Moreno, M.Ã.,
22. Letaifa, S.B.: How to strategize smart cities: Revealing the SMART model. J. Hussein, A.F., Arunkumar, N., Ramirez-Gonzãlez, G.: An IoT-based trace-
Business Res. 68(7), 1414–1419 (2015). https://doi.org/10.1016/j.jbusres. ability system for greenhouse seedling crops. IEEE Access 6, 67528–
2015.01.024 67535 (2018). https://doi.org/10.1109/ACCESS.2018.2877293
23. Kiran, D., Sharma, I., Garg, I.: Industry 5.0 and smart cities: A 41. Dholu, M., Ghodinde, K.A.: Internet of things (IoT) for precision agricul-
futuristic approach. Eur. J. Mol. Clin. Med. 7(8), 2750–2756 (2020). ture application. In: 2018 2nd International Conference on Trends in Elec-
https://ejmcm.com/article_4786.html#:∼:text=Smart%20cities% tronics and Informatics (ICOEI), pp. 339–342. IEEE, Piscataway (2018).
20aim%20at%20a,of%20a%20human%20and%20robot https://doi.org/10.1109/ICOEI.2018.8553720
24. Albino, V., Berardi, U., Dangelico, R.M.: Smart cities: Definitions, dimen- 42. AshifuddinMondal, M., Rehena, Z.: IoT based intelligent agriculture field
sions, performance, and initiatives. J. Urban Technol. 22(1), 3–21 (2015). monitoring system. In: 2018 8th International Conference on Cloud
https://doi.org/10.1080/10630732.2014.942092 Computing, Data Science & Engineering (Confluence), pp. 625–629.
25. Yusoff, N.H., Hussain, M.R.M., Tukiman, I.: Roles of community IEEE, Piscataway (2018). https://doi.org/10.1109/CONFLUENCE.
towards urban farming activities. Planning Malaysia 15(1), 271–278 (2017). 2018.8442535
https://doi.org/10.21837/pm.v15i1.243 43. Noda, A., Fukuda, O., Okumura, H., Arai, K.: Behavior analysis of a
26. dos Santos, U. J. L., Pessin, G., da Costa, C.A., da Rosa Righi, R.: small animal using IoT sensor system. In: 2017 International Confer-
AgriPrediction: A proactive internet of things model to anticipate prob- ence on Intelligent Informatics and Biomedical Sciences (ICIIBMS), pp.
lems and improve production in agricultural crops. Comput. Electron. 9–10. IEEE, Piscataway (2017). https://doi.org/10.1109/ICIIBMS.2017.
Agric. 161, 202–213 (2019) 8279686
27. Mohammadi, K., Shamshirband, S., Motamedi, S., Petković, D., Hashim, 44. Bing, F.: Research on the agriculture intelligent system based on IoT. In:
R., Gocic, M.: Extreme learning machine based prediction of daily dew 2012 International Conference on Image Analysis and Signal Processing,
point temperature. Comput. Electron. Agric. 117(C), 214–225 (2015). pp. 1–4. IEEE, Piscataway (2012). https://doi.org/10.1109/IASP.2012.
https://doi.org/10.1016/j.compag.2015.08.008 6425066
28. Li, L., Xiaoguang, H., Ke, C., Ketai, H.: The applications of wifi- 45. Li, J., Gu, W., Yuan, H.: Research on IoT technology applied to intelli-
based wireless sensor network in internet of things and smart grid. In: gent agriculture. In: Proceedings of the 5th International Conference on
2011 6th IEEE Conference on Industrial Electronics and Applications, Electrical Engineering and Automatic Control, pp. 1217–1224. Springer,
pp. 789–793. IEEE, Piscataway (2011). https://doi.org/10.1109/ICIEA. Berlin, Heidelberg (2016)
2011.5975693 46. Wasson, T., Choudhury, T., Sharma, S., Kumar, P.: Integration of RFID
29. Ruiz-Garcia, L., Lunadei, L., Barreiro, P., Robla, I.: A review of wireless and sensor in agriculture using IoT. In: 2017 International Conference
sensor technologies and applications in agriculture and food industry: state on Smart Technologies For Smart Nation (SmartTechCon), pp. 217–222.
of the art and current trends. Sensors 9(6), 4728–4750 (2009) IEEE, Piscataway (2017). https://doi.org/10.1109/SmartTechCon.2017.
30. Liu, S., Guo, L., Webb, H., Ya, X., Chang, X.: Internet of Things monitor- 8358372
ing system of modern eco-agriculture based on cloud computing. IEEE 47. Mekki, K., Bajic, E., Chaxel, F., Meyer, F.: A comparative study of LPWAN
Access 7, 37050–37058 (2019) technologies for large-scale IoT deployment. ICT Exp. 5(1), 1–7 (2019).
31. Zhang, X., Zhang, J., Li, L., Zhang, Y., Yang, G.: Monitoring citrus soil https://doi.org/10.1016/j.icte.2017.12.005
moisture and nutrients using an IoT based system. Sensors 17(3), 447 48. Albagory, Y.: An efficient sweeping beamforming technique for low-
(2017) altitude platform-to-sensor communications. ICT Exp. 7(1), 88–93 (2021).
32. Davcev, D., Mitreski, K., Trajkovic, S., Nikolovski, V., Koteli, N.: IoT agri- https://doi.org/10.1016/j.icte.2020.03.006
culture system based on LoRaWAN. In: 2018 14th IEEE International 49. Tzounis, A., Katsoulas, N., Bartzanas, T., Kittas, C.: Internet of Things in
Workshop on Factory Communication Systems (WFCS), pp. 1–4. IEEE, agriculture, recent advances and future challenges. Biosyst. Eng. 164, 31–
Piscataway (2018). https://doi.org/10.1109/WFCS.2018.8402368 48 (2017). https://doi.org/10.1016/j.biosystemseng.2017.09.007
33. Elijah, O., Rahman, T.A., Orikumhi, I., Leow, C.Y., Hindia, M.N.: An 50. Popović, T., Latinović, N., Pečić, A., Zečević, Ž., Krstajić, B., Djukanović,
overview of Internet of Things (IoT) and data analytics in agriculture: S.: Architecting an IoT-enabled platform for precision agriculture and eco-
Benefits and challenges. IEEE Internet Things J. 5(5), 3758–3773 (2018). logical monitoring: A case study. Comput. Electron. Agric. 140, 255–265
https://doi.org/10.1109/JIOT.2018.2844296 (2017)
34. Heble, S., Kumar, A., Prasad, K.V.D., Samirana, S., Rajalakshmi, P., Desai, 51. Valluru, D., Kotikam, G., Haribabu, K.: Smart agriculture management of
U.B.: A low power IoT network for smart agriculture. In: 2018 IEEE 4th intelligent things using NB-IoT. Int. J. Modern Agri. 10(1), 78–86 (2021)
World Forum on Internet of Things (WF-IoT), pp. 609–614. IEEE, Pis- 52. Farooq, M.S., Riaz, S., Abid, A., Umer, T., Zikria, Y.B.: Role of IoT tech-
cataway (2018). https://doi.org/10.1109/WF-IoT.2018.8355152 nology in agriculture: A systematic literature review. Electronics 9(2), 319
35. Giordano, S., Seitanidis, I., Ojo, M., Adami, D., Vignoli, F.: IoT solutions (2020). https://doi.org/10.3390/electronics9020319
for crop protection against wild animal attacks. In: 2018 IEEE interna- 53. Jawad, H.M., Nordin, R., Gharghan, S.K., Jawad, A.M., Ismail, M.: Energy-
tional conference on Environmental Engineering (EE), pp. 1–5. IEEE, efficient wireless sensor networks for precision agriculture: A review. Sen-
Piscataway (2018). https://ieeexplore.ieee.org/document/8385275 sors 17(8), 1781 (2017)
36. Mohanraj, I., Ashokumar, K., Naren, J.: Field monitoring and automa- 54. Valente, J., Sanz, D., Barrientos, A., Cerro, J.D., Ribeiro, Á., Rossi, C.: An
tion using IOT in agriculture domain. Procedia Comput. Sci. 93, 931–939 air-ground wireless sensor network for crop monitoring. Sensors 11(6),
(2016). https://doi.org/10.1016/j.procs.2016.07.275 6088–6108 (2011). https://doi.org/10.3390/s110606088
37. Llaria, A., Terrasson, G., Arregui, H., Hacala, A.: Geolocation and 55. Aiello, G., Giovino, I., Vallone, M., Catania, P., Argento, A.: A deci-
monitoring platform for extensive farming in mountain pastures. In: sion support system based on multisensor data fusion for sustainable
SINGH ET AL. 617
greenhouse management. J. Cleaner Prod. 172(20), 4057–4065 (2018). Irrigation Sci. 33(6), 411–427 (2015). https://doi.org/10.1007/s00271-
https://doi.org/10.1016/j.jclepro.2017.02.197 015-0478-0
56. Benaissa, S., Plets, D., Tanghe, E., Verloock, L., Martens, L., Hoebeke, J., 74. Citterio, M., van As, D., Ahlstrøm, A. P., Andersen, M.L., Andersen,
Joseph, W.: Experimental characterisation of the off-body wireless channel S.B., Box, J.E., … Veicherts, M.: Automatic weather stations for
at 2.4 GHz for dairy cows in barns and pastures. Comput. Electron. Agric. basic and applied glaciological research. GEUS Bull. 33, 69–72 (2015).
127, 593–605 (2016). https://doi.org/10.1016/j.compag.2016.07.026 https://doi.org/10.34194/geusb.v33.4512
57. Ruirui, Z., Liping, C., Jianhua, G., Zhijun, M., Gang, X.: An energy- 75. Moore, G. W. K., Cristofanelli, P., Bonasoni, P., Verza, G.P., Semple, J.L.:
efficient wireless sensor network used for farmland soil moisture mon- Automatic weather station observations of the April 2014 Mount Everest
itoring. In: IET International Conference on Wireless Sensor Network avalanche. Arctic Antarctic Alpine Res. 49(2), 321–330 (2017). https://doi.
2010 (IET-WSN 2010), pp. 2–6. IET, Stevenage (2010). https://doi.org/ org/10.1657/AAAR0016-059
10.1049/cp.2010.1017 76. Smeets, P.C., Kuipers Munneke, P., Van As, D., van den Broeke, M.R.,
58. Navarro-Hellín, H., Torres-Sánchez, R., Soto-Valles, F., Albaladejo-Pérez, Boot, W., Oerlemans, H., … van de Wal, R.S.: The K-transect in west
C., López-Riquelme, J.A., Domingo-Miguel, R.: A wireless sensors archi- Greenland: Automatic weather station data (1993-2016). Arctic Antarc-
tecture for efficient irrigation water management. Agric. Water Manage. tic Alpine Res. 50(1), S100002 (2018). https://doi.org/10.1080/15230430.
151, 64–74 (2015). https://doi.org/10.1016/j.agwat.2014.10.022 2017.1420954
59. Pití, A., Verticale, G., Rottondi, C., Capone, A., Lo Schiavo, L.: The role 77. Sarkar, I., Pal, B., Datta, A., Roy, S.: Wi-Fi-based portable weather station
of smart meters in enabling real-time energy services for households: for monitoring temperature, relative humidity, pressure, precipitation, wind
The Italian case. Energies 10(2), 199 (2017). https://doi.org/10.3390/ speed, and direction. In: Information and Communication Technology for
en10020199 Sustainable Development, pp. 399–404. Springer, Singapore (2020)
60. Ojha, T., Misra, S., Raghuwanshi, N.S.: Wireless sensor networks for agri- 78. Jianyun Chen, Yunfan Sun, Chunyan Lin: Research on Application of
culture: The state-of-the-art in practice and future challenges. Comput. Automatic Weather Station Based on Internet of Things. IOP Con-
Electron. Agric. 118, 66–84 (2015). https://doi.org/10.1016/j.compag. ference Series: Earth and Environmental Science. 104, 012015 (2017).
2015.08.011 http://doi.org/10.1088/1755-1315/104/1/012015
61. Azaza, M., Tanougast, C., Fabrizio, E., Mami, A.: Smart greenhouse fuzzy 79. Ferrández-Pastor, F.J., García-Chamizo, J.M., Nieto-Hidalgo, M., Mora-
logic based control system enhanced with wireless data monitoring. ISA Martínez, J.: Precision agriculture design method using a distributed com-
Trans. 61, 297–307 (2016) puting architecture on internet of things context. Sensors 18(6), 1731
62. Kim, Y., Evans, R.G.: Software design for wireless sensor-based site- (2018)
specific irrigation. Comput. Electron. Agric. 66(2), 159–165 (2009). 80. Math, R.K.M., Dharwadkar, N.V.: IoT Based low-cost weather sta-
https://doi.org/10.1016/j.compag.2009.01.007 tion and monitoring system for precision agriculture in India. In:
63. Zhang, F.: Research on applications of Internet of Things in agriculture. 2018 2nd International Conference on I-SMAC (IoT in Social, Mobile,
In: Informatics and Management Science VI, pp. 69–75. Springer, London Analytics and Cloud)(I-SMAC), pp. 81–86. IEEE, Piscataway (2018).
(2013). https://doi.org/10.1007/978-1-4471-4805-0_9 https://doi.org/10.1109/I-SMAC.2018.8653749
64. Pallavi, S., Mallapur, J.D., Bendigeri, K.Y.: Remote sensing and con- 81. Chebbi, W., Benjemaa, M., Kamoun, A., Jabloun, M., Sahli, A.: Devel-
trolling of greenhouse agriculture parameters based on IoT. In 2017 opment of a WSN integrated weather station node for an irrigation
International Conference on Big Data, IoT and Data Science (BID), alert program under Tunisian conditions. In: Eighth International Multi-
pp. 44–48. IEEE, Piscataway (2017). https://doi.org/10.1109/BID.2017. Conference on Systems, Signals & Devices, pp. 1–6. IEEE, Piscataway
8336571 (2011). https://doi.org/10.1109/SSD.2011.5767494
65. Terrasson, G., Llaria, A., Marra, A., Voaden, S.: Accelerometer based solu- 82. Hema, N., Kant, K.: Cost-effective smart irrigation controller using auto-
tion for precision livestock farming: Geolocation enhancement and ani- matic weather stations. Int. J. Hydrol. Sci. Technol. 9(1), 1–27 (2019).
mal activity identification. In: IOP Conference Series: Materials Science https://doi.org/10.1504/IJHST.2019.096795
and Engineering, Vol. 138(1), p. 012004. IOP Publishing, Bristol (2016). 83. Lorite, I.J., Ramírez-Cuesta, J.M., Cruz-Blanco, M., Santos, C.: Using
https://doi.org/10.1088/1757-899X/138/1/012004 weather forecast data for irrigation scheduling under semi-arid conditions.
66. Puar, V. H., Bhatt, C. M., Hoang, D. M., Le, D. N: Communication in inter- Irrigation Sci. 33(6), 411–427 (2015). https://doi.org/10.1007/s00271-
net of things. Information Systems Design and Intelligent Applications 015-0478-0
, 272–281 (Springer, Singapore 2018). https://doi.org/10.1007/978-981- 84. Kapoor, P., Barbhuiya, F.A.: Cloud Based Weather Station using IoT
10-7512-4_28 Devices. In: TENCON 2019–2019 IEEE Region 10 Conference (TEN-
67. Mehdizadeh, S., Behmanesh, J., Khalili, K.: Using MARS, SVM, GEP and CON), pp. 2357–2362. IEEE, Piscataway (2019). https://doi.org/10.
empirical equations for estimation of monthly mean reference evapotran- 1109/TENCON.2019.8929528
spiration. Comput. Electron. Agric. 139, 103–114 (2017) 85. Kodali, R.K., Sahu, A.: An IoT based weather information prototype using
68. Feng, Y., Peng, Y., Cui, N., Gong, D., Zhang, K.: Modeling reference evap- WeMos. In: 2016 2nd International Conference on Contemporary Com-
otranspiration using extreme learning machine and generalized regression puting and Informatics (IC3I), pp. 612–616. IEEE, Piscataway (2016).
neural network only with temperature data. Comput. Electron. Agric. 136, https://doi.org/10.1109/IC3I.2016.7918036
71–78 (2017). https://doi.org/10.1016/j.compag.2017.01.027 86. Kodali, R.K., Mandal, S.: IoT based weather station. In: 2016 International
69. Patil, A.P., Deka, P.C.: An extreme learning machine approach for modeling Conference on Control, Instrumentation, Communication and Computa-
evapotranspiration using extrinsic inputs. Comput. Electron. Agric. 121, tional Technologies (ICCICCT), pp. 680–683. IEEE, Piscataway (2016).
385–392 (2016). https://doi.org/10.1016/j.compag.2016.01.016 https://doi.org/10.1109/ICCICCT.2016.7988038
70. Buchholz, M., Musshoff, O.: The role of weather derivatives and portfolio 87. El-Magrous, A.A., Sternhagen, J.D., Hatfield, G., Qiao, Q.: Internet of
effects in agricultural water management. Agric. Water Manage. 146, 34–44 Things based weather-soil sensor station for precision agriculture. In:
(2014). https://doi.org/10.22004/ag.econ.165812 2019 IEEE International Conference on Electro Information Technology
71. Okafor, N.U., Alghorani, Y., Delaney, D.T.: Improving data quality of low- (EIT), pp. 092–097. IEEE, Piscataway (2019). https://doi.org/10.1109/
cost IoT sensors in environmental monitoring networks using data fusion EIT.2019.8833811
and ML approach. ICT Exp. 6(3), 220–228 (2020). https://doi.org/10. 88. Bienvenido-Huertas, D., Rubio-Bellido, C., Pérez-Ordóñez, J.L., Martínez-
1016/j.icte.2020.06.004 Abella, F.: Estimating adaptive setpoint temperatures using weather sta-
72. Mestre, G., Ruano, A., Duarte, H., Silva, S., Khosravani, H., Pesteh, S., tions. Energies 12(7), 1197 (2019). https://doi.org/10.3390/en12071197
Horta, R.: An intelligent weather station. Sensors 15(12), 31005–31022 89. Paul Mousumi, Sanyal Goutam, Samanta Debabrata, Nguyen Gia Nhu, Le
(2015) Dac-Nhuong: Admission control algorithm based on the effective band-
73. Lorite, I.J., Ramírez-Cuesta, J.M., Cruz-Blanco, M., Santos, C.: Using width in vehicle-to-infrastructure communication. IET Communications.
weather forecast data for irrigation scheduling under semi-arid conditions. 12, (6), 704–711 (2018). http://doi.org/10.1049/iet-com.2017.0825
618 SINGH ET AL.
90. Fourati, M.A., Chebbi, W., Kamoun, A.: Development of a web-based 96. Prasad, A.S., Umamahesh, N.V., Viswanath, G.K.: Optimal irrigation plan-
weather station for irrigation scheduling. In: 2014 Third IEEE Inter- ning model for an existing storage based irrigation system in India. Irriga-
national Colloquium in Information Science and Technology (CIST), tion Drainage Syst. 25(1), 19–38 (2011). https://doi.org/10.1007/s10795-
pp. 37–42. IEEE, Piscataway (2014). https://doi.org/10.1109/CIST.2014. 011-9108-z
7016591 97. Monteleone, S., Moraes, E. A. D., Tondato de Faria, B., Aquino Junior, P.T.,
91. Vellidis, G., Liakos, V., Andreis, J.H., Perry, C.D., Porter, W.M., Barnes, Maia, R.F., Neto, A.T., Toscano, A.: Exploring the adoption of precision
E.M., … Migliaccio, K.W.: Development and assessment of a smartphone agriculture for irrigation in the context of agriculture 4.0: The key role of
application for irrigation scheduling in cotton. Comput. Electron. Agric. Internet of Things. Sensors 20(24), 7091 (2020)
127, 249–259 (2016). https://doi.org/10.1016/j.compag.2016.06.021 98. Togneri, R., Kamienski, C., Dantas, R., Prati, R., Toscano, A., Soininen,
92. Hewage, P., Behera, A., Trovati, M., Pereira, E., Ghahremani, M., Palmieri, J.P., Cinotti, T.S.: Advancing IoT-based smart irrigation. IEEE Internet
F., Liu, Y.: Temporal convolutional neural (TCN) network for an effec- of Things Mag. 2(4), 20–25 (2019). https://doi.org/10.1109/IOTM.0001.
tive weather forecasting using time-series data from the local weather sta- 1900046
tion. Soft Comput. 24(21), 16453–16482 (2020). https://doi.org/10.1007/ 99. Li, M., Sui, R., Meng, Y., Yan, H.: A real-time fuzzy decision support sys-
s00500-020-04954-0 tem for alfalfa irrigation. Comput. Electron. Agric. 163, 104870 (2019).
93. Ponraj, A.S., Vigneswaran, T.: Daily evapotranspiration prediction using https://doi.org/10.1016/j.compag.2019.104870
gradient boost regression model for irrigation planning. J. Supercomput.
76(8), 5732–5744 (2019)
94. Zhang, J., Guan, K., Peng, B., Jiang, C., Zhou, W., Yang, Y., … Cai,
Y.: Challenges and opportunities in precision irrigation decision-support
systems for center pivots. Environ. Res. Lett. 16(5), 053003 (2021).
https://doi.org/10.1088/1748-9326/abe436 How to cite this article: Singh, D.K., Sobti, R., Jain,
95. Sabir Zulqurnain, Nisar Kashif, Zahoor Raja Muhammad Asif, Haque A., Malik, P.K., Le, D.-N.: LoRa based intelligent soil and
Muhammad Reazul, Umar Muhammad, Ag Ibrahim Ag Asri, Le Dac- weather condition monitoring with internet of things for
Nhuong: IoT Technology Enabled Heuristic Model With Morlet Wavelet
precision agriculture in smart cities. IET Commun. 16,
Neural Network for Numerical Treatment of Heterogeneous Mosquito
Release Ecosystem. IEEE Access. 9, 132897–132913 (2021). http://doi. 604–618 (2022). https://doi.org/10.1049/cmu2.12352
org/10.1109/access.2021.3113986

IOT Weather

Uploaded by

Copyright:

Available Formats

IOT Weather

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

IOT Weather

Uploaded by

Copyright:

Available Formats

Received: 19 October 2021 Revised: 10 January 2022 Accepted: 24 January 2022 IET Communications

ORIGINAL RESEARCH PAPER

LoRa based intelligent soil and weather condition monitoring

604 wileyonlinelibrary.com/iet-com IET Commun. 2022;16:604–618.

FIGURE 1 Smart city application areas

to those focusing on social aspects like enabling citizens and

FIGURE 2 Urban farming benefits

TABLE 1 Data and range capacity of LPWAN technologies

Bluetooth Short Low

FIGURE 4 ML algorithms deployed for agricultural application

TABLE 2 Classification of weather station

Parts Functionalities References Key points Conclusion

TABLE 3 ML algorithms applied to weather datas

Year/reference Weather station measured parameters ML technique for irrigation scheduling

FIGURE 8 Soil monitoring sensor node

FIGURE 5 ML algorithms deployed for agricultural application

The various element of urban farming is elaborated in Figure 7

FIGURE 6 Crop water stress measurement methods 3.1 Soil monitoring

FIGURE 7 Components of urban farming

FIGURE 9 Block diagram of developed system

temperature of soil helps in predicting the irrigation require-

3.2 Weather station design

Weather station is a provision, equipped with sensors for mea-

information. The system developed is much cost effective (less

TABLE 4 Cost comparison of commercial weather stations

S. no. Weather station product Cost/unit Make IoT feature

TABLE 5 Developed weather station comparison with patents

Patent ID Patent Title Year Description Developed System

FIGURE 14 Mobile IoT interface

DATA AVAILABILITY STATEMENT

You might also like