
Results in Engineering 22 (2024) 102283
4
challenges, such as improving the agricultural elds’ productivity is
presented by Patil et al. [44]. This system connects both sensors and
irrigation control apparatus to the Cloud. This way, the system’s overall
architecture provides better analysis and problem-solving abilities.
WALLeSMART is a cloud-based solution that Roukh et al. [45] proposed
to develop a smart agricultural management system for the Wallonia
region in Belgium. This suggestion addresses the challenges of collect-
ing, processing, and visualizing massive amounts of agricultural data in
real time. A prototype was developed and evaluated with diverse cul-
tures, and the results showed outstanding efcacy. Kodandaramaiah
et al. [46] suggested a sophisticated IoT and cloud-computing-based
agriculture monitoring system. This system uses sensors to periodi-
cally collect temperature, humidity, soil moisture, and light inside a
greenhouse. Collected data is sent to the Cloud for real-time processing
and storage. This system’s ability to optimize the farmers’ resources and
its low cost make it available to everyone, including small farmers.
Froiz-Meguiez et al. [47] presented a smart irrigation system that
combines LoRa-based IoT sensors, fog computing gateways, and remote
cloud computing. The sensors collect real-time data and send it to the fog
or the Cloud to control the water supply. The results demonstrated the
system’s ability to reduce water consumption by 23 %. The role of the
computing model, deployment model, cloud service model, and the
benets and challenges of cloud computing in the agriculture sector are
discussed by Choudhary et al. [48]. An IoT-based soil moisture moni-
toring (IoT-SM) method using moisture sensors and an ET–based strat-
egy was compared in the study done by Kumar et al. [49]. This study
showed that the IoT system was durable and water-resistant, making it
suitable for outdoor agriculture. Climate-SA (CSA) is discussed by Bengü
Everest [50]. This study was conducted to introduce farmers ’adaptation
to climate change. Farmers’ perceptions of CSA were also taken into
consideration. The authors examined the literature to analyze the
adoption of CSA. They also presented a typology for CSA applications.
The results show that CSA classes have high application potential among
farmers. Helena Shilomboleni [51] highlights the three important
challenges of Africa’s CSA activities. This study provides an overview of
the contested discussions about CSA’s ability to comprehensively and
effectively respond to challenges that farmers encounter, especially
resource-constrained farmers in the south. Kamayab et al. [52] deeply
explore the inuence of farming, on climate change examining green-
house gas emissions, carbon storage and strategies to mitigate its effects.
They emphasize the signicance of nding solutions. Envision a future
driven by cutting edge technologies and collaboration among industries
to foster sustainability and resilience. This in-depth analysis underscores
the potential of agriculture in curbing emissions while ensuring food
security and biodiversity presenting a vision for the future. The design
and deployment of a weather station on Edamame farm are presented by
Tenzin et al. [53]. The results of a comparison between the meteoro-
logical data of this weather station and the data provided by the Davis
Vantage Pro2 installed within the same eld have shown the efciency
of the deployed weather station in measuring different weather pa-
rameters. Vangala et al. [54] delve into security challenges in modern-
ized farming, proposing a smart farming architecture and reviewing
current security protocols. Additionally, it assesses the latest industry
advancements in IoT-based tools. Cesco et al. [55] offer a framework for
designing farm information systems and apply it to a case study on crop
nitrogen fertilization, emphasizing the importance of understanding soil
and crop variability. The study also discusses challenges, especially for
areas with smaller farms, suggesting that digital twins can optimize
predictive analyses for both farmer benets and sustainable agriculture.
The research studies done by Morchid et al. [56] propose innovative
smart irrigation systems utilizing cloud computing, embedded systems,
and IoT to address agricultural challenges. These systems monitor
crucial environmental factors in real-time, achieving a notable 70 %
reduction in water consumption for soil irrigation. It also enables
farmers to access comprehensive farm data remotely, enhancing crop
production and sustainability, thus advancing food security. In addition,
they examine smart irrigation systems using IoT, Cloud Computing, DL,
and ML-based plant disease detection technologies for sustainable
agriculture. SaberiKamarposhti et al. [57]conduct an examination of the
greenhouse gas emissions in agriculture proposing the integration of AI
for monitoring and capturing carbon emissions. They also recommend
implementing strategies to decrease emissions and promote sustain-
ability. Emphasizing the importance of incentives and governmental
regulations, they present a thought-out strategy for the sector to
contribute to combating climate change. Sadri et al. [58] carefully tackle
obstacles in Cloud computing for IoT like delays by proposing fog
computing as a remedy for handling real time data in settings. Through a
review of literature. They examine studies on fog data management
between 2014 and 2019. They present a taxonomy based on context.
Delve into discoveries, benets, limitations, and upcoming hurdles, in
fog data management. Kamyab et al. [59] discuss the impact of AI and
Big Data Analytics on transforming water resource management in
overcoming issues related to acquiring real time data and making
informed decisions. They examine how AI and Big Data Analytics are
currently being used, including the application of machine learning and
deep learning methods for monitoring water quality, and predicting
water demand.
The review of existing literature identies signicant gaps in SA
solutions. First, the current commercial options heavily rely on devices
and software making them unaffordable, for many small and medium
sized farmers. Second, SA is mostly controlled using software. However,
there is a noticeable lack of open-source software that could promote
wider adoption of such innovative solutions. Third, there is an under-
utilization of weather forecast stations in SA which could signicantly
improve farming decisions with accurate predictions if utilized effec-
tively. Moreover, the incorporation of renewable energy sources like
solar power to feed in water pumps and IoT devices is not widely
implemented. This inclusion has the potential to lower carbon emissions
and reduce energy expenses. Finally, existing SA setups operate inde-
pendently without taking advantage of connecting smart farms within
regional or national networks. Establishing these connections will
generate big data that will be used by decision-makers for strategic
plans, enhance the optimization of resource sharing, and improve
agricultural practices at both regional and national levels.
To address these gaps identied in the study several new contribu-
tions are proposed. First, we opted for open-source software to handle
data collection, control, and actuation. Second, we created a cloud based
IoT platform to oversee data generated by various smart farms in real
time. Third, we used off-the-shelf Arduinos Nanos to construct low-cost
sensors and actuators thereby making SA technologies more accessible
to all agricultural entities including small and medium farmers. Addi-
tionally, to enhance water and energy management and support decision
making processes we have integrated weather predictions into our sys-
tem. In pursuit of sustainability and cost reduction our proposed SA
prototype fully relies on solar panels for energy needs. Moreover, we
suggest a setup where numerous smart farms are linked through a
centralized CompactRIO controller to optimize resource utilization and
elevate efciency. Furthermore, to optimize water and energy within
each smart farm across the region, we developed a smart irrigation
system that signicantly reduces water and energy use compared to
traditional methods. Finally, this study encompasses the implementa-
tion and assessment of a smart farm prototype with an emphasis on
application and data interpretation.
After delving into the frameworks and advancements in smart
farming. We are now moving forward to detail the materials and
Methods used in our study to ll the recognized gaps and add value to
the eld.
3. Materials and methods
In this section we outline the methods used to create our IoT based
irrigation system, which aims to improve farming techniques. We delve
B. Et-taibi et al.