INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2453 www.rsisinternational.org
FloraHub: An IoT-Based Smart Plant Hydration System with
Real-Time Monitoring and Cost Analytics
Shaufy Yana Mohd Ezani1, Kurk Wei Yi 2, Intan Ermahani A.Jalil3*, Sabrina Ahmad4, Mohd Sanusi
Azmi5
1Allgo Technologies Sdn. Bhd. Kuala Lumpur, 58200, Malaysia
2,3,4,5Fakulti Teknologi Maklumat dan Komunikasi Universiti Teknikal Malaysia Melaka (UTeM),
Durian Tunggal, Melaka, 76100, Malaysia
DOI: https://dx.doi.org/10.47772/IJRISS.2025.910000205
Received: 07 October 2025; Accepted: 14 October 2025; Published: 07 November 2025
ABSTRACT
The "FloraHub: Smart Plant Hydration System" project tackles the shortcomings of traditional plant watering
methods by proposing an innovative IoT-based solution. Conventional timed watering systems often result in
water wastage and inadequate hydration, adversely affecting plant health and increasing expenses. To address
these challenges, the project introduces an automated watering system integrated with soil moisture sensors and
water flow sensors. These sensors continuously monitor soil moisture levels in real-time, triggering watering
only when necessary, while also providing users the option to utilize a timer or tap a button on the mobile app for
manual watering. Additionally, the incorporation of Grafana analytics enables comprehensive data analysis,
offering insights into soil moisture trends, watering patterns, and water usage. By leveraging technology and
data-driven solutions, the project aims to enhance operational efficiency, minimize water consumption, and
promote environmentally responsible practices in plant care. The FloraHub system represents a significant
advancement in plant management, providing users with a user-friendly and sustainable approach to ensure
optimal plant growth and health.
Keywords- IoT, Smart Irrigation, Sustainable Plant Care, Water Flow Sensor, Automated Watering System
INTRODUCTION
Efficient water management in plant care and agriculture has become increasingly critical due to water scarcity,
rising costs, and environmental concerns. Traditional watering methods such as fixed timers or manual watering
often led to either overwatering or underwatering, both of which negatively impact plant health and resource
efficiency. In particular, auto drip and timer-based systems fail to account for actual soil moisture or
environmental changes, resulting in wasted water and suboptimal plant growth.
Recent developments in Internet of Things (IoT), sensor technology, and artificial intelligence (AI) have opened
up new opportunities for precision irrigation. Smart irrigation systems that monitor soil moisture, humidity,
temperature, and weather forecasts can trigger watering only when needed, thereby improving water use
efficiency and reducing labour requirements [1][2]. For instance, IoT-based systems integrating real-time soil
moisture sensing with cloud platforms have shown improvements in water conservation and healthy plant
growth compared to conventional watering practices [3][4].
There is also growing interest in combining automated irrigation with decision-making algorithms (such as
fuzzy logic, PID controllers, or AI prediction models) to further enhance responsiveness and adaptivity of the
systems [5]. Moreover, integrating additional data sources such as weather forecasts allows the system to avoid
watering when rainfall is imminent, thereby conserving water further [6].
The FloraHub: Smart Plant Hydration System is proposed to address these issues by combining soil moisture
sensors, water flow measurement, IoT connectivity, and analytic dashboards to deliver plant watering that is both
precise and responsive. The system aims to reduce water wastage, maintain optimum soil moisture, improve
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2454 www.rsisinternational.org
plant health, and provide the user with control and insights.
BACKGROUND
The growing importance of sustainable agriculture and water conservation has driven the adoption of automated
irrigation solutions. Traditional irrigation techniques, while simple, often lead to inefficiencies such as
overwatering, underwatering, and inconsistent soil moisture levels. These issues highlight the need for smarter
systems that respond dynamically to environmental conditions rather than relying solely on fixed schedules.
Recent research emphasizes that IoT-enabled irrigation systems provide significant improvements in precision
and sustainability by leveraging real-time data from soil moisture sensors and weather conditions [7]. Such
systems enable better decision-making, reduce human intervention, and allow scalability from small gardens to
commercial farms. Studies also show that integrating smart control with predictive algorithms can improve plant
growth outcomes and resource efficiency [8].
Beyond soil sensing, advancements in wireless communication and cloud connectivity have enhanced the
reliability and accessibility of smart irrigation. Cloud-linked systems allow users to monitor soil moisture, water
usage, and system performance from mobile or web applications, thereby increasing transparency and user
control [9]. Furthermore, hybrid systems that integrate automated watering with user-defined schedules provide
flexibility for diverse agricultural contexts, balancing autonomy with customization [10].
Energy efficiency has also become a focal point in smart irrigation research. Systems powered by renewable
sources such as solar panels demonstrate sustainability and cost savings, making them attractive for rural
communities and regions where grid electricity is limited [11]. Meanwhile, combining wireless sensor networks
with IoT platforms supports large-scale deployment, enabling distributed monitoring and coordinated irrigation
across multiple zones [12].
Despite these advancements, challenges remain in delivering systems that are both cost-effective and
user-friendly, particularly for smallholder farmers and home users. Many prototypes lack advanced features such
as water flow monitoring, usage analytics, and integration with decision-support dashboards. The FloraHub:
Smart Plant Hydration System is designed to address these gaps by combining soil moisture sensing, water flow
analysis, IoT automation, and mobile app integration into a single solution. This approach ensures that plants
receive adequate hydration while enabling users to track water consumption, optimize costs, and promote
sustainable practices.
RELATED WORK
Recent research in smart irrigation has advanced from simple moisture-based systems to more integrated IoT and
AI-enabled solutions. Abdelmoneim et al. [13] compared two approaches for precision irrigation, weather-based
scheduling using evapotranspiration estimates and soil water potential monitoring with low-cost IoT
tensiometers. Their results demonstrated that both methods achieved comparable water productivity, but the
sensor-based approach provided more responsive and adaptable irrigation control.
Similarly, Soussi et al. [14] reviewed recent developments in precision agriculture sensors and highlighted the
importance of smart data processing for effective irrigation. They emphasized that sensor accuracy, integration
with IoT platforms, and real-time analytics are crucial for reliable system performance.
A different perspective was offered by the study on low-power IoT electronics in irrigation [15], which proposed
a prototype that combined soil and climate sensors with energy-efficient microcontrollers. This design focused
on minimizing energy consumption while maintaining effective irrigation scheduling, making it suitable for
long-term deployment in resource-constrained environments.
Dong et al. [16] presented a fully deployed in-field IoT irrigation management system that integrated soil and
environmental monitoring with real-time actuation. Their results showed improved efficiency in water
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2455 www.rsisinternational.org
distribution and highlighted the practical challenges of large-scale deployment, such as sensor calibration and
data handling.
From a socio-technical perspective, Jabbari et al. [17] investigated adoption factors of IoT irrigation in Saudi
Arabia using a GRA/AHP decision analysis framework. They found that cost, ease of use, and reliability were
the most influential factors for farmer adoption, stressing the importance of usability in system design.
Finally, Kaur et al. [18] developed a hybrid IoT and machine learning irrigation system in Rajasthan, India. By
combining multiple sensor inputs with predictive algorithms, the system provided more accurate irrigation
scheduling and demonstrated improvements in water savings and crop performance compared to conventional
methods.
Despite these advances, many systems either focus on automation without comprehensive user interfaces or
prioritize technical efficiency without addressing end-user decision support. In contrast, FloraHub integrates soil
moisture and water flow monitoring with IoT automation, mobile app control, and Grafana dashboards to
provide not only irrigation efficiency but also cost tracking and actionable insights for users.
TABLE I. Comparison Between Existed and Florahub
Ref Method / Tools Key Findings Identified Gaps
[13] IoT tensiometers vs.
weather-based ET
irrigation
Achieved similar water
productivity with flexible
control using low-cost sensors
Limited to lettuce trials;
no analytics or cost
tracking
[14] Review of precision
agriculture sensors and
smart data
Emphasized importance of
sensor accuracy and real-time
data processing
Lacked implementation;
no end-user application
[15] Energy-efficient
microcontrollers with soil
and climate sensors
Reduced power
consumption while
maintaining irrigation
effectiveness
Prototype-level; no
dashboard or water usage
reporting
[16] In-field IoT irrigation
management with
soil/environment sensors
and actuation
Improved field water
distribution efficiency
Faced sensor calibration
issues; lacked cost and
usage analysis
[17] GRA/AHP analysis of
IoT adoption factors
Identified cost, reliability,
and ease of use as critical for
adoption
Focused on adoption; no
technical system design
provided
[18] IoT sensors integrated
with machine learning for
irrigation scheduling
Improved predictive
scheduling, water savings, and
crop yield
Region-specific trial; no
comprehensive reporting
tools
FloraHub
Soil moisture + water
flow sensors, IoT
automation, Flutter
mobile app, Grafana
dashboards
Provides automation,
scheduling, real-time usage
tracking, and cost analysis
Bridges gaps by
combining technical
efficiency with usability
and decision-support
features
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2456 www.rsisinternational.org
METHODOLOGY
The project followed an Agile methodology with the Scrum framework, ensuring iterative development and
continuous refinement. The workflow included:
Planning
The planning phase served as the foundation for developing the smart irrigation system. At this stage, the problem
statement was refined, emphasizing the need to reduce manual watering tasks while ensuring efficient water use
for plant growth. The objectives established were: (i) to automate irrigation based on soil moisture levels, (ii) to
monitor and record water consumption for cost tracking, and (iii) to provide users with remote control and
scheduling features through a mobile application.
To achieve these objectives, a review of existing smart irrigation solutions was conducted to identify common
limitations such as lack of cost monitoring, limited scalability, and absence of comprehensive analytics.
Hardware and software requirements were then outlined, including the selection of soil moisture and water flow
sensors, a Raspberry Pi Pico W as the microcontroller, and a servo motor-controlled valve. On the software side,
Flutter was chosen for mobile app development due to its cross-platform capability, while Grafana was selected
for data visualization and analysis. This structured planning ensured that resources, scope, and deliverables were
aligned with the research objectives.
System Design
At the sensing layer, Figure 1 shows that two main sensors were employed: a soil moisture sensor to detect the
hydration level of the soil and a water flow sensor to monitor the volume of water consumed. These sensors
provided real-time input data essential for determining whether irrigation should be initiated and for tracking
resource usage.
The processing and control layer was implemented using a Raspberry Pi Pico W microcontroller, which served as
the central unit for data acquisition and decision-making. The microcontroller was programmed in MicroPython
to continuously collect sensor data, process it according to predefined thresholds, and activate or deactivate a
servo motor that controlled a 3D-printed water valve. This ensured that water was delivered only when required,
minimizing wastage and maintaining plant health.
Fig. 1. System Architecture of FloraHub
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2457 www.rsisinternational.org
At the application layer, user interaction and data visualization were facilitated. A mobile application, developed
using Flutter, enabled users to select between automatic, manual, and scheduled irrigation modes. The
application also displayed real-time soil moisture and water flow readings retrieved from the microcontroller. To
enhance decision support, Grafana dashboards were integrated into the system, providing analytical insights into
water usage trends and cost over time.
Together, these components formed a modular and scalable architecture capable of supporting both domestic
gardening and small-scale agricultural contexts. The design not only automated irrigation but also empowered
users with actionable data, bridging the gap between efficiency, monitoring, and usability.
Development
The development stage of FloraHub involved the integration of hardware and software components into a
functional prototype. The process began with hardware assembly, where the soil moisture sensor and water flow
sensor were configured and calibrated. The soil moisture sensor was adjusted to detect varying hydration levels,
enabling accurate identification of dry, moist, and wet conditions. At the same time, the water flow sensor was
tested to ensure precision in measuring water volume over time, forming the basis for calculating overall
consumption and cost tracking. The Raspberry Pi Pico W microcontroller was selected as the central processing
unit due to its wireless connectivity and support for MicroPython programming. It was responsible for acquiring
sensor data, executing decision-making rules, and controlling the servo motor attached to a 3D-printed valve that
regulated water distribution.
The software development complemented the hardware configuration. The firmware written in MicroPython
enabled the microcontroller to read sensor values continuously, process them against predefined thresholds, and
actuate the valve accordingly. Data captured from the sensors was then transmitted over Wi-Fi to both the mobile
application and Grafana dashboards for real-time monitoring and visualization. The mobile application,
developed using Flutter, served as the primary user interface. It provided three distinct irrigation modes:
automatic, which activated watering when soil moisture dropped below the threshold; manual, which allowed
users to directly open or close the valve; and scheduled, which enabled users to set irrigation routines according
to preferred times.
In parallel, Grafana was deployed as the analytics platform to visualize water flow data and generate meaningful
insights. The dashboards presented users with clear metrics such as total water usage, frequency of irrigation,
and estimated costs, thereby transforming raw sensor readings into actionable information. The development
phase, therefore, successfully combined hardware functionality, wireless communication, and user-friendly
software into a unified system. This integration ensured that FloraHub was not only capable of automating
irrigation but also of supporting informed decision-making through data-driven insights.
Evaluation
The evaluation of FloraHub was conducted using black-box testing, where the system was examined based on its
inputs and outputs without considering the internal program logic. This approach was chosen to validate whether
the system met its functional requirements from the end-user perspective. The testing process involved
simulating different soil conditions, water flow rates, and user interactions with the mobile application to assess
the correctness of system responses.
For the soil moisture sensor, dry, moist, and wet soil samples were tested as inputs. The expected outputs were
corresponding changes in the application display and appropriate irrigation responses in automatic mode. The
results showed that when the soil reached a dry threshold, the system correctly activated the valve, while for
moist or wet conditions, irrigation was not triggered.
The water flow sensor was evaluated by allowing measured volumes of water to pass through. The expected
output was accurate reporting of water usage within the application and Grafana dashboard. Testing confirmed
that the sensor readings were consistent with the actual water volume, enabling reliable tracking of both
consumption and cost.
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2458 www.rsisinternational.org
For the mobile application, black-box testing validated the three irrigation modes. In automatic mode, the
system-initiated watering when the soil was dry and stopped when the threshold was met. In manual mode, user
input directly controlled the valve, while in scheduled mode, the system activated irrigation at predefined times.
In each case, the observed behaviour matched the expected outcomes, demonstrating that the control logic was
correctly implemented.
Finally, usability aspects were tested by interacting with the system as a typical user would, verifying that the
dashboards displayed real-time data clearly and that system feedback was prompt. Overall, the black-box testing
confirmed that FloraHub met its functional requirements effectively, though it also highlighted potential areas
for improvement, such as extending wireless connectivity and refining sensor calibration for broader soil types.
TABLE II. BLACK-BOX TESTING RESULTS FOR FLORAHUB
Test Case Input Condition Expected Output Actual Output Result
TC-01 Soil is dry (<
threshold)
Valve opens
automatically; irrigation
starts; app shows
“watering”
Valve opened,
irrigation started;
app updated
correctly
Pass
TC-02 Soil is moist (within
threshold)
Valve remains closed;
app shows “no watering”
Valve stayed
closed; app
updated correctly
Pass
TC-03 Soil is wet (>
threshold)
Valve remains closed;
app shows “no watering”
Valve stayed
closed; app
updated correctly
Pass
TC-04 500 ml water passed
through flow sensor
App and Grafana
dashboard show ~500 ml
usage, cost updated
Readings
showed ~500 ml
usage with correct
cost
Pass
TC-05 Manual mode: User
taps “Start”
Valve opens, water
flows, app shows
“watering”
Valve opened,
water flowed, app
updated correctly
Pass
TC-06 Manual mode: User
taps “Stop”
Valve closes, water
stops, app shows
“stopped”
Valve closed,
water stopped,
app updated
correctly
Pass
TC-07 Scheduled mode: Set
irrigation at 10:00 AM
Irrigation starts at 10:00
AM automatically
Irrigation
started on
schedule
Pass
TC-08 Wi-Fi disconnected App fails to update
real-time data; Grafana
does not refresh
App showed
error; Grafana
stopped updating
Pass (error
handling
verified)
RESULT
The results of the FloraHub development are demonstrated through functional outputs, system responses, and
user interactions, as shown in figures below. These figures validate the functionality of the mobile application,
automated irrigation system, and monitoring dashboards.
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2459 www.rsisinternational.org
User Authentication and Profile Management
Figures below displays the results of user account management testing. Password validation and login processes
showed appropriate success and error messages. Additional features such as password recovery and registration
success were verified, ensuring users could securely access the system (Figure 2). Profile management functions
allowed users to update their details, with confirmation messages generated after changes, confirming that
account-related modules operated correctly (Figure 3).
Fig. 2. Login and password verification
Fig3. Profile management and home page
Soil Moisture Alerts and Manual Watering
Figures 4 illustrate system responses to soil conditions and manual irrigation control. When dry soil was
detected, the system alerted users through the application. Manual watering tests confirmed correct execution,
with success messages displayed upon activation and deactivation. This demonstrates the reliability of both
sensor feedback and user-triggered irrigation.
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2460 www.rsisinternational.org
Fig. 3. Alert and manual watering
Scheduled Irrigation
Figures below show the scheduled irrigation functionality. Users were able to add new watering schedules
through the scheduling page, with confirmation messages upon successful entry (Figure 5). The system executed
watering tasks as planned, as illustrated in Figure 6, proving that automation responded accurately to predefined
inputs.
Fig. 4. Schedule of plant watering
Fig. 5. Execution of scheduled task
Analytics and Monitoring via Grafana Dashboard
Figures below display the Grafana dashboards that provide real-time and historical analysis. Soil moisture trends
(Figure 7) and water pattern monitoring (Figure 8) were clearly visualized, supporting informed
decision-making.
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2461 www.rsisinternational.org
Fig. 6. Soil moisture trends dashboard
Fig. 7. Water pattern trends dashboard
Water Cost and Usage Reports
Figures below present the reporting functions of the system. Figure 9 shows the water cost report page, where
consumption is translated into monetary value, allowing users to assess irrigation expenses. Figure 10 extends
this functionality by offering water usage reports on a daily, monthly, and yearly basis, giving users the ability to
monitor long-term patterns. Together, these two reporting features provide comprehensive insights into both cost
efficiency and resource utilization, complementing the system’s automation capabilities.
Fig. 8. Water volume and cost reports
CONCLUSION
This study developed and evaluated FloraHub: A Smart Plant Hydration System, which integrates IoT sensors,
automated control, and data analytics to optimize irrigation practices. The system combined soil moisture and
water flow sensors with a Raspberry Pi Pico W microcontroller and a servo-controlled valve to regulate water
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2462 www.rsisinternational.org
delivery. A Flutter-based mobile application provided three irrigation modes: automatic, manual, and scheduled.
While Grafana dashboards offered real-time reporting of water usage and cost. The prototype demonstrated that
automation and analytics can be effectively combined to reduce manual intervention and enhance
decision-making in plant care.
The results confirmed that FloraHub successfully achieved its objectives. Black-box testing validated the
reliability of the system across different soil conditions, while functional tests showed accurate monitoring of
water flow and consumption. The mobile application proved user-friendly and responsive, and the Grafana
dashboards presented data in a clear and actionable format. Compared with existing smart irrigation systems,
FloraHub provides a more holistic solution by integrating automation, monitoring, and cost analysis into a single
platform, thereby addressing both technical efficiency and user usability.
While the system performed effectively, there remain opportunities for improvement in future work. Extending
the Wi-Fi connectivity range would enhance deployment in larger-scale agricultural settings. Integrating
predictive algorithms or machine learning could allow the system to anticipate irrigation needs based on weather
and soil patterns, thereby improving water efficiency. Additionally, cloud integration could enable remote
monitoring and long-term data storage, while renewable energy options such as solar panels could increase
sustainability. These enhancements would make FloraHub not only suitable for domestic and small-scale
applications but also adaptable to commercial agriculture, contributing further to sustainable resource
management.
ACKNOWLEDGEMENT
The authors would like to express gratitude to Fakulti Teknologi Maklumat dan Komunikasi (FTMK) and
Universiti Teknikal Malaysia Melaka (UTeM) for their invaluable support and resources provided throughout
this research.
REFERENCES
1. Ramesh, S., Karmukilan, N., Lavanya, R., Muvinkumar, M., & Samuthra, P. (2025). IoT Based Smart
AI Plant Irrigation System. International Journal of Engineering Research & Technology, 13(5).
https://doi.org/10.17577/IJERTCONV13IS05025
2. Yap, Z. Y., & Abd Rahman, R. (2024). Development of Smart Fertigation System for Chili Plantation
in Greenhouse Environment. Research Progress in Mechanical and Manufacturing Engineering, 5(2),
227-237. https://publisher.uthm.edu.my/periodicals/index.php/rpmme/article/view/17561
3. Mohd Najid @ Zakaria, N. I., & Rosli Omar. (2024). IoT-based Plant Watering System. Evolution in
Electrical and Electronic Engineering, 5(1), 397-402.
4. Zi, O. Y., & Abd Rahman, R. (2024). Study on Effectiveness of IoT-based Automatic Plant Watering
System on Plant Grow. Journal of Design for Sustainable and Environment, 6(1), 34-39.
5. Sidik, A. R., Tawakal, A., Sumirat, G. S., & Narputro, P. (2025). Smart Irrigation Based on Soil
Moisture Sensors with Photovoltaic Energy for Efficient Agricultural Water Management: A
Systematic Literature Review. Engineering Proceedings, 107(1), Article 17.
https://doi.org/10.3390/engproc2025107017
6. Kushwaha et al. (2024). Developing a smart irrigation monitoring system employing the wireless
sensor network for agricultural water management. Journal of Hydroinformatics.
7. Musa, P., & Basir, M. (2023). Wireless Sensor Networks for Precision Agriculture: A Review. PMC.
Retrieved from https://pmc.ncbi.nlm.nih.gov/articles/PMC10780601/
8. Ali, A., Hussain, T., & Zahid, A. (2025). Smart Irrigation Technologies and Prospects for Enhancing
Water Use Efficiency for Sustainable Agriculture. AgriEngineering, 7(4), 106.
https://doi.org/10.3390/agriengineering7040106
9. Prodanović, R., Rančić, D., Vulić, I., Zorić, N., Bogićević, D., Ostojić, G., Sarang, S., & Stankovski, S.
(2020). Wireless Sensor Network in Agriculture: Model of Cyber Security. Sensors, 20(23), 6747.
https://doi.org/10.3390/s20236747
10. Ahmadi Pargo, T., Akbarpour Shirazi, M., & Fadai, D. (2025). Smart and Efficient IoT-Based Irrigation
System Design: Utilizing a Hybrid Agent-Based and System Dynamics Approach. arXiv.
INTERNATIONAL JOURNAL OF RESEARCH AND INNOVATION IN SOCIAL SCIENCE (IJRISS)
ISSN No. 2454-6186 | DOI: 10.47772/IJRISS | Volume IX Issue X October 2025
Page 2463 www.rsisinternational.org
https://arxiv.org/abs/2502.18298
11. Kunt, Y. E. (2025). Development of a Smart Autonomous Irrigation System Using IoT and AI. arXiv.
https://arxiv.org/abs/2506.11835
12. Wei, X., et al. (2025). Intelligent and automatic irrigation system based on internet of things. Scientific
Reports. https://doi.org/10.1038/s41598-025-98137-2
13. Abdelmoneim, A. A., Khadra, R., Elkamouh, A., Derardja, B., & Dragonetti, G. (2024). Towards
affordable precision irrigation: An experimental comparison of weather-based and soil water
potential-based irrigation using low-cost IoT-tensiometers on drip irrigated lettuce. Sustainability,
16(1), 306. https://doi.org/10.3390/su16010306
14. Soussi, A., Zero, E., Sacile, R., Trinchero, D., & Fossa, M. (2024). Smart sensors and smart data for
precision agriculture: A review. Sensors, 24(8), 2647. https://doi.org/10.3390/s24082647
15. Low Power IoT Electronics in Precision Irrigation. (2023). Smart Agricultural Technology, 5. Elsevier.
https://doi.org/10.1016/j.atech.2023.100310
16. Dong, Y., Werling, B., Cao, Z., Li, G., et al. (2024). Implementation of an in-field IoT system for
precision irrigation management. Frontiers in Water, 15 February 2024.
https://doi.org/10.3389/frwa.2024.1353597
17. Jabbari, A., Teli, T. A., Masoodi, F., Reegu, F. A., Uddin, M., & Albakri, A. (2024). Prioritizing factors
for the adoption of IoT-based smart irrigation in Saudi Arabia: A GRA/AHP approach. Frontiers in
Agronomy, 6, 1335443. https://doi.org/10.3389/fagro.2024.1335443
18. Kaur, V., Sharma, M., & Gupta, N. (2024). Developing a hybrid irrigation system for smart agriculture
using IoT sensors and machine learning in Sri Ganganagar, Rajasthan. Sensors, Article ID 6676907.
https://doi.org/10.1155/2024/6676907