INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 05,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1464
SMART MONITORING SYSTEM FOR DETERMINING THE AMOUNT OF
MACROELEMENTS ENSURING HEALTHY PLANT GROWTH
Kamolakhon Haydarova
Lecturer at Kokand University
Odinakhon Melikozieva
Student at Kokand University
Annotation:
This article provides information about sensors and automated systems based on
artificial intelligence used to detect macroelements in soil in agriculture. In the Republic of
Uzbekistan, the level of automation in the agricultural sector is developing at a moderate pace.
The level of automation in Uzbekistan's agriculture is currently around 10-20%, and these
technologies are mainly widely used in large farms and agrarian enterprises. In small and
medium farms, these processes are still developing, and in the future, additional incentives and
infrastructure development by the state are required to create more opportunities for them.
This article analyzes methods of measuring soil composition using a combination of Arduino
and Soil NPK Sensors and displaying this data on an OLED display or through an Android
application. The principles of operation of the Soil NPK Sensor, its technical specifications, and
its integration with Arduino are thoroughly covered in this article.
Keywords:
Arduino, NPK sensor, nitrogen, phosphorus, potassium, OLED display, RS485
(MAX845) module, Bluetooth
Introduction
Soil fertility is one of the important factors for healthy plant growth and high yield. Out of the
17 essential elements required for plant vital activity, 14 are taken from the soil, while three
elements are absorbed through air and water. Among these elements, nitrogen (N), phosphorus
(P), and potassium (K) are considered the most important and are widely used in commercial
fertilizers. Therefore, accurate measurement and monitoring of soil NPK content is of great
importance in creating optimal conditions for plants.
Development of Soil NPK Sensors:
NPK sensors consist of several types of devices developed to measure the level of nutrients in
the soil. These sensors offer a much more convenient, economical, and efficient alternative
compared to traditional laboratory analyses. The sensors are distinguished by their small size,
affordability, low power consumption, and fast accuracy. The main direction of sensor
development is to make them even more compact, affordable, and efficient.
Internet of Things (IoT) and Machine Learning Technologies:
In recent years, IoT technologies and machine learning (ML) methods have been widely used to
monitor soil and determine its composition. IoT systems help to transmit data collected through
sensors to the network and enable remote monitoring. ML technologies, in turn, make it
possible to make accurate predictions about soil composition based on the data collected by
sensors. With the help of ML, it is possible to accurately predict the levels of nutrients (N, P, K)
in the soil, which helps farmers to allocate their resources efficiently.
Traditional and Modern Methods:
Methods used to study soil are divided into two groups: traditional and modern. Traditional
methods are carried out through laboratory analyses, but they require time and resources.
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 05,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1465
Modern methods, on the other hand, ensure timely and efficient results through sensors, IoT
systems, and ML. At the same time, new technologies help make soil monitoring faster and
more affordable.
Future Prospects:
The development of sensors and IoT systems creates new opportunities for monitoring soil in
the agricultural sector. Among the areas being studied, the development of highly accurate,
widespread, and affordable sensors deserves special attention. Additionally, with ML and IoT
technologies, it becomes possible to analyze soil data in real-time and make effective decisions
based on the results.
Analyzing the work of scientists who have implemented automation in agriculture helps to
better understand innovative approaches and the growing role of technologies in this field. The
introduction of automation technologies into agriculture has created opportunities for farmers to
increase efficiency, save resources, and ensure ecological sustainability. Below is an analysis of
the work carried out by scientists in this field, including their achievements and shortcomings.
Several scientists have conducted research on automating fertilization processes. For example,
in a study conducted by Zhang et al. (2020) [1], a system was developed aimed at optimizing
the fertilization process using NPK sensors and IoT systems. According to the research results,
real-time soil monitoring allowed for accurate determination of fertilization quantities and
enabled effective management of this process. Their work is important from the perspective of
increasing soil fertility and reducing ecological footprint.
Lee et al. (2019) [2]
conducted research related to the automation of irrigation systems and
developed methods to optimize irrigation through the application of IoT and artificial
intelligence. In their work, the efficiency of the irrigation system was improved using soil
moisture measurement sensors and AI algorithms. The system automatically monitors the
amount of water in the soil and performs fertilization and irrigation at the required time. This
method not only saves water but also helps improve crop quality.
Kumar et al. (2021) [3]
considered an approach aimed at developing mobile applications and
remote monitoring systems in their research. Their work confirmed the effectiveness of
remotely monitoring soil conditions, obtaining real-time NPK measurements, and continuously
providing farmers with information. Through mobile applications, the condition of the land on
farms is quickly analyzed, and farmers can make correct decisions about fertilization or
irrigation. This approach is especially useful for small and medium farmers because they can
apply modern technologies at low cost.
In the study conducted by
Santos et al. (2020) [4]
, the use of automated agricultural machinery
(for example, robotics and artificial intelligence in tractors) was analyzed. According to the
results of the study, through the automation of fertilizing the land, preparing the soil, and
harvesting processes, it was possible to achieve a 40% increase in efficiency. The systems they
proposed demonstrated the possibility of saving resources and time, increasing labor
productivity, and reducing ecological footprint.
In the work carried out by
Zhang and Chen (2021) [5]
, automated systems were developed
through the use of artificial intelligence in agriculture. They proposed innovative solutions
using algorithms focused on data analysis, fertilization optimization, and biodiversity
conservation. With the help of AI systems, it is possible to automatically forecast soil
characteristics and take necessary measures. These technologies play an important role not only
in increasing efficiency but also in ensuring ecological sustainability.
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 05,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1466
The application of automation systems in agriculture faces several challenges. The high cost of
comparison and monitoring systems and the different responses of soil under varying conditions
can hinder the effective operation of the system. For small farmers, implementing these
technologies is often financially difficult, as the purchase and installation costs of advanced
technologies are high. Also, the limited availability of technical and scientific knowledge can
sometimes cause problems in effectively operating the systems. This article provides
information about creating one such project and its practical implementation.
Methods
Information about the sensors and actuators used in this project was provided in our previous
articles [6].
The smart monitoring system for plant growth integrates several sensors and actuators on the
Arduino platform. To build this system, the following components are used:
Soil NPK Sensor
(a sensor that measures soil composition)
Arduino Nano
(main control module)
MAX485 RS-485 interface
(for data exchange via the Modbus protocol)
SSD1306 OLED display
(for displaying soil components)
HC-05 or HC-06 Bluetooth module
(for connection with an Android application)
12V power supply
(for the sensor and Arduino)
The Soil NPK sensor operates via the Modbus RTU protocol and connects to the Arduino
through the RS485 interface. The sensor functions at a voltage of 9V–24V and accurately
measures soil composition in mg/kg units.
Figure 1. Connection diagram of the system project for determining soil macroelements.
(
From right to left:
NPK sensor, Max485 module, Bluetooth, Arduino NANO, OLED display)
Device connection scheme: (Table 1)
The interconnection of the Soil NPK Sensor is carried out according to the following scheme:
The
VCC pin
of the sensor is connected to a
12V power source
.
The
GND pin
is connected to the
Arduino GND pin
.
The
A and B pins
are connected to the corresponding pins of the
MAX485 interface
module
.
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 05,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1467
The
RO and DI pins
of the MAX485 interface are connected to
Arduino D2 and D3
pins
.
The
TX and RX pins
of the
HC-05 Bluetooth module
are connected to the
Arduino
RX and TX pins
.
The
OLED display
is connected to
Arduino A4 (SDA)
and
A5 (SCL)
pins.
Table 1. Connection status of project devices:
Device
Pin
Connection Piont
NPK sensor
VCC
12V quvvat manbai
GND
Arduino GND
A
Max485 A
B
Max485 B
MAX485
VCC
Arduino 5V
GND
Arduino GND
RO
Arduino D2
DI
Arduino D3
DE/RE
Arduino D4
A
NPK Sensor A
B
NPK Sensor B
HC-05 Bluetooth
VCC
Arduino 5V
GND
Arduino GND
TX
Arduino D0 (RX)
RX
Arduino D1 (TX)
OLED Displey
VCC
Arduino 5V
GND
Arduino GND
SDA
Arduino A4
SCL
Arduino A5
Software and Modbus Requests:
In the Arduino program, the
SoftwareSerial
and
Modbus
libraries are used. The sensor is
controlled using the following Modbus commands:
To read Nitrogen (N): 0x01, 0x03, 0x00, 0x1E, 0x00, 0x01, 0xE4, 0x0C
To read Phosphorus (P): 0x01, 0x03, 0x00, 0x1F, 0x00, 0x01, 0xB5, 0xCC
To read Potassium (K): 0x01, 0x03, 0x00, 0x20, 0x00, 0x01, 0x85, 0xC0
The program sends these commands sequentially and displays the results on both the
OLED
display
and the
Android application
.
Several libraries are used in writing the code section of the program. Before executing the loop()
and setup() functions, the operational status of the existing devices is declared. Below is a
sample code for the introduction part of the program.
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 05,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1468
Results
The developed program code section is uploaded to the Arduino microcontroller using the
Arduino IDE
software. After running the program, the
NPK sensor
is placed into the soil
where values need to be measured. Under the proper conditions, the values can be observed on
the
OLED display
.
Figure
1.
Display view of
the
measured
values on the
OLED screen
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 05,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1469
Figure 2.
Display view of the
measured values on
an Android phone
The system was tested and the following results were achieved:
1.
The accuracy of the Soil NPK Sensor was up to ±2% F.S., and experimental results gave
satisfactory outcomes when compared to standard laboratory tests.
2.
Real-time data was displayed through the OLED screen, enabling rapid monitoring for
farmers and researchers.
3.
Data was transmitted to an Android application via the HC-05 Bluetooth module,
allowing users to remotely monitor soil composition via the app.
Discussion
The research results showed that the combination of the Soil NPK Sensor and the Arduino
platform can be an effective solution for developing a smart monitoring system in agriculture.
The system has the following advantages:
Portable and user-friendly:
The device is easy to move and can be used to measure
any type of soil.
Affordable and cost-effective:
While NPK measurement in commercial laboratories is
expensive, this system provides accurate results at a low cost.
Remote monitoring capability:
Real-time monitoring is possible via an Android app
through Bluetooth.
However, the system also has certain limitations:
The sensor operates only within a temperature range of
5°C to 45°C
, meaning results
may be inaccurate in very cold or hot conditions.
Measurements are limited to the
0–1999 mg/kg
range; if the nutrient levels in the soil
exceed this range, additional testing is required.
Conclusion
The development and implementation of technologies in the field of soil monitoring provide
farmers with the opportunity to achieve higher yields and use resources efficiently. The
integration of sensors, IoT systems, and machine learning technologies will significantly
optimize the processes of soil management and monitoring in the future.
In this article, a system for monitoring soil fertility was created based on
Arduino
and a
Soil
NPK Sensor
, and it was tested through experiments. The system is accurate, fast, and user-
friendly, and can be widely used in agriculture and scientific research.
This innovative approach to soil monitoring helps farmers optimize the fertilization process,
increase crop productivity, and utilize resources more efficiently.
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 05,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1470
References:
1.
Lou, X., Zhang, L., Zhang, X., Fan, J., & Li, C. (2020, November). Design of intelligent
farmland environment monitoring system based on wireless sensor network. In Journal of
Physics: Conference Series (Vol. 1635, No. 1, p. 012031). IOP Publishing.
2.
Li L. et al. Two-dimensional mosaic bismuth nanosheets for highly selective ambient
electrocatalytic nitrogen reduction //Acs Catalysis. – 2019. – Т. 9. – №. 4. – С. 2902-2908.
3.
Visvesvaran, C., Kamalakannan, S., Kumar, K. N., Sundaram, K. M., Vasan, S. M. S. S., &
Jafrrin, S. (2021, October). Smart greenhouse monitoring system using wireless sensor
networks. In 2021 2nd international conference on smart electronics and communication
(ICOSEC) (pp. 96-101). IEEE.
4.
González-Santos S. P. Creating Life: An Embryo Assembly Line //Beauty and Monstrosity
in Art and Culture. – Routledge. – С. 153-161.
5.
Wang, S., Zhou, C., Zhang, D., Chen, L., & Sun, H. (2021). A deep learning framework
design for automatic blastocyst evaluation with multifocal images. IEEE Access, 9, 18927-
18934.
6.
Haydarova K. ROBOTOTEXNIKADA SENSORLAR VA AKTUATORLAR.
MA’LUMOT CHIQARUVCHI DISPLAY TURLARI //QO ‘QON UNIVERSITETI
XABARNOMASI. – 2024. – Т. 13. – С. 366-371.
7.
Haydarova K. TUPROQ NPK SENSORI VA ARDUINO: O'SIMLIKLARNI SOG ‘LOM
O ‘STIRISH UCHUN AQLLI MONITORING TIZIMI //QO ‘QON UNIVERSITETI
XABARNOMASI. – 2024. – Т. 13. – С. 390-392.
8.
Haydarova K. ROBOTOTEXNIKA: IT SOHASIDAGI AHAMIYATI VA O’RGANILISH
DARAJASI //University Research Base. – 2024. – С. 1004-1006.
9.
Haydarova K. THE ROLE OF WOMEN IN MODERN ARTIFICIAL INTELLIGENCE
AND ROBOTICS //International Journal of Artificial Intelligence. – 2025. – Т. 1. – №. 3.
– С. 716-721.
10.
Kamolaxon H. et al. SUV-HAYOT MANBAI. VATANIMIZNING SUVGA BO ‘LGAN
EHTIYOJI VA QURG ‘OQCHILIKNING OLDINI OLISH YO ‘LLARI //" GLOBAL
MUNOSABATLAR NAZARIYASI: YOSHLARNING TARAQQIYOT GʻOYALARI"
xalqaro ilmiy-amaliy anjumani materiallari. – 2025. – Т. 1. – №. 2. – С. 27-32.
11.
Haydarova K. et al. TABIAT VA BIZ. OROL DENGIZINING MUAMMOLARI //"
GLOBAL MUNOSABATLAR NAZARIYASI: YOSHLARNING TARAQQIYOT
GʻOYALARI" xalqaro ilmiy-amaliy anjumani materiallari. – 2025. – Т. 1. – №. 2. – С. 33-
37.
12. FA, Nuraliev, and Kuziev Sh S. "THE COEFFICIENTS OF AN OPTIMAL
QUADRATURE
FORMULA
IN
THE
SPACE
OF
DIFFERENTIABLE
FUNCTIONS." Uzbek Mathematical Journal 67.2 (2023).
13. Nuraliev F. A., Kuziev S. S., Djuraeva K. A. Approximate Solution Fredholm Integral
Equation of the Second Kind by the Optimal Quadrature Method //Проблемы
вычислительной и прикладной математики. – 2024. – №. 4/2 (60). – С. 66-73.
14. Nuraliev F. A., Kuziev S. S. Optimal Quadrature Formulas with Derivative in the Space:
Optimal Quadrature Formulas with Derivative in the Space //MODERN PROBLEMS
AND PROSPECTS OF APPLIED MATHEMATICS. – 2024. – Т. 1. – №. 01.
15. Qo’Ziyev S. S., Tillaboyev B. S. O. TALABALARDA IJODKORLIKNI
RIVOJLANTIRISHDA AXBOROT KOMMUNIKATSION TEXNOLOGIYALARNING
INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE
ISSN: 2692-5206, Impact Factor: 12,23
American Academic publishers, volume 05, issue 05,2025
Journal:
https://www.academicpublishers.org/journals/index.php/ijai
page 1471
O ‘RNI //Oriental renaissance: Innovative, educational, natural and social sciences. – 2021.
– Т. 1. – №. 10. – С. 344-352.
16. Shadimetov K., Nuraliev F., Kuziev S. Coefficients and errors of the optimal quadrature
formula of the Hermite type //AIP Conference Proceedings. – AIP Publishing, 2024. – Т.
3147. – №. 1.
17. Shadimetov K., Nuraliev F., Kuziev S. Optimal Quadrature Formula of Hermite Type in
the Space of Differentiable Functions //International Journal of Analysis and Applications.
– 2024. – Т. 22. – С. 25-25.
