Smart Agricultural Device for Soil Fertility Assessment and Tomato Crop Growth Prediction

This study developed a Smart Agricultural Device for Soil Fertility Assessment and Tomato Crop Growth Prediction using Internet of Things (IoT) technology and rule-based analysis techniques to support soil monitoring and improve agricultural decision-making for tomato cultivation. Soil fertility plays an important role in determining tomato crop productivity, as factors such as soil moisture, pH level, and nutrient availability significantly influence plant growth and yield. However, traditional soil assessment methods often require laboratory testing, which may be costly, time-consuming, and inaccessible to many small-scale farmers. In response to these challenges, the study proposed an IoT-enabled monitoring system capable of collecting, processing, and presenting soil-related information in a more accessible and timely manner.
The developed system integrates several hardware components, including a soil moisture sensor, soil pH sensor, and NPK sensor, which are connected to an ESP32 microcontroller to collect essential soil parameters necessary for tomato crop development. The NPK sensor communicates through an RS485 communication module and utilizes a switching power supply to ensure stable nutrient monitoring and system performance. The ESP32 microcontroller serves as the main processing unit responsible for gathering sensor readings and transmitting collected soil information through Wi-Fi connectivity to a MySQL database managed using XAMPP for storage and monitoring purposes. The system also incorporates an LCD display and a web-based dashboard to present soil readings, fertility classifications, crop growth assessment, and recommendation outputs in an understandable and accessible format.
The study employed a developmental research design guided by the Agile Software Development Life Cycle (SDLC) to support continuous system development, testing, and refinement. The Agile methodology enabled iterative improvements throughout the planning, designing, development, and testing stages to ensure system functionality and reliability. The developed system applied a rule-based soil fertility assessment and crop growth estimation approach using predefined threshold values obtained from documented agricultural references and publicly available datasets related to tomato cultivation. Collected soil parameter values, including soil moisture, pH level, and nutrient content, were compared with standard soil requirements suitable for tomato growth to classify soil fertility conditions and estimate possible crop growth outcomes.
Results of the study showed that the developed system successfully performed soil monitoring, data processing, Wi-Fi transmission, database storage, dashboard visualization, and recommendation generation during system testing. The developed device was able to gather soil-related information and display soil fertility status through both the LCD interface and web-based dashboard. Sample soil parameter classifications generated by the system indicated varying fertility conditions, including poor and moderate soil quality, based on moisture level, pH balance, and nutrient availability. The system also generated corresponding recommendations regarding irrigation scheduling and fertilizer application to support improved soil management and crop productivity.
Although the study was limited to system development and functionality testing, findings demonstrated the feasibility and potential of integrating IoT-based monitoring and predictive soil assessment in smart agriculture applications. The developed system provides an alternative approach for monitoring soil conditions while assisting users in making more informed agricultural decisions related to tomato crop cultivation. Furthermore, the study highlights the importance of technology-driven agricultural solutions in promoting efficient resource management, soil monitoring, and sustainable farming practices. Future studies may focus on wider field implementation, laboratory validation of sensor readings, and the incorporation of more advanced predictive techniques to further improve system performance and accuracy.

Internet of Things (IoT), Soil Fertility Monitoring, Tomato Crop Growth Prediction, ESP32 Microcontroller, Smart Agriculture, Soil Monitoring System

1. Ampo, M. V., Castro J. A. D., Ramoso, J. P., Ilang-Ilang, M., Rodulfo, V. A., Del Rosario, A., Reyes, D. D., and De Guzman, J. J. (2024). Design and development of a sensor and actuator network for smart irrigation and fertilization in tomato production. University of the Philippines Los Baños Journal Articles. Retrieved from https://www.ukdr.uplb.edu.ph/cgi/viewcontent.cgi?article=7073&context=journal-articles [Google Scholar] [Crossref]

2. Dela Cruz, B., Ramos, R., Carambas, G. M., Peronce, I. P., and Perreras, J. (2025). Digging deeper: Soil quality monitoring system for Alaminos City farmers. Retrieved from https://doi.org/10.47772/IJRISS.2025.9020126 [Google Scholar] [Crossref]

3. Fajir, Y., Qayoom, A., Erasmus, E., Schutte-Smith, M., and Visser, H. (2024). A review on the application of advanced soil and plant sensors in the agriculture sector. Computers and Electronics in Agriculture, 226, 109395. https://www.sciencedirect.com/science/article/pii/S0168169924007762 [Google Scholar] [Crossref]

4. Kumar, S. N., Suriyan, K., Jacob, A. T., Varghese, A., and Francis, Emma. (2025). Smart farming for a sustainable future: Implementing IoT-based systems in precision agriculture. Bulletin of the National Research Centre, 49, Article 66. https://bnrc.springeropen.com/articles/10.1186/s42269-025-01366-8 [Google Scholar] [Crossref]

5. Lionel, B. M., Musabe, R., Gatera, O., and Twizere, C., (2025). A comparative study of machine learning models in predicting crop yield. Discover Agriculture, 3, Article 35. https://link.springer.com/article/10.1007/s44279-025-00335-z [Google Scholar] [Crossref]

6. Martinez, C. G., Aringo, M. Q., Ella, V., and Martinez O. G. (2022). Development of low-cost soil moisture monitoring system for efficient irrigation water management of upland crops. International Journal of Scientific and Research Publications, 12(6), 530–536. Retrieved from https://www.researchgate.net/publication/361458669_Development_of_Low-cost_Soil_Moisture_Monitoring_System_for_Efficient_Irrigation_Water_Management_of_Upland_Crops [Google Scholar] [Crossref]

7. Montañez, J. J., and Sarmiento, J. (2024). Machine learning for the detection of soil pH, macronutrients, and micronutrients with crop and fertilizer recommendations. International Journal of Artificial Intelligence, 14(1), 439–446. https://doi.org/10.11591/ijai.v14.i1.pp439-446 [Google Scholar] [Crossref]

8. Mukherjee, S., Dash, P. K., Das D., and Das, S. (2023). Growth, yield and water productivity of tomato as influenced by deficit irrigation water management. Irrigation Science, 41, 645–659. https://pmc.ncbi.nlm.nih.gov/articles/PMC10384587/ [Google Scholar] [Crossref]

9. Ramzan, S., Ali, B., Raza, A., Hussain I., Fitriyani, N. L., Gu, Y., and Syafrudin M. (2024). An innovative artificial neural network model for smart crop prediction using sensory network-based soil data. Scientific Reports, 14, Article 28658. https://pmc.ncbi.nlm.nih.gov/articles/PMC11623066/ [Google Scholar] [Crossref]

10. Sobhy, D. M., and Anandhi, A. (2025). Soil nutrient monitoring technologies for sustainable agriculture: A systematic review. Sustainability, 17(18), 8477. https://www.mdpi.com/2071-1050/17/18/8477 [Google Scholar] [Crossref]

11. Sujatha, M., and Jaidhar, C. D. (2024). Machine learning-based approaches to enhance soil fertility—A review. Expert Systems with Applications, 237, 121565. https://www.sciencedirect.com/science/article/abs/pii/S0957417423030592 [Google Scholar] [Crossref]

12. Chaudhary A., Singh P. D., Verma R., and Sharma, M. (2025). Monitoring soil health using machine learning techniques for improved crop yield prediction. Cureus, 16(4), e4577. Retrieved from https://www.cureusjournals.com/articles/4577-monitoring-soil-health-using-machine-learning-techniques-for-improved-crop-yield-prediction [Google Scholar] [Crossref]

13. Fauziah, N. O., Fitriatin, B. N., Fakhrurroja, H., and Simarmata, T. (2024). Enhancing Soil Nutritional Status in Smart Farming: The Role of IoT-Based Management for Meeting Plant Requirements. Retrieved from https://onlinelibrary.wiley.com/doi/10.1155/2024/8874325 [Google Scholar] [Crossref]

• Breeding for a Greener Future: Selective Breeding and Crossbreeding Approaches to Minimize Methane Emissions in Ruminant Livestock
• Determinants of Adoption of Post-Harvest Losses Prevention Techniques among Banana/Plantain Marketers in Lagos State, Nigeria
• Enhancing Rice Yield Prediction Using UAV-Based Multispectral Imaging and Machine Learning Algorithms
• Seed-Borne Fungi of Groundnuts (Arachis Hypogaea) and Their Management with Ginger (Zingiber Officinale) Extract In Makurdi, Nigeria
• The Influence of Landforms and Slope on Agricultural Cropping Patterns in Chhatrapati Sambhajinagar District