Automated Rose Farming with IoT and Machine Learning: A Real-Time Predictive Irrigation System

Nur Zatil 'Ismah Hashim; Noramalina Abdullah; Intan Sorfina Zainal Abidin

doi:10.58915/aset.v4i2.2707

Authors

Nur Zatil 'Ismah Hashim Universiti Sains Malaysia
Noramalina Abdullah Universiti Sains Malaysia
Intan Sorfina Zainal Abidin Universiti Sains Malaysia

DOI:

https://doi.org/10.58915/aset.v4i2.2707

Keywords:

IoT platform, Machine learning, Rose cultivation, Soil moisture, Sustainable agriculture

Abstract

Precision agriculture offers a practical solution to the limitations of traditional farming, particularly for delicate crops like roses. Manual irrigation methods often lead to inconsistent watering, resource wastage, and reduced crop health. This project introduces an IoT-based automated rose farming system enhanced with machine learning to enable real-time environmental monitoring and intelligent irrigation control. The system is built on the VisionFive2 RISC-V board and integrates SHT3x temperature-humidity and soil moisture sensors to capture real-time data. These inputs are transmitted via the MQTT protocol for live monitoring and processed using a Random Forest Regression model to predict optimal irrigation durations. The irrigation is automated through a DC water pump activated via a relay, with safeguards in place to avoid unnecessary cycles for predictions below one second. An alert feature also notifies users when soil moisture drops below critical thresholds. The model achieved 100% classification accuracy, with precision, recall, and F1-scores of 1.00, confirming high reliability in differentiating between above- and below-median irrigation needs. System testing validated accurate data acquisition, real-time dashboard integration, and responsive irrigation control. This work demonstrates a cost-effective, scalable solution for smart floriculture. Future improvements may include weather forecasting integration, adaptive learning for evolving plant needs, and automated fertigation to further optimize sustainability and yield.

References

[1] De Carvalho, P. R., Naoum-Sawaya, J., & Elhedhli, S. Blockchain-Enabled supply chains: An application in fresh-cut flowers. Applied Mathematical Modelling, vol 110 (2022) pp. 841–858.

[2] Singh, S., & Singh, A. Floriculture Market - by product type, by flower Type, by End-Use, by Distribution Channel & Forecast 2024 – 2032. In Global Market Insights Inc. (2024).

[3] Chen, J., Sun, Y., Oki, L. R., Sisneroz, J. A., Reid, K., Nackley, L. L., Contreras, R. N., Kim, S., Schuch, U. K., Haver, D. L., Stuke, M., Fron, A., Kopp, K., Jones, S. B., & Hipps, L. Climate-ready landscape Plants: Garden roses trialed at reduced irrigation frequency in Utah, USA. HortTechnology, vol 33, issue 5 (2023) pp. 477–492.

[4] Plusquellec, H. Modernization of large‐scale irrigation systems: is it an achievable objective or a lost cause. Irrigation and Drainage, vol 58, issue S1 (2009).

[5] Koech, R., & Langat, P. Improving Irrigation water use Efficiency: A review of advances, challenges and opportunities in the Australian context. Water, vol 10, issue 12 (2018) p. 1771.

[6] Mantilla, F., Mejía, G., & Tascón, D. The Role of Industry 4.0 Technologies in the Export Flower Industry: Insights from a Systematic Literature Review and Surveys in Emerging Economies. Results in Engineering (2025) p. 104507.

[7] Et-Taibi, B., Abid, M. R., Boufounas, E., Morchid, A., Bourhnane, S., Hamed, T. A., & Benhaddou, D. Enhancing water management in smart agriculture: a cloud and IoT-Based smart irrigation system. Results in Engineering, vol 22, (2024) p. 102283.

[8] Arachchillage, U. S. S. S., Amarasinghe, D. H. L., Kirindegamaarachchi, M. C., L, A. B., & W, F. W. M. K. S. S. Smart Intelligent Floriculture Assistant Agent (SIFAA). In 2021 3rd International Conference on Advancements in Computing (ICAC) (2022) pp. 449–454.

[9] Singh, H., Singh, T., & Sood, Y. Smart Floriculture: Emerging technologies and future Prospects. Journal of Experimental Agriculture International, vol 47, issue 2 (2025) pp. 172–181.

[10] Le, N. T. Development of Smart Irrigation & Sunshade Systems for Chrysanthemum Cultivation in Greenhouse Based on the Internet of Things. IFToMM Asian conference on Mechanism and Machine Science, (2021) pp. 950–960.

[11] Song, N. H., & He, N. Y. Crop Nutrition Diagnosis Expert System based on artificial neural networks. In Third International Conference on Information Technology and Applications (ICITA’05), vol 1 (2005) pp. 357–362.

[12] Eli-Chukwu, N. C. Applications of artificial intelligence in agriculture: A review. Eng. Technol. Appl. Sci. Res., vol 9 (2019) pp. 4377–4383.

[13] Vincent, D. R., Deepa, N., Elavarasan, D., Srinivasan, K., Chauhdary, S. H., & Iwendi, C. Sensors driven AI-Based Agriculture Recommendation model for assessing land suitability. Sensors, vol 19, issue 17 (2019) p. 3667.

[14] Adedoja, A., Owolawi, P. A., & Mapayi, T. Deep Learning Based on NASNet for Plant Disease Recognition Using Leave Images. In Proceedings of the International Conference on Advances in Big Data, Computing and Data Communication Systems (2019) pp. 1–5.

[15] Al-Ghobari, H. M., Mohammad, F. S., Marazky, M. S. E., & Dewidar, A. Z. Automated irrigation systems for wheat and tomato crops in arid regions. Water SA, vol 43, issue 2 (2017) p. 354.

[16] Bowlekar, A. P. Performance Evaluation of Real Time Automatic Irrigation System on the Yield of Cabbage (Brassica oleracea L.). International Journal of Pure & Applied Bioscience, vol 7, issue 5 (2019) pp. 160–165.

[17] Hardie, M. Review of novel and emerging proximal soil moisture sensors for use in agriculture. Sensors, vol 20, issue 23 (2020) p. 6934.

[18] Vera, J., Conejero, W., Mira-García, A. B., Conesa, M. R., & Ruiz-Sánchez, M. C. Towards irrigation automation based on dielectric soil sensors. The Journal of Horticultural Science and Biotechnology, vol 96, issue 6 (2021) pp. 696–707.

[19] Pramanik, M., Khanna, M., Singh, M., Singh, D., Sudhishri, S., Bhatia, A., & Ranjan, R. Automation of soil moisture sensor-based basin irrigation system. Smart Agricultural Technology, vol 2 (2021) p. 100032.

[20] Banda-Chavez, J. M., Serrano-Rubio, J. P., Manjarrez-Carrillo, A. O., Rodriguez-Vidal, L. M., & Herrera-Guzman, R. Intelligent Wireless Sensor Network for ornamental plant care. IECON 2018-44th Annual Conference of the IEEE Industrial Electronics Society. (2018). pp. 2723-2728.