Early Identification and Notification of Diseased Crops Using AI Powered Internet of Things Device

Öz

This work seeks to contribute to the realization, by 2030, of the United Nations’ Sustainable Development Goal number two: “End hunger, achieve food security and improved nutrition and promote sustainable agriculture.” To contribute to the attainment of this goal, farm crops must be in a healthy state and maintained in healthy conditions. So, a round-the-clock monitoring of plant conditions is vital. There have been some plant monitoring techniques, such as the conventional monitoring technique, in which human is involved with the physical inspection of crops on farmlands. Satellite monitoring of crops has been used in some other instances but are expensive and limited to large scale farmlands. To make crop monitoring technology available to all including peasant farmers in developing nations, the adoption of convolution matrix of artificial neural network and Internet of Things (IoT) gives birth to this new approach. The developed system demonstrated high accuracy of 0.51 from the classification report obtained while detecting crop diseases and defects, collecting real-time environmental data. The macro average value of 0.56 was obtained for precision of the developed model for the 21 samples considered. Classification recall weighted average value of 0.51 and weighted f1-score of 0.49 were obtained simultaneously. For the model’s hardware, key components used by the system included an IoT-based sensor network, a camera system utilizing YOLOv8 for image processing, an automated response system, and a cloud-based platform for remote monitoring. Careful assembly of these components formed a formidable remote monitoring and reporting system that seeks to ease and improve methods of plant monitoring. For the analysis of the plant leaves, a neural network processes the image, and comparisons are made with the stored feature of healthy crop leaves. Confusion and classification results showed significant potential for enhancing crop management practices, improving resource utilization, and enabling data-driven agricultural decision-making. Validation of the AI-enhanced model was carried out using field data logged in cloud by means of IoT. All these operations are displayed on a liquid crystal display unit of the model. The successful implementation of this technology serves as a model for the broader adoption of smart farming techniques, with implications for improving agricultural productivity and sustainability. While further long-term testing is recommended, this work presents a significant contribution to the field of precision agriculture, offering promising solutions to critical food crisis challenges in the world.

Anahtar Kelimeler

• IoT
• SDGs
• FAO
• UNICEF
• Crop

Etik Beyan

There is no need to obtain permission from the ethics committee for this study.

Kaynakça

1. Adetutu, A. E., Bayo, Y. F., Emmanuel, A. A. and Opeyemi, A. A. A. (2024). A Review of hyperspectral ımaging analysis techniques for onset crop disease detection, ıdentification and classification. Journal of Forest and Environmental Science, 40(1): 1–8.
2. Aithal, S. and Aithal, P. S. (2024). Information Communication and computation technologies (ICCT) for Agricultural and environmental ınformation systems for society 5.0. International Journal of Applied Engineering and Management Letters (IJAEML), 8(1): 67–100.
3. Akinyuyi, O. B. (2024). AI in agriculture: A comparative review of developments in the USA and Africa. Research Journal of Science and Engineering, 10(2): 060–070.
4. Alarcon, M. and Marty, P. (2024). Observing farm plots to increase attentiveness and cooperation with nature: A case study in Belgium. Agriculture and Human Values, 41(2): 525–539.
5. Asante, B. O., Ma, W., Prah, S. and Temoso, O. (2024). Promoting the adoption of climate-smart agricultural technologies among maize farmers in Ghana: using digital advisory services. Mitigation and Adaptation Strategies for Global Change, 29(3): 19.
6. Baitu, G. P., Gadalla, O. A. A. and Öztekin, Y. B. (2023). Traditional Machine learning-based classification of cashew kernels using colour features. Journal of Tekirdag Agricultural Faculty, 20(1): 115–124.
7. Chandrasekaran, S. K. and Rajasekaran, V. A. (2024). Energy-efficient cluster head using modified fuzzy logic with WOA and path selection using enhanced CSO in IoT-enabled smart agriculture systems. The Journal of Supercomputing, 80(8): 11149–11190.
8. Che, Y., Zheng, G., Li, Y., Hui, X. and Li, Y. (2024). Unmanned agricultural machine operation system in farmland based on ımproved fuzzy adaptive priority-driven control algorithm. Electronics, 13(20): 4144.

9. Fitri, R., Perkasa, A. Y., Widjaja, H. and Seanders, O. (2024). Evaluation of Urban Farming System Sustainability in Central Province of Jakarta, Indonesia. Journal of Tekirdag Agricultural Faculty, 21(1): 256–264.
10. Hakimi, M., Amiri, G. A., Jalalzai, S., Darmel, F. A. and Ezam, Z. (2024). Exploring the integration of AI and cloud computing: navigating opportunities and overcoming challenges. TIERS Information Technology Journal, 5(1): 57-69.
11. Harsonowati, W., Latifah, E., Nurrahma, A. H. I., Purwani, J., Iqbal, R., Parray, J. A. and Patel, A. D. (2024). Emerging diseases: trend research and omics-based analysis reveals mechanisms of endophytes modulate Chilli plant resilience. Symbiosis, 93(3): 241-254.
12. Jaramillo-Hernández, J. F., Julian, V., Marco-Detchart, C. and Rincón, J. A. (2024). Application of machine vision techniques in low-cost devices to improve efficiency in precision farming. Sensors, 24(3): 937.
13. Katoch, O. R. (2024). Tackling child malnutrition and food security: assessing progress, challenges, and policies in achieving SDG 2 in India. Nutrition & Food Science, 54(2): 349-365.
14. Kommey, R. E. and Fombad, M. C. (2024). Knowledge Sharing technologies for rice farmers: A perspective from the Eastern Region of Ghana. Knowledge Management & E-Learning, 16(2): 355–378.
15. Li, H., Wang, S. X., Shang, F., Niu, K. and Song, R. (2024). Applications of large language models in cloud computing: An empirical study using real-world data. International Journal of Innovative Research in Computer Science & Technology, 12(4): 59-69.
16. Mondal, D., Roy, K., Pal, D. and Kole, D. K. (2022). Deep Learning-based approach to detect and classify signs of crop leaf diseases and pest damage. SN Computer Science, 3(6): 433.
17. Oliveira, A., Dias, A., Santos, T., Rodrigues, P., Martins, A. and Almeida, J. (2024). LiDAR-Based unmanned aerial vehicle offshore wind blade ınspection and modeling. Drones, 8(11): 617.
18. Patil, R. R., Kumar, S., Rani, R., Agrawal, P. and Pippal, S. K. (2023). A bibliometric and word cloud analysis on the role of the internet of things in agricultural plant disease detection. Applied System Innovation, 6(1): 27.
19. Quy, V. K., Hau, N. V., Anh, D. V., Quy, N. M., Ban, N. T., Lanza, S., ... and Muzirafuti, A. (2022). IoT-enabled smart agriculture: architecture, applications, and challenges. Applied Sciences, 12(7): 3396.
20. Sporchia, F., Antonelli, M., Aguilar-Martínez, A., Bach-Faig, A., Caro, D., Davis, K. F., Sonnino, R. and Galli, A. (2024). Zero hunger: Future challenges and the way forward towards the achievement of sustainable development goal 2. Sustainable Earth Reviews, 7(1): 10.
21. Tessema, L., Negash, W., Kakuhenzire, R., Belay, G., Seid, E. and Enyew, M. (2023). Seed health trade‐offs in adopting quality declared seed in potato farming systems. Crop Science, 64(3): 1340–1348.
22. Xin, J. and Zazueta, F. (2016). Technology trends in ICT–towards data-driven, farmer-centered and knowledge-based hybrid cloud architectures for smart farming. Agricultural Engineering International: CIGR Journal, 18(4): 275-279.
23. Zhang, Y., Zhang, B., Shen, C., Liu, H., Huang, J., Tian, K. and Tang, Z. (2024). Review of the field environmental sensing methods based on multi-sensor information fusion technology. International Journal of Agricultural and Biological Engineering, 17(2): 1-13.