Edge AI based soil nutrient monitoring and crop suggestion system using raspberry pi

The aim of this study is to develop an Edge AI-based soil nutrient monitoring and crop recommendation system using a Raspberry Pi 4 Model B. The system utilizes pH and NPK sensors to measure soil properties and employs a lightweight Random Forest classifier for predicting suitable crops. The proposed system achieves a crop recommendation accuracy of 95.4%, with an inference latency of 95 milliseconds and an end-to-end response time of 0.18 seconds. Performance is evaluated in terms of latency, power consumption, hardware cost, and system uptime. Field validation was conducted using 2,400 soil samples collected from twelve agricultural plots in Tamil Nadu, demonstrating the system’s reliability in real-world conditions. The edge-based architecture enables real-time processing without reliance on internet connectivity, making it suitable for rural deployments. Additionally, the system is cost-effective, with a hardware cost of approximately USD 112, making it accessible for smallholder farmers. Future work includes integrating advanced data sources and improving model performance through distributed learning approaches.

1.       R. Rao and P. Nair, "IoT-based precision agriculture monitoring system using Raspberry Pi," Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 4, pp. 145–153, 2021. 2.       S. Balaji, A. Rajan, and K. Suresh, "Machine learning approaches for soil nutrient prediction in precision farming," Comput. Electron. Agric., vol. 182, p. 105998, 2021. 3.       M. Javaid, A. Haleem, I. H. Khan, and R. Suman, "Understanding the potential applications of artificial intelligence in agriculture sector," Adv. Agrochem., vol. 2, no. 1, pp. 15–30, 2023. 4.       D. Benos, D. Tagarakis, G. Dolias, R. Berruto, D. Kateris, and D. Bochtis, "Machine learning in agriculture: A comprehensive updated review," Sensors, vol. 21, no. 11, p. 3758, 2021. 5.       V. G. Dhanya, A. Subeesh, N. L. Kushwaha, D. K. Vishwakarma, T. N. Kumar, N. Ritika, and A. N. Singh, "Deep learning based weed detection and smart pesticide spraying robot for precision agriculture," Comput. Electron. Agric., vol. 206, p. 107647, 2022. 6.       K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, "Machine learning in agriculture: A review," Sensors, vol. 18, no. 8, p. 2674, 2018. 7.       T. Talaviya, D. Shah, N. Patel, H. Yagnik, and M. Shah, "Implementation of artificial intelligence in agriculture for optimisation of irrigation and application of pesticides and herbicides," Artif. Intell. Agric., vol. 4, pp. 58–73, 2020. 8.       S. S. Band, S. Janizadeh, S. C. Pal, A. Saha, R. Chakrabortty, M. Shokri, and A. Mosavi, "Novel ensemble approach of deep learning neural network (DLNN) model and particle swarm optimization (PSO) algorithm for prediction of gully erosion susceptibility," Sensors, vol. 20, no. 19, p. 5609, 2020. 9.       A. Dey, S. Ghosh, and T. K. Das, "Edge computing in IoT-based agriculture: Challenges and applications," in Proc. Int. Conf. Comput. Intell. Knowl. Econ., Dubai, UAE, 2021, pp. 678–683. 10.    H. Pham, T. H. Nguyen, M. H. Tran, and N. T. Nguyen, "A real-time monitoring system for soil parameters using IoT and machine learning," IEEE Sens. J., vol. 22, no. 10, pp. 9905–9914, 2022.