iCrop+: An Edge-boosted Crop Disease Detection System via TinyML and LoRa Communication

Crop disease detection is essential for controlling dis-ease spread and minimizing agricultural losses. In this demo, we present an implementation of iCrop+, an end-to-end autonomous crop disease detection system that integrates on-device AI, low-power long-range communication (LoRa), and server-based deep learning to create a hybrid architecture suitable for real-world deployment. The prototype efficiently balances local processing and remote inference through category-based optimization, adaptive classification, and intelligent data transmission, ensuring that only the most informative segments are transmitted to the server. Built on low-cost devices such as Raspberry Pi, LoRa transceiver modules, and a laptop, the demo showcases its potential for enhancing precision agriculture applications, providing a scalable, cost-effective solution for large-scale crop monitoring. The validation results show that iCrop+ provides 90% classification accuracy while reducing data transmission by up to 60% over server-only inference solutions.