Smart Farming with Deep Learning: CNN-Based Crop Disease Detection Using Drone Imaging and IoT

Abstract

Plant diseases represent a major challenge to global food security, often resulting in severe yield reductions if not detected and controlled promptly. This work introduces an AI-based framework that integrates deep learning, drone-assisted imaging, and IoT-enabled real-time monitoring for effective disease detection and management. A convolutional neural network (CNN) is trained on crop leaf image datasets to accurately classify different disease types. The system is further equipped with a mobile application and cloud-based alert service to support timely farmer interventions. Experimental evaluation demonstrates a classification accuracy exceeding 95% and reliable alert generation, underscoring the system's potential as a scalable solution for precision agriculture and smart farming.

Plant phenotyping relevance

植物葉画像から病害状態を分類するCNN・ドローン画像・IoT監視システムが研究の中心であり、植物病害の表現型を直接推定する方法として評価されている。

Code and data availability

The paper describes a CNN (ResNet-50/MobileNet) trained on the Plant Village dataset for crop disease detection, but provides no author-deposited dataset, code, model checkpoints, or supplement with availability statements or URLs. Plant Village is a third-party dataset cited as a training source, not a paper-specific,

No evidence-backed public reproduction asset is currently recorded.