AGROSENSE: Smart Farming and Rice Crop Disease Detection Using IoT and Machine Learning

Abstract

Rice cultivation is affected by water mismanagement and plant diseases, leading to reduced productivity. This paper presents AgroSense, an IoT- and Machine Learning-based smart farming system for real-time monitoring and disease detection in rice crops. IoT sensors measure soil moisture, temperature, humidity, and pH, while a Convolutional Neural Network (CNN) model classifies rice leaf diseases such as Blast, Sheath Blight, and Bacterial Blight. Automated irrigation is triggered based on soil moisture thresholds to optimize water usage. Experimental results show reliable sensor performance and a validation accuracy of approximately 89% for disease detection. Cloud integration enables real-time monitoring and alert notifications through a mobile/web interface. The system reduces manual intervention, improves early disease identification, and supports efficient and sustainable rice farming.

Code and data availability

The article describes an IoT/CNN rice disease detection system but provides no public dataset, image collection, code repository, model checkpoint, or supplement with availability language. No paper-specific reproducible asset is identified.

No evidence-backed public reproduction asset is currently recorded.