Smart Agriculture System for Grape Leaf Disease Detection Using AI, Image Processing and Sensors

Abstract: Modern agriculture faces growing challenges including crop diseases, inconsistent environmental conditions, and the absence of intelligent monitoring tools. Grape cultivation, a major commercial crop in Maharashtra and across India, is particularly vulnerable to diseases like Black Rot, Esca, and Leaf Blight, which can cause severe yield losses if not detected early. This paper proposes a Smart Agriculture System that combines IoT-based environmental sensing, Digital Twin technology, and Artificial Intelligence to address these challenges in a unified and practical platform. The system uses an ESP32 microcontroller interfaced with DHT11, soil moisture, and MQ135 sensors to collect real-time field data on temperature, humidity, soil conditions, and air quality. Sensor readings are wirelessly transmitted to a web- based dashboard that forms a live Digital Twin of the farm. In addition, a Convolutional Neural Network (CNN) trained on the PlantVillage grape leaf dataset allows farmers to upload leaf images and instantly receive disease classification results — identifying Healthy leaves, Black Rot, Esca, or Leaf Blight with approximately 94.7% accuracy. The overall system reduces dependence on manual field inspections, enables timely alerts, and supports informed decision-making for better crop management. Experimental results confirm the solution is cost-effective, scalable, and well-suited for real- world deployment in smart farming environments.

Keywords: Smart Agriculture, Grape Leaf Disease Detection, ESP32, Digital Twin, CNN, IoT, Image Processing, Precision Farming, PlantVillage Dataset