AI Driven Crop Disease Detection and Management System

Abstract

Crop diseases cause large yield losses worldwide and represent a serious threat to food security. Traditional detection methods rely on manual inspection, which is time-consuming and error-prone. The AI-driven Crop Disease Detection and Management System presented in this paper combines environmental data analytics utilizing Random Forest regression for disease risk predictions with Convolutional Neural Networks (CNNs) for image-based disease identification. A carefully selected portion of the PlantVillage dataset, with an emphasis on the crops maize, tomato, and potato, is used to train the model. The hybrid approach leverages temperature, humidity, and rainfall data to increase prediction reliability. When compared to traditional CNN-only methods, experimental evaluation shows an accuracy of 94.33% and enhanced early disease prediction skills. The system, which offers real-time disease monitoring, is implemented as a mobile application and web platform. detection, forecasting, and treatment suggestions. This hybrid approach promotes sustainable agriculture through proactive disease management and optimized resource use.

Plant phenotyping relevance

植物画像から病害状態を識別するAI手法と、その評価・実装が研究の中心であり、植物病害フェノタイピングに該当する。

Code and data availability

The paper uses the public PlantVillage dataset and OpenWeatherMap API data, but provides no author-deposited code, trained models, or paper-specific dataset with an availability statement or URL. PlantVillage is a generic third-party dataset, not a paper-specific asset.

No evidence-backed public reproduction asset is currently recorded.