Early detection of banana leaf diseases using CNN, IoT sensors, and RAG-based prototype in the Dominican Republic (#2415)

Authors

Orgaz-Agüera, Francisco

Cascante Cruz, Gadiel

Cristóbal Marcelino, Cindy Marilyn

Trinidad Domínguez, María Esther

Abstract

This paper presents the design, development, and validation of the DeepBanana platform, an artificial intelligence (AI)-based solution for the early detection of diseases in banana crops through automated analysis of leaf images. Framed within the international DeepFarm project, funded by the Erasmus+ program, the system integrates convolutional neural networks (CNNs), data augmentation techniques, transfer learning, and a modular architecture adaptable to the technological conditions of Dominican farms. The platform was trained on a labeled dataset of over 1,900 images classified into seven plant health categories, achieving an accuracy close to 89%. The technical pipeline stages, CNN model architecture, automated retraining system, and the incorporation of a conversational interface with retrieval-augmented generation (RAG) capabilities are detailed.