Advancing Coffee Leaf Rust Disease Management: A Deep Learning Approach for Accurate Detection and Classification Using Convolutional Neural Networks

Abstract

Coffee Leaf Rust (CLR), caused by the fungus Hemileia vastatrix, poses a severe threat to global coffee production. Timely detection is critical for effective control measures. This study employs Convolutional Neural Networks (CNNs) to enhance CLR detection accuracy. Traditionally, this task relies on expert assessment. DL emerges as a promising approach, capable of autonomously extracting salient features. Our model, trained on a diverse dataset, accurately identifies CLR. Using 1365 meticulously curated images, the model undergoes rigorous preprocessing and augmentation. The DL-based approach achieves remarkable accuracy (98.89%), precision (99.00%), recall (98.07%), and an F1 score of (98.55%). These outcomes establish the CNN model as a proficient system for precise, real-time CLR diagnosis. This study contributes to the creation of an efficient system, safeguarding coffee orchard vitality and productivity.

Plant phenotyping relevance

コーヒー葉の病徴を画像から検出・分類するCNN手法が研究の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として採用。

Code and data availability

The paper uses the publicly available RoCoLe dataset, but that is a cited prior-work dataset (Parraga-Alava et al., 2019), not a paper-specific asset deposited by these authors. No author code, trained model, or data deposit with an availability statement or URL is provided; the review-history and license links are not

No evidence-backed public reproduction asset is currently recorded.