MACHINE VISION HYPERGRAPH NEURAL NETWORKS FOR EARLY DETECTION OF DAMPING-OFF AND ROOT ROT DISEASE IN COFFEE PLANTATIONS

Abstract

Coffee has long promoted international trade and prosperity, employing millions of small-scale producers. The high demand for this crop has resulted in global supply networks. Young coffee seedlings are vulnerable to fungal diseases such as damping-off and root rot, which cause significant damage and substantially reduce plant productivity. Signs include wilting, root rot, and seedling death both before and after sprouting. Deep learning could allow automatic and scalable prediction of plant diseases. This study aims to enhance early detection of coffee seedling diseases, ensure model adaptability across samples, and optimize computational efficiency for practical implementation. The proposed Vision-based Heterogeneous Graph Neural Network (Vi-HGNN) model, which combines computer vision and graph neural networks (GNNs), provides information about disease transmission patterns over time and space. After training, the model can accurately detect early signs of infection, allowing farmers to intervene before the damage spreads. Experimental results show that Vi-HGNN achieves a 97.77 % detection accuracy, outperforming existing methods in precision, F1-score, and pathogen coverage. Future developments will aim to expand detection capabilities to include additional diseases, pests, and weeds, improving overall crop health monitoring.