Self-Supervised Learning for Soybean Disease Detection Using UAV Hyperspectral Imagery

Abstract

Highlights: What are the main findings? A self-supervised learning framework achieves 92% accuracy in early soybean disease detection using unlabelled UAV hyperspectral data, matching supervised baselines. A distance-based spectral pairing technique enables effective feature learning directly from canopy reflectance without manual annotations. What are the implications of the main findings? The framework addresses the annotation bottleneck in remote sensing, enabling scalable early disease detection for large-scale agricultural monitoring. The approach reduces reliance on expert-labeled field data while maintaining high accuracy, making precision agriculture more accessible and cost-effective. The accuracy of machine learning models in plant disease detection significantly relies on large volumes of knowledge-based labeled data; the acquisition of annotation remains a significant bottleneck in domain-specific research such as plant disease detection. While unsupervised learning alleviates the need for labeled data, its effectiveness is constrained by the intrinsic separability of feature clusters. These limitations underscore the need for approaches that enable supervised early disease detection without extensive annotation. To this end, we propose a self-supervised learning (SSL) framework for the early detection of soybean’s sudden death syndrome (SDS) using hyperspectral data acquired from an unmanned aerial vehicle (UAV). The methodology employs a novel distance-based spectral pairing technique that derives intermediate labels directly from the data. In addition, we introduce an adapted contrastive loss function designed to improve cluster separability and reinforce discriminative feature learning. The proposed approach yields an 11% accuracy gain over agglomerative hierarchical clustering and attains both classification accuracy and F1 score of 0.92, matching supervised baselines. Reflectance frequency analysis further demonstrates robustness to label noise, highlighting its suitability in label-scarce settings.