Unsupervised detection of ash dieback disease (Hymenoscyphus fraxineus) using diffusion-based hyperspectral image clustering

TL;DR

This paper presents an unsupervised hyperspectral image clustering method, D-VIS, for detecting ash dieback disease, achieving comparable accuracy to supervised methods without requiring expert labels.

Contribution

It introduces the D-VIS clustering algorithm for unsupervised detection of ash dieback disease in hyperspectral images, reducing reliance on labeled data.

Findings

Achieved 71% overall accuracy in disease detection

Unsupervised clustering closely matches supervised classification results

Demonstrates potential for large-scale forest health monitoring

Abstract

Ash dieback (Hymenoscyphus fraxineus) is an introduced fungal disease that is causing the widespread death of ash trees across Europe. Remote sensing hyperspectral images encode rich structure that has been exploited for the detection of dieback disease in ash trees using supervised machine learning techniques. However, to understand the state of forest health at landscape-scale, accurate unsupervised approaches are needed. This article investigates the use of the unsupervised Diffusion and VCA-Assisted Image Segmentation (D-VIS) clustering algorithm for the detection of ash dieback disease in a forest site near Cambridge, United Kingdom. The unsupervised clustering presented in this work has high overlap with the supervised classification of previous work on this scene (overall accuracy = 71%). Thus, unsupervised learning may be used for the remote detection of ash dieback disease without the need for expert labeling.