Detection of Bark Beetle Attacks using Hyperspectral PRISMA Data and Few-Shot Learning

TL;DR

This paper introduces a novel few-shot learning approach using contrastive learning and hyperspectral PRISMA data to accurately detect bark beetle infestations and forest health status with limited labeled samples.

Contribution

It presents a new contrastive learning framework for hyperspectral data that improves detection of bark beetle attacks with minimal labeled data.

Findings

Outperforms original PRISMA spectral bands in detection accuracy

Surpasses Sentinel-2 data in identifying bark beetle infestations

Effective in estimating proportions of healthy, attacked, and dead trees

Abstract

Bark beetle infestations represent a serious challenge for maintaining the health of coniferous forests. This paper proposes a few-shot learning approach leveraging contrastive learning to detect bark beetle infestations using satellite PRISMA hyperspectral data. The methodology is based on a contrastive learning framework to pre-train a one-dimensional CNN encoder, enabling the extraction of robust feature representations from hyperspectral data. These extracted features are subsequently utilized as input to support vector regression estimators, one for each class, trained on few labeled samples to estimate the proportions of healthy, attacked by bark beetle, and dead trees for each pixel. Experiments on the area of study in the Dolomites show that our method outperforms the use of original PRISMA spectral bands and of Sentinel-2 data. The results indicate that PRISMA hyperspectral data combined with few-shot learning offers significant advantages for forest health monitoring.