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

2025-11-14

AI Summary

Pine wilt disease, caused by the pinewood nematode and vectored by bark beetles, severely degrades coniferous forest health, necessitating early, accurate, and scalable monitoring. Method: This paper proposes a quantitative forest health monitoring framework integrating hyperspectral remote sensing with few-shot learning. It introduces a contrastive learning–driven 1D CNN to extract discriminative spectral features from PRISMA hyperspectral data, followed by pixel-wise few-shot support vector regression (SVR) to estimate sub-pixel fractional abundances of healthy, infested, and dead trees. Contribution/Results: Evaluated in the Dolomites (Italy), the method significantly outperforms both raw PRISMA bands and Sentinel-2 multispectral data—particularly under extreme sample scarcity—enabling sub-pixel quantification of tree health status. It establishes a novel paradigm for high-accuracy, low-cost, large-scale early warning of forest pest outbreaks.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• Detecting bark beetle infestations in coniferous forests using hyperspectral data
• Developing few-shot learning methods for forest health monitoring with limited samples
• Estimating proportions of healthy, attacked and dead trees from satellite imagery

Innovation

• Few-shot learning with contrastive learning framework
• One-dimensional CNN encoder for hyperspectral feature extraction
• Support vector regression for tree health classification