Mapping melliferous tree species in Kenya via one-class classification with hyperspectral unsupervised domain adaptation

2026-08-03

AI Summary

This study addresses the challenge of unclear spatial distributions of melliferous tree species in Kenya, which hinders beekeeping development, and the limited cross-regional generalization of existing one-class classification methods. To overcome this, the authors propose a hyperspectral unsupervised domain adaptation framework for one-class classification (HyUDA-One), which requires only target-class labels and integrates airborne hyperspectral and LiDAR data. By introducing a spatial-spectral regularized pseudo-positive learning mechanism, the method effectively mitigates domain shift and significantly enhances model generalization to unlabeled new regions. Experimental results show F1-scores of 0.788, 0.845, and 0.768 for Senegalia mellifera, Vachellia tortilis, and Commiphora africana in the training area, respectively, and 0.756 and 0.884 for the first two species in unseen regions. The approach successfully generates melliferous species distribution maps and is extendable to other one-class remote sensing mapping tasks, such as invasive species detection.

Abstract

The beekeeping sector holds significant potential for livelihood diversification among the agropastoral communities in Kenya. Melliferous tree species play a critical role by providing essential nectar sources for bees. However, limited knowledge of their precise spatial distributions constrains the full development of beekeeping. One-class classification (OCC) offers a practical solution for detecting single target species without requiring extensive labeled data from other classes. Although existing OCC methods perform well in trained domains, the generalization capability to unseen domains remains limited due to domain shift. To address these challenges, this study proposes a hyperspectral unsupervised domain adaptation OCC framework (HyUDA-One) for tree species mapping using airborne hyperspectral imagery and laser scanning data. The spatial-spectral regularized pseudo-positive learning was designed to mitigate domain shift and improve model generalizability. The effectiveness of HyUDA-One was demonstrated by mapping three key melliferous tree species in two savanna landscapes in southern Kenya. The results show that HyUDA-One significantly improves performance in unlabeled domains. The F1-scores of 0.788, 0.845, and 0.768 were achieved for Senegalia mellifera, Vachellia tortilis, and Commiphora africana in the trained domain, respectively. In the untrained domain, the F1-scores of Senegalia mellifera and Vachellia tortilis were 0.756 and 0.884, respectively. The distribution maps revealed the spatial patterns of these melliferous tree species and the nectar source availability, offering an important reference for sustainable beekeeping development in savanna landscapes. Furthermore, the proposed framework can potentially be extended to other mapping applications, such as invasive species detection.

Problem

• melliferous tree species
• one-class classification
• domain shift
• hyperspectral imagery
• spatial distribution

Innovation

• one-class classification
• unsupervised domain adaptation
• hyperspectral imagery
• spatial-spectral regularization
• pseudo-positive learning