From Articles to Canopies: Knowledge-Driven Pseudo-Labelling for Tree Species Classification using LLM Experts

2026-04-17

AI Summary

This study addresses key challenges in hyperspectral tree species classification—namely, scarce labels, class imbalance, spectral mixing, and ecological heterogeneity—by integrating hyperspectral and LiDAR data to construct canopy graph structures. It pioneers the use of large language models to automatically extract species coexistence knowledge from ecological literature, generating a coexistence probability matrix as a biologically informed prior. This prior is embedded into a semi-supervised pseudo-labeling pipeline to enable accurate classification under low annotation costs. Evaluated on real-world forest datasets, the proposed method achieves a 5.6% accuracy gain over the best baseline. Expert assessment confirms that errors in the coexistence prior remain below 15%, demonstrating the effectiveness and novelty of this knowledge-driven approach.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data
• Computer Vision: Multi-modal Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Hyperspectral tree species classification is challenging due to limited and imbalanced class labels, spectral mixing (overlapping light signatures from multiple species), and ecological heterogeneity (variability among ecological systems). Addressing these challenges requires methods that integrate biological and structural characteristics of vegetation, such as canopy architecture and interspecific interactions, rather than relying solely on spectral signatures. This paper presents a biologically informed, semi-supervised deep learning method that integrates multi-sensor Earth observation data, specifically hyperspectral imaging (HSI) and airborne laser scanning (ALS), with expert, ecological knowledge. The approach relies on biologically inspired pseudo-labelling over a precomputed canopy graph, yielding accurate classification at low training cost. In addition, ecological priors on species cohabitation are automatically derived from reliable sources using large language models (LLMs) and encoded as a cohabitation matrix with likelihoods of species occurring together. These priors are incorporated into the pseudo-labelling strategy, effectively introducing expert knowledge into the model. Experiments on a real-world forest dataset demonstrate 5.6% improvement over the best reference method. Expert evaluation of cohabitation priors reveals high accuracy with differences no larger than 15%.

Problem

• hyperspectral tree species classification
• spectral mixing
• ecological heterogeneity
• limited labeled data
• canopy structure

Innovation

• pseudo-labelling
• large language models
• hyperspectral classification
• ecological priors
• canopy graph