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

• URL: http://arxiv.org/abs/2604.16115v1
• Date: Fri, 17 Apr 2026 14:52:02 GMT
• Title: From Articles to Canopies: Knowledge-Driven Pseudo-Labelling for Tree Species Classification using LLM Experts
• Abstract summary: This paper presents a biologically informed, semi-supervised deep learning method that integrates multi-sensor Earth observation data with expert, ecological knowledge.<n>The approach relies on biologically inspired pseudo-labelling over a precomputed canopy graph, yielding accurate classification at low training cost.<n> Experiments on a real-world forest dataset demonstrate 5.6% improvement over the best reference method.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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%.

Related papers

• GeoDecider: A Coarse-to-Fine Agentic Workflow for Explainable Lithology Classification [52.5232577739543]
  Lithology classification aims to infer subsurface rock types from well-logging signals.<n>Existing methods still treat lithology classification as a single-pass classification task.<n>We propose GeoDecider, a coarse-to-fine agentic workflow that enables accurate and explainable lithology classification.
  arXiv  Detail & Related papers  (2026-05-05T05:42:51Z)
• Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference [17.708423679075075]
  We present two end-to-end variants for hierarchy-aware multimodal learning.<n>CLiBD-HiR introduces Hierarchical Information Regularization (HiR) to shape embedding geometry across taxonomic levels.<n>CLiBD-HiR-Fuse trains a lightweight fusion predictor that supports image-only, DNA-only, or joint inference.
  arXiv  Detail & Related papers  (2026-03-26T15:47:03Z)
• Overview of GeoLifeCLEF 2023: Species Composition Prediction with High Spatial Resolution at Continental Scale Using Remote Sensing [9.66382598562254]
  We organized an open machine learning challenge called GeoLifeCLEF 2023.<n>The training dataset comprised of 5 million plant species distributed across Europe.<n>We evaluated models ability to predict species in 22 thousand small plots based on standardized surveys.
  arXiv  Detail & Related papers  (2025-09-30T05:49:16Z)
• Hyperbolic Multimodal Representation Learning for Biological Taxonomies [23.639218053531962]
  Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence.<n>We investigate whether hyperbolic networks can provide a better embedding space for such hierarchical models.<n>Our method embeds multimodal inputs into a shared hyperbolic space using contrastive and a novel stacked entailment-based objective.
  arXiv  Detail & Related papers  (2025-08-22T18:52:50Z)
• BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning [60.80381372245902]
  We find emergent behaviors in biological vision models via large-scale contrastive vision-language training.<n>We train BioCLIP 2 on TreeOfLife-200M to distinguish different species.<n>We identify emergent properties in the learned embedding space of BioCLIP 2.
  arXiv  Detail & Related papers  (2025-05-29T17:48:20Z)
• Combining Observational Data and Language for Species Range Estimation [63.65684199946094]
  We propose a novel approach combining millions of citizen science species observations with textual descriptions from Wikipedia.<n>Our framework maps locations, species, and text descriptions into a common space, enabling zero-shot range estimation from textual descriptions.<n>Our approach also acts as a strong prior when combined with observational data, resulting in more accurate range estimation with less data.
  arXiv  Detail & Related papers  (2024-10-14T17:22:55Z)
• TEPI: Taxonomy-aware Embedding and Pseudo-Imaging for Scarcely-labeled Zero-shot Genome Classification [0.0]
  A species' genetic code or genome encodes valuable evolutionary, biological, and phylogenetic information. Traditional bioinformatics tools have made notable progress but lack scalability and are computationally expensive. We propose addressing this problem through zero-shot learning using TEPI, taxonomy-aware Embedding and Pseudo-Imaging.
  arXiv  Detail & Related papers  (2024-01-24T04:16:28Z)
• Spatial Implicit Neural Representations for Global-Scale Species Mapping [72.92028508757281]
  Given a set of locations where a species has been observed, the goal is to build a model to predict whether the species is present or absent at any location. Traditional methods struggle to take advantage of emerging large-scale crowdsourced datasets. We use Spatial Implicit Neural Representations (SINRs) to jointly estimate the geographical range of 47k species simultaneously.
  arXiv  Detail & Related papers  (2023-06-05T03:36:01Z)
• Two-View Fine-grained Classification of Plant Species [66.75915278733197]
  We propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species.
  arXiv  Detail & Related papers  (2020-05-18T21:57:47Z)
• Automatic image-based identification and biomass estimation of invertebrates [70.08255822611812]
  Time-consuming sorting and identification of taxa pose strong limitations on how many insect samples can be processed. We propose to replace the standard manual approach of human expert-based sorting and identification with an automatic image-based technology. We use state-of-the-art Resnet-50 and InceptionV3 CNNs for the classification task.
  arXiv  Detail & Related papers  (2020-02-05T21:38:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.