Quantifying pollen and spore morphology using a language model
Biology Letters · 2026
DOI: 10.1098/rsbl.2026.0313 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biology Letters, 2026. Verfasst von Luke Mander und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Environment, Earth and Ecosystem Sciences, The Open University , Milton Keynes, UK. Hauptthemen laut MEDLINE: Pollen, Spores, Plants. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: UKRI, Leverhulme Trust, China Scholarship Council.
Abstract (Originalsprache)
In a typical systematic paper, specimen morphology is described with natural language, and taxonomic specialists use glossaries of technical terminology to establish and communicate taxon concepts, using morphology to delimit species. Textual descriptions of specimen morphology are therefore foundational to biological systematics, but they also serve as a primary data source for studies of morphological evolution. Typically, researchers extract attributes of taxon morphology from descriptions and analyse them to quantify how organismal form has evolved. Focussing on fossil pollen and spores as records of plant evolution, we outline a potential approach to quantifying and comparing morphology that involves using a language model (LM) to transform textual descriptions of specimen morphology into numerical embeddings and then analysing the embeddings statistically. Our results show how an LM can be used to quantitatively analyse the morphological information contained within the text of taxonomic descriptions, illustrating that first-order botanical groupings such as pollen versus spores can be distinguished in the text of a single monograph and potentially from multiple texts by different authors. Although our dataset is small, we tentatively suggest that the spore-plant dominated tropical vegetation of the Carboniferous was comparable in morphological diversity to the angiosperm dominated tropical rainforests of the Palaeogene.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Environment, Earth and Ecosystem Sciences, The Open University , Milton Keynes, UK.
- Institute of Environmental Sciences, Leiden University , Leiden, The Netherlands.
- Department of Plant Biology, University of Illinois , Urbana, IL, USA.
- Smithsonian Tropical Research Institute , Panama City, Panama, Panama City, Panama.
- Department of Earth Sciences and Engineering, Missouri University of Science and Technology , Rolla, MO, USA.
ORCID-Profile: Luke Mander, Surangi W Punyasena, Carlos Jaramillo, Francisca Oboh-Ikuenobe
Förderung
- UKRI
- Leverhulme Trust
- China Scholarship Council
- NSF
Zitieren
APA
Mander, L., Sun, P., Punyasena, S. W., Jaramillo, C., & Oboh-Ikuenobe, F. (2026). Quantifying pollen and spore morphology using a language model. Biology Letters. https://doi.org/10.1098/rsbl.2026.0313
Vancouver
Mander L, Sun P, Punyasena SW, Jaramillo C, Oboh-Ikuenobe F. Quantifying pollen and spore morphology using a language model. Biology Letters. 2026. doi:10.1098/rsbl.2026.0313
BibTeX
@article{Mander2026,
author = {Mander, Luke and Sun, Peng and Punyasena, Surangi W and Jaramillo, Carlos and Oboh-Ikuenobe, Francisca},
title = {Quantifying pollen and spore morphology using a language model},
journal = {Biology Letters},
year = {2026},
doi = {10.1098/rsbl.2026.0313}
}
EUVIMED