EUVIMEDEUVIMED entdecken
Open Access

Towards the automatized identification of moss species from their spore morphology

Alix Milis iD, Martin Hofmann iD, Patrick Mäder iD, Jana Wäldchen iD, Myriam de Haan, Petra Ballings, Iris Van der Beeten, Bernard Goffinet iD, Alain Vanderpoorten

Annals of Botany · 2026

DOI: 10.1093/aob/mcaf215 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of Botany, 2026. Verfasst von Alix Milis und 8 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Botany, University of Liège, B22 Sart-Tilman, Liège B-4000, Belgium. Hauptthemen laut MEDLINE: Bryophyta, Spores. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Funds for Scientific Research (FRS-FNRS).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Aims Automatized species identification tools have massively facilitated plant identification. In mosses, spore ultrastructure appears to be a promising taxonomic character, but has been largely under-exploited. Here, we test artificial intelligence-based approaches to identify species from their spore morphology. In particular, we determine whether the number of spores, their polarity, and variation among populations and capsules affect model accuracy.

Methods

Scanning electron microscopy spore images were generated for five capsules of five populations in ten species. Convolutional neural networks with a highly modularized architecture (ResNeXt) were trained to identify the species, population and capsule of origin of a spore. The training set was progressively sub-sampled to test the impact of sample size on model accuracy. To assess whether variation in spore morphology among populations affected model accuracy, one population was successively removed to test a model trained on the four remaining populations. Key Results Species were correctly identified at average rates of 92 %, regardless of polarity. Model accuracy decreased progressively with decreasing sample size, dropping to about 80 % with 15 % of the initial dataset. The population and capsule of origin of a spore was retrieved at rates >75 %, indicating the presence of diagnostic population and capsule markers on the sporoderm. Strong population structure in some species caused a substantial drop of model accuracy when model training and testing was performed on different populations.

Conclusions

Spore morphology appears to be an extremely promising tool for moss species identification and may usefully complement the suite of morphological characters used so far in moss taxonomy. The presence of spore diagnostic features at the population and capsule level raises substantial questions on the origin of this structure, which are discussed. Substantial infraspecific variation makes it necessary, however, to train an automatized identification tool from a range of populations and capsules.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BryophytaSporesMicroscopy, Electron, ScanningNeural Networks, ComputerArtificial IntelligenceSpecies Specificity

Stichwörter der Autor:innen

Bryophytesconvolutional neural networksscanning electron microscopyspecies identificationsporessporodermultrastructure

Autor:innen und Institutionen

  • Institute of Botany, University of Liège, B22 Sart-Tilman, Liège B-4000, Belgium.
  • Research and Collection Departments, Botanic Garden Meise, Nieuwelaan 38, Meise B-1860, Belgium.
  • Fakultät für Informatik und Automatisierung, Data-Intensive Systems and Visualization, Technische Universität Ilmenau, Ehrenbergstraße 29, Ilmenau 98693, Germany.
  • German Centre for Integrative Biodiversity Research, iDiv (Halle-Jena-Leipzig), Puschstraße 4, Leipzig 04103, Germany.
  • Faculty of Biological Sciences, Friedrich Schiller University Jena, Fürstengraben 1, Jena 07743, Germany.
  • Department of Biogeochemical Integration, Max Planck Institute for Biogeochemistry, Hans Knöll Strasse 10, Jena 07745, Germany.

ORCID-Profile: Alix Milis, Martin Hofmann, Patrick Mäder, Jana Wäldchen, Bernard Goffinet

Förderung

  • Funds for Scientific Research (FRS-FNRS)

Zitieren

APA

Milis, A., Hofmann, M., Mäder, P., Wäldchen, J., de Haan, M., Ballings, P., Van der Beeten, I., Goffinet, B., & Vanderpoorten, A. (2026). Towards the automatized identification of moss species from their spore morphology. Annals of Botany. https://doi.org/10.1093/aob/mcaf215

Vancouver

Milis A, Hofmann M, Mäder P, Wäldchen J, de Haan M, Ballings P, et al. Towards the automatized identification of moss species from their spore morphology. Annals of Botany. 2026. doi:10.1093/aob/mcaf215

BibTeX
@article{Milis2026,
  author = {Milis, Alix and Hofmann, Martin and Mäder, Patrick and Wäldchen, Jana and de Haan, Myriam and Ballings, Petra and Van der Beeten, Iris and Goffinet, Bernard and Vanderpoorten, Alain},
  title = {Towards the automatized identification of moss species from their spore morphology},
  journal = {Annals of Botany},
  year = {2026},
  doi = {10.1093/aob/mcaf215}
}
Kostenlos starten →