Article Dans Une Revue Nature Plants Année : 2025

Learning the syntax of plant assemblages

1 UMR AMAP - Botanique et Modélisation de l'Architecture des Plantes et des Végétations
2 IROKO - Sciences environnementales guidées par les données
3 Cirad-BIOS - Département Systèmes Biologiques
4 LIRMM | ADVANSE - ADVanced Analytics for data SciencE
5 LECA - Laboratoire d'Ecologie Alpine
6 MU / MUNI - Masaryk University [Brno] = Masarykova univerzita [Brno] = Université Masaryk [Brno]
7 University of Belgrade [Belgrade]
8 Conservatoire Botanique National Méditerranéen de Porquerolles
9 UPV / EHU - Universidad del País Vasco [Espainia] / Euskal Herriko Unibertsitatea [España] = University of the Basque Country [Spain] = Université du pays basque [Espagne]
10 UNISI - Università degli Studi di Siena = University of Siena
11 MLU - Martin-Luther-Universität Halle Wittenberg - Martin-Luther-University Halle Wittenberg
12 University of Nova Gorica
13 UKIM - Ss. Cyril and Methodius University in Skopje / Универзитет „Св. Кирил и Методиј“ во Скопје [Skopje, Republic of North Macedonia]
14 Sapienza University of Rome - Department of Informatics and System Sciences
15 ZHAW - Zürcher Hochschule für Angewandte Wissenschaften = Zurich University of Applied Sciences
16 Universität Bayreuth [Deutschland] = University of Bayreuth [Germany] = Université de Bayreuth [Allemagne]
17 IAP-NASU - Institute of Applied Physics of the National Academy of Sciences of Ukraine
18 ISIGE - Institut Supérieur d'Ingénierie et de Gestion de l'Environnement
19 University of Rostock = Universität Rostock
20 EDYSAN - Ecologie et Dynamique des Systèmes Anthropisés - UMR CNRS 7058 UPJV
21 Swiss Federal Institute for Forest, Snow and Landscape Research WSL
Svetlana Aćić
Jesper Erenskjold Moeslund
  • Fonction : Auteur
Aaron Pérez-Haase
Remigiusz Pielech
  • Fonction : Auteur
Jozef Sibik
  • Fonction : Auteur
Zvjezdana Stančić
  • Fonction : Auteur
Domas Uogintas

Résumé

To address the urgent biodiversity crisis, it is crucial to understand the nature of plant assemblages. The distribution of plant species is shaped not only by their broad environmental requirements but also by micro-environmental conditions, dispersal limitations, and direct and indirect species interactions. While predicting species composition and habitat type is essential for conservation and restoration purposes, it remains challenging. In this study, we propose an approach inspired by advances in large language models to learn the ‘syntax’ of abundance-ordered plant species sequences in communities. Our method, which captures latent associations between species across diverse ecosystems, can be fine-tuned for diverse tasks. In particular, we show that our methodology is able to outperform other approaches to (1) predict species that might occur in an assemblage given the other listed species, despite being originally missing in the species list (16.53% higher accuracy in retrieving a plant species removed from an assemblage than co-occurrence matrices and 6.56% higher than neural networks), and (2) classify habitat types from species assemblages (5.54% higher accuracy in assigning a habitat type to an assemblage than expert system classifiers and 1.14% higher than tabular deep learning). The proposed application has a vocabulary that covers over 10,000 plant species from Europe and adjacent countries and provides a powerful methodology for improving biodiversity mapping, restoration and conservation biology. As ecologists begin to explore the use of artificial intelligence, such approaches open opportunities for rethinking how we model, monitor and understand nature.

Fichier principal
Vignette du fichier
Lablanc_etal_Nature_Plants_2025.pdf (3.66 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence
DOI

Cite 10.58060/QR4B-G979 Jeu de données European Vegetation Survey, The IAVS Working Group. (2023). EVA project # 182 – 2023-04-20 safeGUARDing biodivErsity aNd critical ecosystem services across sectors and scales (GUARDEN) – C. Leblanc [Data set]. Masaryk University, Faculty of Science, Department of Botany and Zoology. https://doi.org/10.58060/QR4B-G979

Dates et versions

hal-05313746 , version 1 (14-10-2025)

Licence

Identifiants

Citer

César Leblanc, Pierre Bonnet, Maximilien Servajean, Wilfried Thuiller, Milan Chytrý, et al.. Learning the syntax of plant assemblages. Nature Plants, 2025, 11, pp.2026-2040. ⟨10.1038/s41477-025-02105-7⟩. ⟨hal-05313746⟩
1909 Consultations
309 Téléchargements

Altmetric

Partager

  • More