Learning the syntax of plant assemblages

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.

Authors

Institutions

Publication Details

Journal
Nature Plants
Published
2025-10-13
DOI
https://doi.org/10.1038/s41477-025-02105-7
Citations
2
Primary Topic
Species Distribution and Climate Change
Type
article
Field-Weighted Citation Impact
3.68

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Learning the syntax of plant assemblages

Tetiana Dziuba, Michele De Sanctis, Juan Antonio Campos, Domas Uogintas et al.
2 citations
Nature Plants
Species Distribution and Climate Change
3.68
article

Learning the syntax of plant assemblages

Tetiana Dziuba, Michele De Sanctis, Juan Antonio Campos, Domas Uogintas, Jesper Erenskjold Moeslund, Maximilien Servajean, Jozef Šibík, Alexis Joly, Ute Jandt, Andraž Čarni, Thomas Wohlgemuth, Gianmaria Bonari, Olivier Argagnon, Florian Jansen, Emmanuel Garbolino, Zvjezdana Stančić, Remigiusz Pielech, Jürgen Dengler, Milan Chytrý, César Leblanc, Renata Ćušterevska, Svetlana Aćić, Wilfried Thuiller, Jonathan Lenoir, Aaron Pérez‐Haase, Idoia Biurrun, Pierre Bonnet, Helge Bruelheide
article en
2 citations

Abstract

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.

Nature PlantsVol. 11(10)
University of Siena (IT), Jagiellonian University (PL), Centre National de la Recherche Scientifique (FR), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (FR), Institut national de recherche en sciences et technologies du numérique (FR), National Academy of Sciences of Ukraine (UA), University of the Basque Country (ES), Slovenian Academy of Sciences and Arts (SI), University of Zagreb (HR), University of Nova Gorica (SI), Université de Montpellier (FR), Aarhus University (DK), Slovak Academy of Sciences (SK), Masaryk University (CZ), Swiss Federal Institute for Forest, Snow and Landscape Research (CH), German Centre for Integrative Biodiversity Research (DE), University of Belgrade (RS), Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement (FR), Université Paul-Valéry Montpellier (FR), Laboratoire d'Informatique, de Robotique et de Microélectronique de Montpellier (FR), Ecologie et Dynamique des Systèmes Anthropisés (FR), UMR Botanique et Modélisation de l’Architecture des Plantes et des végétations (FR), Nature Research Centre (LT), Institut de Biologia Evolutiva (ES), Institut Agro Montpelier (FR), Laboratoire d'Écologie Alpine (FR), M.G. Kholodny Institute of Botany (UA), Bibliothèque Nationale de France (FR), Institut de Recherche pour le Développement (FR), Conservatoire Botanique National Méditerranéen de Porquerolles (FR), Research Centre of the Slovenian Academy of Sciences and Arts, University of Rostock (DE), University of Bayreuth (DE), Martin Luther University Halle-Wittenberg (DE), École Nationale Supérieure des Mines de Paris (FR), Université Savoie Mont Blanc (FR), Universitat de Barcelona (ES), Ss. Cyril and Methodius University in Skopje (MK), ZHAW Zurich University of Applied Sciences (CH), Sapienza University of Rome (IT), Université Grenoble Alpes (FR)
European Commission, HORIZON EUROPE Framework Programme
Openalex Percentile: Top 7%
Species Distribution and Climate Change
3.68
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.