Learning the syntax of plant assemblages

J 2025

Learning the syntax of plant assemblages

LEBLANC, Cesar; Pierre BONNET; Maximilien SERVAJEAN; Wilfried THUILLER; Milan CHYTRÝ et. al.

Základní údaje

Originální název

Learning the syntax of plant assemblages

Autoři

Vydání

Nature Plants, LONDON, NATURE PORTFOLIO, 2025, 2055-026X

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10611 Plant sciences, botany

Stát vydavatele

Německo

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL, URL

Impakt faktor

Impact factor: 13.600 v roce 2024

Organizační jednotka

Přírodovědecká fakulta

DOI

https://doi.org/10.1038/s41477-025-02105-7

UT WoS

001591921900001

EID Scopus

2-s2.0-105018760144

Klíčová slova anglicky

Biodiversity; Conservation of Natural Resources; Ecosystem; Plants

Štítky

14314020, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 7. 1. 2026 17:45, Mgr. Marie Novosadová Šípková, DiS.

Anotace

V originále

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.

Citovat

LEBLANC, Cesar; Pierre BONNET; Maximilien SERVAJEAN; Wilfried THUILLER; Milan CHYTRÝ; Svetlana ACIC; Olivier ARGAGNON; Idoia BIURRUN; Gianmaria BONARI; Helge BRUELHEIDE; Juan Antonio CAMPOS; Andraz CARNI; Renata CUSTEREVSKA; De Sanctis MICHELE; Jurgen DENGLER; Tetiana DZIUBA; Emmanuel GARBOLINO; Ute JANDT; Florian JANSEN; Jonathan LENOIR; Jesper Erenskjold MOESLUND; Aaron PEREZ-HAASE; Remigiusz PIELECH; Jozef SIBIK; Zvjezdana STANCIC; Domas UOGINTAS; Thomas WOHLGEMUTH a Alexis JOLY. Learning the syntax of plant assemblages. Nature Plants. LONDON: NATURE PORTFOLIO, 2025, roč. 11, č. 10, s. 2026-2040, 18 s. ISSN 2055-026X. Dostupné z: https://doi.org/10.1038/s41477-025-02105-7.

@article{2542980,
   author = {Leblanc, Cesar and Bonnet, Pierre and Servajean, Maximilien and Thuiller, Wilfried and Chytrý, Milan and Acic, Svetlana and Argagnon, Olivier and Biurrun, Idoia and Bonari, Gianmaria and Bruelheide, Helge and Campos, Juan Antonio and Carni, Andraz and Custerevska, Renata and Michele, De Sanctis and Dengler, Jurgen and Dziuba, Tetiana and Garbolino, Emmanuel and Jandt, Ute and Jansen, Florian and Lenoir, Jonathan and Moeslund, Jesper Erenskjold and PerezandHaase, Aaron and Pielech, Remigiusz and Sibik, Jozef and Stancic, Zvjezdana and Uogintas, Domas and Wohlgemuth, Thomas and Joly, Alexis},
   article_location = {LONDON},
   article_number = {10},
   doi = {https://doi.org/10.1038/s41477-025-02105-7},
   keywords = {Biodiversity; Conservation of Natural Resources; Ecosystem; Plants},
   language = {eng},
   issn = {2055-026X},
   journal = {Nature Plants},
   title = {Learning the syntax of plant assemblages},
   url = {https://doi.org/10.58060/QR4B-G979},
   volume = {11},
   year = {2025}
}

TY  - JOUR
ID  - 2542980
AU  - Leblanc, Cesar - Bonnet, Pierre - Servajean, Maximilien - Thuiller, Wilfried - Chytrý, Milan - Acic, Svetlana - Argagnon, Olivier - Biurrun, Idoia - Bonari, Gianmaria - Bruelheide, Helge - Campos, Juan Antonio - Carni, Andraz - Custerevska, Renata - Michele, De Sanctis - Dengler, Jurgen - Dziuba, Tetiana - Garbolino, Emmanuel - Jandt, Ute - Jansen, Florian - Lenoir, Jonathan - Moeslund, Jesper Erenskjold - Perez-Haase, Aaron - Pielech, Remigiusz - Sibik, Jozef - Stancic, Zvjezdana - Uogintas, Domas - Wohlgemuth, Thomas - Joly, Alexis
PY  - 2025
TI  - Learning the syntax of plant assemblages
JF  - Nature Plants
VL  - 11
IS  - 10
SP  - 2026-2040
EP  - 2026-2040
PB  - NATURE PORTFOLIO
SN  - 2055026X
KW  - Biodiversity
KW  - Conservation of Natural Resources
KW  - Ecosystem
KW  - Plants
UR  - https://doi.org/10.58060/QR4B-G979
N2  - 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.
ER  -

LEBLANC, Cesar; Pierre BONNET; Maximilien SERVAJEAN; Wilfried THUILLER; Milan CHYTRÝ; Svetlana ACIC; Olivier ARGAGNON; Idoia BIURRUN; Gianmaria BONARI; Helge BRUELHEIDE; Juan Antonio CAMPOS; Andraz CARNI; Renata CUSTEREVSKA; De Sanctis MICHELE; Jurgen DENGLER; Tetiana DZIUBA; Emmanuel GARBOLINO; Ute JANDT; Florian JANSEN; Jonathan LENOIR; Jesper Erenskjold MOESLUND; Aaron PEREZ-HAASE; Remigiusz PIELECH; Jozef SIBIK; Zvjezdana STANCIC; Domas UOGINTAS; Thomas WOHLGEMUTH a Alexis JOLY. Learning the syntax of plant assemblages. \textit{Nature Plants}. LONDON: NATURE PORTFOLIO, 2025, roč.~11, č.~10, s.~2026-2040, 18 s. ISSN~2055-026X. Dostupné z: https://doi.org/10.1038/s41477-025-02105-7.

Přehled o publikaci