CoChat
Sign Up
Cited by 10Ecology and Vegetation Dynamics StudiesSpecies Distribution and Climate ChangeBotany and Plant Ecology Studies

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Learning the syntax of plant assemblages

Open access
Leblanc, César, Bonnet, Pierre, Servajean, Maximilien, Thuiller, Wilfried, Chytrý, Milan, Aćić, Svetlana, Argagnon, Olivier, Biurrun, Idoia, Bonari, Gianmaria, Bruelheide, Helge, Campos, Juan Antonio, Čarni, Andraž, Ćušterevska, Renata, De Sanctis, Michele, Dengler, Jürgen, Dziuba, Tetiana, Garbolino, Emmanuel, Jandt, Ute, Jansen, Florian, Lenoir, Jonathan, Moeslund, Jesper Erenskjold, Pérez-Haase, Aaron, Pielech, Remigiusz, Sibik, Jozef, Stančić, Zvjezdana, Uogintas, Domas, Wohlgemuth, Thomas, Joly, Alexis·2025·Nature Plants
DOI 10.1038/s41477-025-02105-7PMC PMC12537494

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41477-025-02105-7

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 66

  1. Tilman, D., Isbell, F. & Cowles, J. M. Biodiversity and ecosystem functioning. Annu. Rev. Ecol. Evol. Syst. 45, 471–493 (2014). · DOI · Paper page
  2. Callaway, R. M. et al. Positive Interactions and Interdependence in Plant Communities (Springer, 2007).
  3. Diamond, J. M. in Ecology and Evolution of Communities (eds Cody, M. L. & Diamond, J. M.) 342–444 (Harvard Univ. Press, 1975).
  4. Cody, M. L. & Diamond, J. M. (eds) Ecology and Evolution of Communities (Harvard Univ. Press, 1975).
  5. Thuiller, W., Pollock, L. J., Gueguen, M. & Münkemüller, T. From species distributions to meta-communities. Ecol. Lett. 18, 1321–1328 (2015). · DOI
  6. Münkemüller, T. et al. Dos and don’ts when inferring assembly rules from diversity patterns. Glob. Ecol. Biogeogr. 29, 1212–1229 (2020). · DOI
  7. Veech, J. A. A probabilistic model for analysing species co‐occurrence. Glob. Ecol. Biogeogr. 22, 252–260 (2013). · DOI
  8. Gotelli, N. J. & Ulrich, W. The empirical Bayes approach as a tool to identify non-random species associations. Oecologia 162, 463–477 (2010). · DOI
  9. Blanchet, F. G., Cazelles, K. & Gravel, D. Co-occurrence is not evidence of ecological interactions. Ecol. Lett. 23, 1050–1063 (2020). · DOI
  10. Bruelheide, H. et al. A checklist for using Beals’ index with incomplete floristic monitoring data: reply to Christensen et al. (2021): Problems in using Beals’ index to detect species trends in incomplete floristic monitoring data. Divers. Distrib. 27, 1328–1333 (2021). · DOI
  11. Garbolino, E., De Ruffray, P., Brisse, H. & Grandjouan, G. Probable flora: an expression mean of ecological gradients in France. C. R. Biol. 336, 73–81 (2013). · DOI
  12. Whittaker, R. H. Dominance and diversity in land plant communities: numerical relations of species express the importance of competition in community function and evolution. Science 147, 250–260 (1965). · DOI
  13. Keddy, P. A., & Shipley, B. Competitive hierarchies in herbaceous plant communities. Oikos 54, 234 (1989). · DOI
  14. Chytrý, M. et al. EUNIS habitat classification: expert system, characteristic species combinations and distribution maps of European habitats. Appl. Veg. Sci. 23, 648–675 (2020). · DOI
  15. Dinerstein, E. et al. An ecoregion-based approach to protecting half the terrestrial realm. BioScience 67, 534–545 (2017). · DOI · Paper page
  16. Noble, I. The role of expert systems in vegetation science. Vegetatio 69, 115–121 (1987). · DOI
  17. Hastie, T., Tibshirani, R., Friedman, J. H. & Friedman, J. H. The Elements of Statistical Learning: Data Mining, Inference, and Prediction 2nd edn (Springer, 2009). · DOI · Paper page
  18. De Cáceres, M. et al. A comparative framework for broad-scale plot-based vegetation classification. Appl. Veg. Sci. 18, 543–560 (2015). · DOI
  19. Deneu, B. et al. Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment. PLoS Comput. Biol. 17, e1008856 (2021). · DOI
  20. Černá, L. & Chytrý, M. Supervised classification of plant communities with artificial neural networks. J. Veg. Sci. 16, 407–414 (2005). · DOI
  21. Olden, J. D., Lawler, J. J. & Poff, N. L. Machine learning methods without tears: a primer for ecologists. Q. Rev. Biol. 83, 171–193 (2008). · DOI · Paper page
  22. Wisz, M. S. et al. The role of biotic interactions in shaping distributions and realised assemblages of species: implications for species distribution modelling. Biol. Rev. 88, 15–30 (2013). · DOI · Paper page
  23. Poggiato, G. et al. On the interpretations of joint modeling in community ecology. Trends Ecol. Evol. 36, 391–401 (2021). · DOI
  24. Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017).
  25. Marcos, D. et al. Fully automatic extraction of morphological traits from the web: utopia or reality? Appl. Plant Sci. 13, e70005 (2025). · DOI
  26. Lam, H. Y. I., Ong, X. E. & Mutwil, M. Large language models in plant biology. Trends Plant Sci. 29, 1145–1155 (2024). · DOI
  27. Devlin, J., Chang, M. W., Lee, K. & Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, volume 1 (long and short papers), 4171–4186 (Association for Computational Linguistics, 2019).
  28. Chytrý, M. et al. European Vegetation Archive (EVA): an integrated database of European vegetation plots. Appl. Veg. Sci. 19, 173–180 (2016). · DOI
  29. Pärtel, M., Szava-Kovats, R. & Zobel, M. Dark diversity: shedding light on absent species. Trends Ecol. Evol. 26, 124–128 (2011). · DOI
  30. Bebis, G. & Georgiopoulos, M. Feed-forward neural networks. IEEE Potentials 13, 27–31 (1994). · DOI
  31. Veech, J. A. The pairwise approach to analysing species co-occurrence. J. Biogeog. 41, 1029–1035 (2014). · DOI
  32. Murphy, K. P. Machine Learning: A Probabilistic Perspective (MIT Press, 2012).
  33. Morrison, L. W. Nonsampling error in vegetation surveys: understanding error types and recommendations for reducing their occurrence. Plant Ecol. 222, 577–586 (2021). · DOI
  34. Mucina, L. et al. Vegetation of Europe: hierarchical floristic classification system of vascular plant, bryophyte, lichen, and algal communities. Appl. Veg. Sci. 19, 3–264 (2016). · DOI
  35. Beltagy, I., Lo, K., & Cohan, A. SciBERT: A pretrained language model for scientific text. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 3613 (Association for Computational Linguistics, 2019). · DOI · Paper page
  36. Bruelheide, H. et al. splot—a new tool for global vegetation analyses. J. Veg. Sci. 30, 161–186 (2019). · DOI
  37. Carmona, C. P. & Pärtel, M. Estimating probabilistic site-specific species pools and dark diversity from co-occurrence data. Glob. Ecol. Biogeogr. 30, 316–326 (2021). · DOI
  38. Bruelheide, H. et al. Using incomplete floristic monitoring data from habitat mapping programmes to detect species trends. Divers. Distrib. 26, 782–794 (2020). · DOI
  39. Morin, P. J. Community Ecology (John Wiley & Sons, 2009).
  40. Kissling, W. D. et al. Towards novel approaches to modelling biotic interactions in multispecies assemblages at large spatial extents. J. Biogeogr. 39, 2163–2178 (2012). · DOI
  41. Ryo, M. et al. Explainable artificial intelligence enhances the ecological interpretability of black-box species distribution models. Ecography 44, 199–205 (2021). · DOI
  42. Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In International Conference on Machine Learning, 3319–3328 (PMLR, 2017).
  43. Tichý, L. & Chytrý, M. Probabilistic key for identifying vegetation types in the field: a new method and Android application. J. Veg. Sci. 30, 1035–1038 (2019). · DOI
  44. Chao, A. et al. An attribute-diversity approach to functional diversity, functional beta diversity, and related (dis) similarity measures. Ecol. Monogr. 89, e01343 (2019). · DOI
  45. Guisan, A. & Zimmermann, N. E. Predictive habitat distribution models in ecology. Ecol. Modell. 135, 147–186 (2000). · DOI · Paper page
  46. Joly, A. et al. Overview of LifeCLEF 2023: evaluation of AI models for the identification and prediction of birds, plants, snakes and fungi. In International Conference of the Cross-Language Evaluation Forum for European Languages, 416–439 (Springer, 2023). · DOI
  47. Joly, A. et al. Overview of LifeCLEF 2024: challenges on species distribution prediction and identification. In International Conference of the Cross-Language Evaluation Forum for European Languages, 183–207 (Springer, 2024). · DOI
  48. Botella, C. et al. Overview of GeoLifeCLEF 2023: species composition prediction with high spatial resolution at continental scale using remote sensing. In CLEF 2023 Working Notes 24th Conference and Labs of the Evaluation Forum Vol. 3497, 1954–1971 (CEUR, 2023).
  49. Picek, L. et al. Overview of GeoLifeCLEF 2024: species composition prediction with high spatial resolution at continental scale using remote sensing. In CLEF 2024 Working Notes of the 25th Conference and Labs of the Evaluation Forum. 186, 1966–1977 (CEUR, 2024).
  50. Bonnet, P. et al. Synergizing digital, biological, and participatory sciences for global plant species identification: enabling access to a worldwide identification service. Biodivers. Inf. Sci. Stand. 7 (2023). · DOI
  51. Contini, M. et al. Seatizen Atlas: a collaborative dataset of underwater and aerial marine imagery. Sci. Data 12, 67 (2025). · DOI
  52. Botella, C. et al. The GeoLifeCLEF 2023 dataset to evaluate plant species distribution models at high spatial resolution across Europe. Preprint at https://doi.org/10.48550/arXiv.2308.05121 (2023). · DOI
  53. Joly, A. et al. LifeCLEF 2024 teaser: challenges on species distribution prediction and identification. In European Conference on Information Retrieval, 19–27 (Springer, 2024). · DOI
  54. Joly, A. et al. LifeCLEF 2025 teaser: challenges on species presence prediction and identification, and individual animal identification. In European Conference on Information Retrieval, 373–381 (Springer, 2025). · DOI
  55. Leblanc, C. et al. Mapping biodiversity at very-high resolution in Europe. In Proc. Computer Vision and Pattern Recognition Conference, 2349–2358 (2025). · DOI
  56. Jansen, F. & Dengler, J. Plant names in vegetation databases—a neglected source of bias. J. Veg. Sci. 21, 1179–1186 (2010). · DOI
  57. Roberts, D. R. et al. Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography 40, 913–929 (2017). · DOI · Paper page
  58. Picek, L. et al. Geoplant: spatial plant species prediction dataset. Adv. Neural Inf. Process. Syst. 37, 126653–126676 (2024).
  59. Paszke, A. et al. Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, 8026–8037 (2019).
  60. Wolf, T. et al. Transformers: state-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (eds Liu, Q. & Schlangen, D.) 38–45 (Association for Computational Linguistics, 2020).
  61. Haykin, S. Neural Networks: A Comprehensive Foundation (Prentice Hall PTR, 1998).
  62. Ho, T. K. Random decision forests. In Proc. 3rd International Conference on Document Analysis and Recognition vol. 1, 278–282 (IEEE, 1995). · DOI
  63. Chen, T. & Guestrin, C. Xgboost: a scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794 (2016). · DOI · Paper page
  64. Arik, S. Ö. & Pfister, T. Tabnet: attentive interpretable tabular learning. Proc. AAAI Conf. Artif. Intell. 35, 6679–6687 (2021).
  65. Gorishniy, Y., Rubachev, I., Khrulkov, V. & Babenko, A. Revisiting deep learning models for tabular data. Adv. Neural Inf. Process. Syst. 34, 18932–18943 (2021).
  66. Leblanc, C. et al. A deep-learning framework for enhancing habitat identification based on species composition. Appl. Veg. Sci. 27, e12802 (2024). · DOI

Metadata

Authors
Leblanc, C., Bonnet, P., Servajean, M., Thuiller, W., Chytrý, M., Aćić, S., Argagnon, O., Biurrun, I., Bonari, G., Bruelheide, H., Campos, J. A., Čarni, A., Ćušterevska, R., De Sanctis, M., Dengler, J., Dziuba, T., Garbolino, E., Jandt, U., Jansen, F., Lenoir, J., Moeslund, J. E., Pérez-Haase, A., Pielech, R., Sibik, J., Stančić, Z., Uogintas, D., Wohlgemuth, T., & Joly, A.
Affiliations
  • Centre National de la Recherche Scientifique (FR)
  • Masaryk University (CZ)
  • University of Belgrade (RS)
  • Conservatoire botanique national méditerranéen (FR)
  • University of the Basque Country (ES)
  • University of Siena (IT)
  • German Centre for Integrative Biodiversity Research (DE)
  • University of Nova Gorica (SI)
  • Ss. Cyril and Methodius University in Skopje (MK)
  • University of Bayreuth (DE)
  • National Academy of Sciences of Ukraine (UA)
  • Institut Supérieur d'Ingénierie et Gestion de l'Environnement - ISIGE (FR)
  • University of Rostock (DE)
  • Aarhus University (DK)
  • Jagiellonian University (PL)
  • University of Zagreb (HR)
  • Nature Research Centre (LT)
  • Swiss Federal Institute for Forest, Snow and Landscape Research (CH)
Corresponding author
Leblanc, César
ORCID
Venue
Nature Plants
Publisher
Springer Science and Business Media LLC
Published
2025-10-13
Volume
11
Issue
10
Pages
2026-2040
ISSN
  • 2055-026X (ISSN-L)
  • 2055-0278
DOI
10.1038/s41477-025-02105-7
PMC
PMC12537494
OpenAlex
W4415101811
Cited by
10
References
1
Citations by year
2026: 9 · 2025: 1
FWCI
6.43
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Plants (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Jagiellonian University Repository (Jagiellonian University) (submittedVersion, cc-by-nc-nd)
  • HAL (submittedVersion, cc-by)
  • Agritrop (Cirad) (submittedVersion, cc-by)
  • DORA WSL (Swiss Federal Institute for Forest, Snow and Landscape Research) (submittedVersion, cc-by)
  • AgroSpace (University of Belgrade, Faculty of Agriculture) (submittedVersion, cc-by)
  • Scopus (Elsevier) (submittedVersion, other-oa)
  • Use Siena air (University of Siena) (submittedVersion, cc-by)
Funders
  • European Commission (101134954, 101060639, 101060693)
  • HORIZON EUROPE Framework Programme (101060693, 101060639, 101134954)
Topics
  • Physical Sciences › Environmental Science › Nature and Landscape Conservation › Ecology and Vegetation Dynamics Studies
  • Physical Sciences › Environmental Science › Ecological Modeling › Species Distribution and Climate Change
  • Life Sciences › Agricultural and Biological Sciences › Plant Science › Botany and Plant Ecology Studies
Keywords
plant assemblages, species co-occurrence, habitat classification, plant communities, large language models, biodiversity conservation, plant distribution
MeSH terms
Conservation of Natural Resources, Plants, Ecosystem, Biodiversity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review