GeoPl@ntNet: A Platform for Exploring Essential Biodiversity Variables

Alexis Joly; C\'esar Leblanc; Lukas Picek; Maximilien Servajean; Pierre Bonnet; R\'emi Palard

arxiv: 2511.13790 · v2 · submitted 2025-11-16 · 🧬 q-bio.QM · cs.AI

GeoPl@ntNet: A Platform for Exploring Essential Biodiversity Variables

Lukas Picek , C\'esar Leblanc , Alexis Joly , Pierre Bonnet , R\'emi Palard , Maximilien Servajean This is my paper

Pith reviewed 2026-05-17 22:36 UTC · model grok-4.3

classification 🧬 q-bio.QM cs.AI

keywords biodiversityweb platformspecies mappingAI generated mapsEssential Biodiversity VariablesEuropeinteractive toolconservation data

0 comments

The pith

GeoPl@ntNet provides an interactive platform that makes high-resolution AI-generated maps of biodiversity variables accessible to everyone across Europe.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper presents GeoPl@ntNet as a web application that turns complex biodiversity data into easy-to-use interactive maps and reports. The tool covers species distributions, habitats, and indicators at a fine scale of 50 by 50 meters using artificial intelligence. Users can click on areas like cities or nature reserves to see local details and get summaries of protected or invasive species. Such accessibility could help more people understand and act on biodiversity issues in their regions.

Core claim

The central contribution is GeoPl@ntNet, an interactive web application for exploring Essential Biodiversity Variables. It features dynamic maps and fact sheets based on AI-generated data from convolutional neural networks and large language models. The platform supports selection of specific regions to view local species coverage and produces reports detailing protected, invasive, and endemic species counts.

What carries the argument

A cascading pipeline of convolutional neural networks and large language models that produces high-resolution maps of species distributions and biodiversity indicators.

Load-bearing premise

The maps generated by the AI pipeline accurately represent actual species distributions and biodiversity conditions in the real world.

What would settle it

A direct comparison of the platform's predicted species lists for a known area against independent field observations or existing verified datasets revealing large mismatches.

read the original abstract

This paper describes GeoPl@ntNet, an interactive web application designed to make Essential Biodiversity Variables accessible and understandable to everyone through dynamic maps and fact sheets. Its core purpose is to allow users to explore high-resolution AI-generated maps of species distributions, habitat types, and biodiversity indicators across Europe. These maps, developed through a cascading pipeline involving convolutional neural networks and large language models, provide an intuitive yet information-rich interface to better understand biodiversity, with resolutions as precise as 50x50 meters. The website also enables exploration of specific regions, allowing users to select areas of interest on the map (e.g., urban green spaces, protected areas, or riverbanks) to view local species and their coverage. Additionally, GeoPl@ntNet generates comprehensive reports for selected regions, including insights into the number of protected species, invasive species, and endemic species.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

GeoPl@ntNet describes a usable web platform for 50m AI biodiversity maps but offers no validation data to support accuracy claims.

read the letter

Hi, the core of this paper is a description of GeoPl@ntNet, an interactive site that runs a CNN-to-LLM pipeline to generate 50-by-50-meter maps of species distributions, habitats, and biodiversity indicators over Europe, then lets users pick regions and receive auto-generated reports on protected, invasive, or endemic species counts. The work shows a complete, deployed system that turns model outputs into something non-experts can actually navigate and query. That practical packaging is the main contribution; similar visualization efforts exist, but the specific combination of fine-scale cascading models, area selection, and report generation appears new as an integrated platform. The write-up is straightforward about the pipeline stages and interface choices, which makes the engineering steps easy to follow. The clear limitation is the lack of any performance numbers, held-out tests, or comparisons against field data or national monitoring sets. The text explains what the maps are supposed to show but supplies no error rates, confusion matrices, or spatial accuracy checks at the stated resolution, so the claim that users are exploring reliable Essential Biodiversity Variables stays untested. This paper would mainly interest people building or using biodiversity data tools, conservation planners, or educators who need quick regional overviews rather than readers hunting for new algorithms or ecological theory. It is a systems paper, not a methods or results paper, so its value is in the implementation details. I would send it for peer review in an applications or informatics venue, but only after the authors add at least basic validation evidence so referees can judge whether the maps are fit for the intended uses.

Referee Report

1 major / 1 minor

Summary. The manuscript describes GeoPl@ntNet, an interactive web application designed to make Essential Biodiversity Variables accessible through dynamic maps and fact sheets. Its core is a cascading CNN-LLM pipeline that generates maps of species distributions, habitat types, and biodiversity indicators across Europe at resolutions as fine as 50x50 meters; the platform supports region selection and automated reports on protected, invasive, and endemic species.

Significance. If the generated maps prove accurate, the platform could meaningfully improve public and scientific access to high-resolution EBV data by combining interactive visualization with region-specific reporting. The absence of any quantitative validation, however, prevents assessment of whether the claimed resolution and reliability are achieved.

major comments (1)

[Abstract] Abstract: the description of the AI-generated maps at 50x50 m resolution supplies no performance metrics, held-out validation against field plots or national monitoring programs, or error analysis, leaving the central claim that users can explore reliable Essential Biodiversity Variables unsupported.

minor comments (1)

The manuscript would benefit from explicit statements of the specific CNN architectures, LLM models, training datasets, and any post-processing steps used in the cascading pipeline.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback highlighting the need for clearer validation details in the abstract. We address this concern directly below and will revise the manuscript accordingly.

read point-by-point responses

Referee: [Abstract] Abstract: the description of the AI-generated maps at 50x50 m resolution supplies no performance metrics, held-out validation against field plots or national monitoring programs, or error analysis, leaving the central claim that users can explore reliable Essential Biodiversity Variables unsupported.

Authors: We agree that the abstract does not provide performance metrics, held-out validation, or error analysis for the 50 m resolution maps. The manuscript primarily describes the GeoPl@ntNet platform, its cascading CNN-LLM pipeline, interactive features, and region-specific reporting capabilities, drawing on established models for species distribution and habitat mapping rather than presenting new empirical validation. To address this, we will revise the abstract to explicitly note the reliance on pre-existing model outputs and their associated uncertainties, and we will add a dedicated limitations section discussing the absence of fresh field-plot validation against national monitoring programs. This revision will better contextualize the platform's role in facilitating exploration of EBVs while acknowledging that reliability depends on the accuracy of the underlying AI components. revision: yes

Circularity Check

0 steps flagged

No circularity: purely descriptive platform paper with no derivations

full rationale

The paper is a descriptive account of the GeoPl@ntNet web application, its interface, and the high-level cascading CNN+LLM pipeline used to generate the maps. No equations, fitted parameters, predictions, uniqueness theorems, or ansatzes appear in the text. Claims about map resolution and functionality are presented as direct outcomes of the implemented system rather than derived quantities that reduce to their own inputs. The manuscript contains no load-bearing self-citations or self-definitional steps, making the description self-contained.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a software platform description paper with no mathematical derivations, fitted parameters, or new theoretical entities introduced.

pith-pipeline@v0.9.0 · 5465 in / 984 out tokens · 23685 ms · 2026-05-17T22:36:16.089178+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/RealityFromDistinction reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

These maps, developed through a cascading pipeline involving convolutional neural networks and large language models, provide an intuitive yet information-rich interface to better understand biodiversity, with resolutions as precise as 50×50 meters.
IndisputableMonolith/Foundation/AlexanderDuality alexander_duality_circle_linking unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

We use a multimodal ensemble... three ResNet-like encoders... Pl@ntBERT... multi-class classification into EUNIS habitat types

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

31 extracted references · 31 canonical work pages

[1]

R. A. Barber, S. G. Ball, R. K. Morris, and F. Gilbert. Target-group backgrounds prove effective at correcting sampling bias in maxent mod- els.Diversity and Distributions, 28(1):128–141, 2022

work page 2022
[2]

Bellard, C

C. Bellard, C. Bertelsmeier, P. Leadley, W. Thuiller, and F. Courchamp. Impacts of climate change on the future of biodiversity.Ecology letters, 15(4):365–377, 2012

work page 2012
[3]

Bonnet, A

P. Bonnet, A. Affouard, J.-C. Lombardo, M. Chouet, H. Gresse, V . He- quet, R. Palard, M. Fromholtz, V . Espitalier, H. Goëau, et al. Syner- gizing digital, biological, and participatory sciences for global plant species identification: enabling access to a worldwide identification ser- vice.Biodiversity Information Science and Standards, 7, 2023

work page 2023
[4]

Botella, B

C. Botella, B. Deneu, D. Marcos, M. Servajean, J. Estopinan, T. Larcher, C. Leblanc, P. Bonnet, and A. Joly. The geolifeclef 2023 dataset to eval- uate plant species distribution models at high spatial resolution across europe.arXiv preprint arXiv:2308.05121, 2023

work page arXiv 2023
[5]

Botella, B

C. Botella, B. Deneu, D. Marcos, M. Servajean, T. Larcher, C. Leblanc, J. Estopinan, P. Bonnet, and A. Joly. Overview of geolifeclef 2023: Species composition prediction with high spatial resolution at continen- tal scale using remote sensing. InCLEF 2023 Working Notes-24th Con- ference and Labs of the Evaluation Forum, volume 3497, pages 1954– 1971, 2023

work page 2023
[6]

Braun-Blanquet

J. Braun-Blanquet. Plant sociology. the study of plant communities. 1932

work page 1932
[7]

S. H. Butchart, M. Walpole, B. Collen, A. Van Strien, J. P. Scharlemann, R. E. Almond, J. E. Baillie, B. Bomhard, C. Brown, J. Bruno, et al. Global biodiversity: indicators of recent declines.Science, 328(5982): 1164–1168, 2010

work page 2010
[8]

Chytr `y, S

M. Chytr `y, S. M. Hennekens, B. Jiménez-Alfaro, I. Knollová, J. Den- gler, F. Jansen, F. Landucci, J. H. Schaminée, S. A´ci´c, E. Agrillo, et al. European vegetation archive (eva): an integrated database of european vegetation plots.Applied vegetation science, 19(1):173–180, 2016

work page 2016
[9]

Chytr `y, L

M. Chytr `y, L. Tich`y, S. M. Hennekens, I. Knollová, J. A. Janssen, J. S. Rodwell, T. Peterka, C. Marcenò, F. Landucci, et al. Eunis habitat clas- sification: Expert system, characteristic species combinations and dis- tribution maps of european habitats.Applied Vegetation Science, 23(4): 648–675, 2020

work page 2020
[10]

E. Cole, G. Van Horn, C. Lange, A. Shepard, P. Leary, P. Perona, S. Loarie, and O. Mac Aodha. Spatial implicit neural representations for global-scale species mapping. InInternational conference on ma- chine learning, pages 6320–6342. PMLR, 2023

work page 2023
[11]

Contini, V

M. Contini, V . Illien, M. Julien, M. Ravitchandirane, V . Russias, A. Lazennec, T. Chevrier, C. L. Rintz, L. Carpentier, P. Gogendeau, et al. Seatizen atlas: a collaborative dataset of underwater and aerial marine imagery.Scientific Data, 12(1):67, 2025

work page 2025
[12]

Deneu, M

B. Deneu, M. Servajean, P. Bonnet, C. Botella, F. Munoz, and A. Joly. Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment.PLoS computa- tional biology, 17(4), 2021

work page 2021
[13]

Elith and J

J. Elith and J. R. Leathwick. Species distribution models: ecological explanation and prediction across space and time.Annual review of ecology, evolution, and systematics, 40(1):677–697, 2009

work page 2009
[14]

Estopinan, M

J. Estopinan, M. Servajean, P. Bonnet, A. Joly, and F. Munoz. Mapping global orchid assemblages with deep learning provides novel conserva- tion insights.Ecological Informatics, 81:102627, 2024

work page 2024
[15]

Fontana, G

M. Fontana, G. Zeni, and S. Vantini. Conformal prediction: a unified review of theory and new challenges.Bernoulli, 29(1):1–23, 2023

work page 2023
[16]

N. J. Gotelli and R. K. Colwell. Quantifying biodiversity: procedures and pitfalls in the measurement and comparison of species richness. Ecology letters, 4(4):379–391, 2001

work page 2001
[17]

Guisan, R

A. Guisan, R. Tingley, J. B. Baumgartner, I. Naujokaitis-Lewis, P. R. Sutcliffe, A. I. Tulloch, T. J. Regan, L. Brotons, E. McDonald-Madden, C. Mantyka-Pringle, et al. Predicting species distributions for conser- vation decisions.Ecology letters, 16(12):1424–1435, 2013

work page 2013
[18]

K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016

work page 2016
[19]

A. Joly, C. Botella, L. Picek, S. Kahl, H. Goëau, B. Deneu, D. Marcos, J. Estopinan, C. Leblanc, T. Larcher, et al. Overview of lifeclef 2023: evaluation of ai models for the identification and prediction of birds, plants, snakes and fungi. InInternational Conference of the Cross- Language Evaluation Forum for European Languages, pages 416–439. Springer, 2023

work page 2023
[20]

A. Joly, L. Picek, S. Kahl, H. Goëau, V . Espitalier, C. Botella, B. Deneu, D. Marcos, J. Estopinan, C. Leblanc, et al. Lifeclef 2024 teaser: Chal- lenges on species distribution prediction and identification. InEuropean Conference on Information Retrieval, pages 19–27. Springer, 2024

work page 2024
[21]

A. Joly, L. Picek, S. Kahl, H. Goëau, V . Espitalier, C. Botella, D. Mar- cos, J. Estopinan, C. Leblanc, T. Larcher, et al. Overview of lifeclef 2024: Challenges on species distribution prediction and identification. InInternational Conference of the Cross-Language Evaluation Forum for European Languages, pages 183–207. Springer, 2024

work page 2024
[22]

A. Joly, L. Picek, S. Kahl, H. Goëau, L. Adam, C. Botella, M. Serva- jean, D. Marcos, C. Leblanc, T. Larcher, et al. Lifeclef 2025 teaser: Challenges on species presence prediction and identification, and indi- vidual animal identification. InEuropean Conference on Information Retrieval, pages 373–381. Springer, 2025

work page 2025
[23]

Leblanc, A

C. Leblanc, A. Joly, T. Lorieul, M. Servajean, and P. Bonnet. Species distribution modeling based on aerial images and environmental fea- tures with convolutional neural networks. InCLEF (Working Notes), pages 2123–2150, 2022

work page 2022
[24]

Leblanc, P

C. Leblanc, P. Bonnet, M. Servajean, M. Chytr `y, S. A ´ci´c, O. Ar- gagnon, A. Bergamini, I. Biurrun, G. Bonari, J. A. Campos, et al. A deep-learning framework for enhancing habitat identification based on species composition.Applied Vegetation Science, 27(3):e12802, 2024

work page 2024
[25]

Leblanc, P

C. Leblanc, P. Bonnet, M. Servajean, and A. Joly. Pl@ ntbert: leverag- ing large language models to enhance vegetation classification through species composition analysis. Università di Bologna, 2024

work page 2024
[26]

Leblanc, P

C. Leblanc, P. Bonnet, M. Servajean, W. Thuiller, M. Chytr `y, S. A ´ci´c, O. Argagnon, I. Biurrun, G. Bonari, H. Bruelheide, et al. Learning the syntax of plant assemblages. 2025

work page 2025
[27]

Leblanc, L

C. Leblanc, L. Picek, R. Palard, B. Deneu, M. Servajean, P. Bonnet, and A. Joly. Mapping biodiversity at very-high resolution in europe. InPro- ceedings of the Computer Vision and Pattern Recognition Conference, pages 2349–2358, 2025

work page 2025
[28]

Marcos, R

D. Marcos, R. van de Vlasakker, I. N. Athanasiadis, P. Bonnet, H. Goëau, A. Joly, W. D. Kissling, C. Leblanc, A. S. van Proosdij, and K. P. Panousis. Fully automatic extraction of morphological traits from the web: Utopia or reality?Applications in Plant Sciences, page e70005, 2025

work page 2025
[29]

S. J. Phillips, M. Dudík, J. Elith, C. H. Graham, A. Lehmann, J. Leath- wick, and S. Ferrier. Sample selection bias and presence-only distri- bution models: implications for background and pseudo-absence data. Ecological applications, 19(1):181–197, 2009

work page 2009
[30]

Picek, C

L. Picek, C. Botella, M. Servajean, C. Leblanc, R. Palard, T. Larcher, B. Deneu, D. Marcos, P. Bonnet, and a. joly. Geoplant: Spatial plant species prediction dataset. In A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang, editors,Advances in Neu- ral Information Processing Systems, volume 37, pages 126653–126676. Curran Ass...

work page 2024
[31]

Picek, C

L. Picek, C. Botella, M. Servajean, C. Leblanc, R. Palard, T. Larcher, B. Deneu, D. Marcos, J. Estopinan, P. Bonnet, et al. Overview of geo- lifeclef 2024: Species composition prediction with high spatial resolu- tion at continental scale using remote sensing. InCLEF 2024-Working Notes of the 25th Conference and Labs of the Evaluation Forum, volume 3740, ...

work page 2024

[1] [1]

R. A. Barber, S. G. Ball, R. K. Morris, and F. Gilbert. Target-group backgrounds prove effective at correcting sampling bias in maxent mod- els.Diversity and Distributions, 28(1):128–141, 2022

work page 2022

[2] [2]

Bellard, C

C. Bellard, C. Bertelsmeier, P. Leadley, W. Thuiller, and F. Courchamp. Impacts of climate change on the future of biodiversity.Ecology letters, 15(4):365–377, 2012

work page 2012

[3] [3]

Bonnet, A

P. Bonnet, A. Affouard, J.-C. Lombardo, M. Chouet, H. Gresse, V . He- quet, R. Palard, M. Fromholtz, V . Espitalier, H. Goëau, et al. Syner- gizing digital, biological, and participatory sciences for global plant species identification: enabling access to a worldwide identification ser- vice.Biodiversity Information Science and Standards, 7, 2023

work page 2023

[4] [4]

Botella, B

C. Botella, B. Deneu, D. Marcos, M. Servajean, J. Estopinan, T. Larcher, C. Leblanc, P. Bonnet, and A. Joly. The geolifeclef 2023 dataset to eval- uate plant species distribution models at high spatial resolution across europe.arXiv preprint arXiv:2308.05121, 2023

work page arXiv 2023

[5] [5]

Botella, B

C. Botella, B. Deneu, D. Marcos, M. Servajean, T. Larcher, C. Leblanc, J. Estopinan, P. Bonnet, and A. Joly. Overview of geolifeclef 2023: Species composition prediction with high spatial resolution at continen- tal scale using remote sensing. InCLEF 2023 Working Notes-24th Con- ference and Labs of the Evaluation Forum, volume 3497, pages 1954– 1971, 2023

work page 2023

[6] [6]

Braun-Blanquet

J. Braun-Blanquet. Plant sociology. the study of plant communities. 1932

work page 1932

[7] [7]

S. H. Butchart, M. Walpole, B. Collen, A. Van Strien, J. P. Scharlemann, R. E. Almond, J. E. Baillie, B. Bomhard, C. Brown, J. Bruno, et al. Global biodiversity: indicators of recent declines.Science, 328(5982): 1164–1168, 2010

work page 2010

[8] [8]

Chytr `y, S

M. Chytr `y, S. M. Hennekens, B. Jiménez-Alfaro, I. Knollová, J. Den- gler, F. Jansen, F. Landucci, J. H. Schaminée, S. A´ci´c, E. Agrillo, et al. European vegetation archive (eva): an integrated database of european vegetation plots.Applied vegetation science, 19(1):173–180, 2016

work page 2016

[9] [9]

Chytr `y, L

M. Chytr `y, L. Tich`y, S. M. Hennekens, I. Knollová, J. A. Janssen, J. S. Rodwell, T. Peterka, C. Marcenò, F. Landucci, et al. Eunis habitat clas- sification: Expert system, characteristic species combinations and dis- tribution maps of european habitats.Applied Vegetation Science, 23(4): 648–675, 2020

work page 2020

[10] [10]

E. Cole, G. Van Horn, C. Lange, A. Shepard, P. Leary, P. Perona, S. Loarie, and O. Mac Aodha. Spatial implicit neural representations for global-scale species mapping. InInternational conference on ma- chine learning, pages 6320–6342. PMLR, 2023

work page 2023

[11] [11]

Contini, V

M. Contini, V . Illien, M. Julien, M. Ravitchandirane, V . Russias, A. Lazennec, T. Chevrier, C. L. Rintz, L. Carpentier, P. Gogendeau, et al. Seatizen atlas: a collaborative dataset of underwater and aerial marine imagery.Scientific Data, 12(1):67, 2025

work page 2025

[12] [12]

Deneu, M

B. Deneu, M. Servajean, P. Bonnet, C. Botella, F. Munoz, and A. Joly. Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment.PLoS computa- tional biology, 17(4), 2021

work page 2021

[13] [13]

Elith and J

J. Elith and J. R. Leathwick. Species distribution models: ecological explanation and prediction across space and time.Annual review of ecology, evolution, and systematics, 40(1):677–697, 2009

work page 2009

[14] [14]

Estopinan, M

J. Estopinan, M. Servajean, P. Bonnet, A. Joly, and F. Munoz. Mapping global orchid assemblages with deep learning provides novel conserva- tion insights.Ecological Informatics, 81:102627, 2024

work page 2024

[15] [15]

Fontana, G

M. Fontana, G. Zeni, and S. Vantini. Conformal prediction: a unified review of theory and new challenges.Bernoulli, 29(1):1–23, 2023

work page 2023

[16] [16]

N. J. Gotelli and R. K. Colwell. Quantifying biodiversity: procedures and pitfalls in the measurement and comparison of species richness. Ecology letters, 4(4):379–391, 2001

work page 2001

[17] [17]

Guisan, R

A. Guisan, R. Tingley, J. B. Baumgartner, I. Naujokaitis-Lewis, P. R. Sutcliffe, A. I. Tulloch, T. J. Regan, L. Brotons, E. McDonald-Madden, C. Mantyka-Pringle, et al. Predicting species distributions for conser- vation decisions.Ecology letters, 16(12):1424–1435, 2013

work page 2013

[18] [18]

K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016

work page 2016

[19] [19]

A. Joly, C. Botella, L. Picek, S. Kahl, H. Goëau, B. Deneu, D. Marcos, J. Estopinan, C. Leblanc, T. Larcher, et al. Overview of lifeclef 2023: evaluation of ai models for the identification and prediction of birds, plants, snakes and fungi. InInternational Conference of the Cross- Language Evaluation Forum for European Languages, pages 416–439. Springer, 2023

work page 2023

[20] [20]

A. Joly, L. Picek, S. Kahl, H. Goëau, V . Espitalier, C. Botella, B. Deneu, D. Marcos, J. Estopinan, C. Leblanc, et al. Lifeclef 2024 teaser: Chal- lenges on species distribution prediction and identification. InEuropean Conference on Information Retrieval, pages 19–27. Springer, 2024

work page 2024

[21] [21]

A. Joly, L. Picek, S. Kahl, H. Goëau, V . Espitalier, C. Botella, D. Mar- cos, J. Estopinan, C. Leblanc, T. Larcher, et al. Overview of lifeclef 2024: Challenges on species distribution prediction and identification. InInternational Conference of the Cross-Language Evaluation Forum for European Languages, pages 183–207. Springer, 2024

work page 2024

[22] [22]

A. Joly, L. Picek, S. Kahl, H. Goëau, L. Adam, C. Botella, M. Serva- jean, D. Marcos, C. Leblanc, T. Larcher, et al. Lifeclef 2025 teaser: Challenges on species presence prediction and identification, and indi- vidual animal identification. InEuropean Conference on Information Retrieval, pages 373–381. Springer, 2025

work page 2025

[23] [23]

Leblanc, A

C. Leblanc, A. Joly, T. Lorieul, M. Servajean, and P. Bonnet. Species distribution modeling based on aerial images and environmental fea- tures with convolutional neural networks. InCLEF (Working Notes), pages 2123–2150, 2022

work page 2022

[24] [24]

Leblanc, P

C. Leblanc, P. Bonnet, M. Servajean, M. Chytr `y, S. A ´ci´c, O. Ar- gagnon, A. Bergamini, I. Biurrun, G. Bonari, J. A. Campos, et al. A deep-learning framework for enhancing habitat identification based on species composition.Applied Vegetation Science, 27(3):e12802, 2024

work page 2024

[25] [25]

Leblanc, P

C. Leblanc, P. Bonnet, M. Servajean, and A. Joly. Pl@ ntbert: leverag- ing large language models to enhance vegetation classification through species composition analysis. Università di Bologna, 2024

work page 2024

[26] [26]

Leblanc, P

C. Leblanc, P. Bonnet, M. Servajean, W. Thuiller, M. Chytr `y, S. A ´ci´c, O. Argagnon, I. Biurrun, G. Bonari, H. Bruelheide, et al. Learning the syntax of plant assemblages. 2025

work page 2025

[27] [27]

Leblanc, L

C. Leblanc, L. Picek, R. Palard, B. Deneu, M. Servajean, P. Bonnet, and A. Joly. Mapping biodiversity at very-high resolution in europe. InPro- ceedings of the Computer Vision and Pattern Recognition Conference, pages 2349–2358, 2025

work page 2025

[28] [28]

Marcos, R

D. Marcos, R. van de Vlasakker, I. N. Athanasiadis, P. Bonnet, H. Goëau, A. Joly, W. D. Kissling, C. Leblanc, A. S. van Proosdij, and K. P. Panousis. Fully automatic extraction of morphological traits from the web: Utopia or reality?Applications in Plant Sciences, page e70005, 2025

work page 2025

[29] [29]

S. J. Phillips, M. Dudík, J. Elith, C. H. Graham, A. Lehmann, J. Leath- wick, and S. Ferrier. Sample selection bias and presence-only distri- bution models: implications for background and pseudo-absence data. Ecological applications, 19(1):181–197, 2009

work page 2009

[30] [30]

Picek, C

L. Picek, C. Botella, M. Servajean, C. Leblanc, R. Palard, T. Larcher, B. Deneu, D. Marcos, P. Bonnet, and a. joly. Geoplant: Spatial plant species prediction dataset. In A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang, editors,Advances in Neu- ral Information Processing Systems, volume 37, pages 126653–126676. Curran Ass...

work page 2024

[31] [31]

Picek, C

L. Picek, C. Botella, M. Servajean, C. Leblanc, R. Palard, T. Larcher, B. Deneu, D. Marcos, J. Estopinan, P. Bonnet, et al. Overview of geo- lifeclef 2024: Species composition prediction with high spatial resolu- tion at continental scale using remote sensing. InCLEF 2024-Working Notes of the 25th Conference and Labs of the Evaluation Forum, volume 3740, ...

work page 2024