Citizen science & machine learning for plant Identification: challenges from Pl@ntNet



Joseph Salmon

IMAG, Univ Montpellier, CNRS, Inria, Montpellier, France

Consortium Pl@ntnet

Plant importance

The “weight” of plants on Earth

Biomass on earth (Bar-On et al., 2018)

The services they provide to us

  • Provisioning: Food, Medicines …

Honey bee John Severns
Public domain

  • Supporting: Photosynthesis, soil formation, water cycle, …

Leaves on the ground, in a forest Malene Thyssen
Public domain

Leaves on the ground, in a forest Lynette Schimming − EOL
CC-BY-NC

  • Regulating: Pollination, Climate, …

Leaves on the ground, in a forest fuerst.ernst
CC-BY-SA

  • Cultural: Places for recreation, wonder, …

Pl@ntNet insight



Tree with roots

Pl@ntNet: ML for citizen science

A machine learning-driven citizen science platform for mobile plant identification





Pl@ntNet & Cooperative Learning

User centric visualization

123456789PositionencodingLinearProjectionPatchs16x16...++MLPNormalizationNormalizationMulti-headattention12xSoftmax scores(87 572 species)Similarity Search(k-nearest neighbors)Inference (DinoV2)Conformal PredictionUser's feedbackSpecies #1Species #2Species #3Image (query)Embedding(dim=768)User(picture a plant)Send requestShow closestimagesper speciesShow species names and scoresGet species list...Species #1Species #2Eryngium maritimum L. Eryngium campestre L. Species #3...Citizen CP goal: Reliable plant ID, w. uncertainty controlled

Scientific challenges

A multidisciplinary collaboration:

  • Statistics / Machine Learning researchers
  • Ecologists
  • Engineers
  • Citizen contributors

Addressing open challenges:

  • Theoretical foundations
  • Methodological advances
  • Large-scale computational needs
  • Cross-disciplinary integration

The current Pl@ntNet Team

Alexis Joly
Primary investigator, INRIA
Web site

Pierre Bonnet
Primary investigator, CIRAD
ResearchGate

Jean-Christophe Lombardo
Software Manager, IA engineer, INRIA
LinkedIn

Hervé Goëau
Researcher, CIRAD
ResearchGate

Christophe Botella
Researcher, INRIA
ResearchGate

Joseph Salmon
Researcher, INRIA
Website

Benjamin Bourel
Researcher, INRIA
Website

Lee Sue Han
Senior Lecturer, Swinburne University of Technology Sarawak Campus
Scholar

Diego Marcos
Researcher, INRIA
ResearchGate

Vanessa Hequet
Botanist, IRD
LinkedIn

Murielle Simo-Droissart
Botanist, IRD
ResearchGate

Jean-Marc Sadaillan
Project manager, INRAE
LinkedIn

Anna Valduriez
Research Engineer in Citizen Science, INRIA
LinkedIn

Antoine Affouard
Backend & DB engineer, INRIA
LinkedIn

Mathias Chouet
Backend engineer, CIRAD
GitHub

Hugo Gresse
Mobile engineer, INRIA
GitHub | LinkedIn

Thomas Paillot
Front engineer, INRIA
LinkedIn

Rémi Palard
Geo & Fullstack engineer, CIRAD
LinkedIn

Théo Simoes
Backend engineer, INRAE
LinkedIn

Ilyass Moummad
Post-doc, INRIA
Personal website | Google Scholar

Théo Larcher
PhD candidate, INRIA
LinkedIn

Giulio Martellucci
PhD candidate, INRIA
LinkedIn

Raphaël Benerradi
PhD candidate, INRIA
LinkedIn

Pablo Ubilla pavez
PhD candidate, INRIA
Personal website

Romane Dubois
PhD candidate, INRAE
LinkedIn

Franck Cabot
PhD candidate, CIRAD
LinkedIn

Bronislav Abadie
PhD candidate, Univ. Montpellier/Inria
LinkedIn

Alex Alì Maleknia
PhD candidate, CNRS / Inria
Website

Some personal contributions


  • Pl@ntNet-300K (Garcin et al., 2021): Creation and release of a large-scale dataset sharing the same property (Long Tail!) as Pl@ntNet; available for the community to improve learning systems


  • Prediction uncertainty quantification
    with long tail data (Ding et al., 2026): providing prediction sets with statistical guarantees with Conformal Prediction


  • Learning & crowd-sourced data (Lefort et al., 2024; Lefort et al., 2025): How to leverage multiple labels per image to improve the model? Need to assert quality: the workers, the images/labels, the model, etc.


Pl@ntNet,
challenging standard ML assumptions Tree with roots

Pl@ntNet classification challenges



Multi-class supervised learning pushed to the limit:



Massive scale

Millions of images across thousands of species (classes)

Structured labels

A hierarchical taxonomy, with visually similar species prone to confusion

Biased data

A citizen-science dataset, unevenly sampled across species and regions

Pl@ntNet : a digital commons project


9 705 222

Users with accounts

3X more users without accounts

87 572

(WCVP) Species with photos

out of 404 176

1 543 469 073

Queries

unlabeled images : without species

33 630 691

Observations

labeled images: with species

Diversity of plants Rkitko
(Wikimedia Commons)

436 TB

Storage

Source: Pl@ntNet stats

WCVP: World Checklist of Vascular Plants database.

Bias in Citizen Science Data





Tree with roots

Geographic bias (Pl@ntNet observations)

Biases lead to long tail distributions

Selection bias

What gets photographed is not random.

Easy access

Visible species

Easy identification

Temporal bias

What we see depends on when we look.

Season

Flowering

Plant appearance

Subjective bias

Observations can reflect observers own choices.

Personal preferences

Rare species

Endangered species

…


more observations ≠ a more representative dataset

The Pl@ntNet-300K dataset



Tree with roots

Datafication & data sharing


Popular labeled datasets limitations:

  • structure of labels too simplistic (CIFAR-10, CIFAR-100)
  • tasks too easy to discriminate / low labels confusion (MNIST)
  • too well-balanced, same number of images per class (Imagenet)
  • duplicate, low-quality, irrelevant images (Recht et al., 2019)


Pl@ntNet-300K: a curated, shareable subset of Pl@ntNet for frictionless reproducibility (Donoho, 2024)

  • Advance plant identification research with real-world biodiversity data
  • Engage the ML community with meaningful challenges beyond synthetic benchmarks

Pl@ntNet-300K: Long tail visualization


Y-Scale:
Species Preview

Details on Pl@ntNet-300K


Goal: Provide a real life scenario for supervised learning, with multi-class and long-tail label distribution


Pl@ntNet-300K v1.0 characteristics:


  • 306,146 color images
  • Size: 32 GB
  • Labels: 1 000+ species
  • Required 2 000 000 volunteers

Neurips (Datasets and Benchmarks track) paper

(Garcin et al., 2021)


Zenodo, 1 click download

https://zenodo.org/record/5645731


Code to train models

https://github.com/plantnet/PlantNet-300K


2026 Update: Pl@ntNet-300K v2.0 on Zenodo

Take home message

Future work

  • Handling label hierarchy
  • Human–computer interaction / performative learning / model collapse
  • Improve robustness to adversarial users
  • Improve label agregation, leverage gamification e.g., theplantgame.com

Dataset release:

Code release:

References

References

Bar-On, Y. M., Phillips, R., & Milo, R. (2018). The biomass distribution on earth. Proceedings of the National Academy of Sciences, 115(25), 6506–6511.
Ding, T., Fermanian, J.-B., & Salmon, J. (2026). Conformal Prediction for Long-Tailed Classification. ICLR.
Donoho, D. (2024). Data science at the singularity. Harvard Data Science Review, 6(1).
Garcin, C., Joly, A., Bonnet, P., Affouard, A., Lombardo, J.-C., Chouet, M., Servajean, M., Lorieul, T., & Salmon, J. (2021). Pl@ntNet-300K: A plant image dataset with high label ambiguity and a long-tailed distribution. Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks.
Lefort, T., Affouard, A., Charlier, B., Lombardo, J.-C., Chouet, M., Goëau, H., Salmon, J., Bonnet, P., & Joly, A. (2025). Cooperative learning of pl@ntNet’s artificial intelligence algorithm: How does it work and how can we improve it? Methods in Ecology and Evolution.
Lefort, T., Charlier, B., Joly, A., & Salmon, J. (2024). Identify ambiguous tasks combining crowdsourced labels by weighting areas under the margin. TMLR.
Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019). Do imagenet classifiers generalize to imagenet? ICML, 5389–5400.