Published in Nature Plants, 2025
This paper (currently in review) proposes a novel approach inspired by advances in large language models to learn the “syntax” of abundance-ordered plant species sequences in communities.
Recommended citation: Leblanc, C., Bonnet, P., Servajean, M., Thuiller, W., Chytrý, M., Aćić, S., ... & Joly, A. (2025). Learning the syntax of plant assemblages.
Download Paper
Published in Applications in Plant Sciences, 2024
This paper explores the feasibility of using large language models to automatically extract morphological traits of plants from unstructured online text, presenting a novel approach that achieves high accuracy in trait identification.
Recommended citation: Marcos, D., van de Vlasakker, R., Athanasiadis, I. N., Bonnet, P., Goëau, H., Joly, A., ... & Panousis, K. P. (2024). Fully automatic extraction of morphological traits from the web: Utopia or reality?. Applications in Plant Sciences, e70005.
Download Paper
Published in Applied Vegetation Science, 2024
This paper introduces a novel deep-learning framework designed to improve habitat identification based on species composition, providing significant advancements over traditional expert systems.
Recommended citation: Leblanc, C., Bonnet, P., Servajean, M., Chytrý, M., Aćić, S., Argagnon, O., ... & Joly, A. (2024). A deep‐learning framework for enhancing habitat identification based on species composition. Applied Vegetation Science, 27(3), e12802.
Download Paper
Published in Conference on Computer Vision and Pattern Recognition, 2025
This paper describes a cascading multimodal pipeline for high-resolution biodiversity mapping across Europe, integrating species distribution modeling, biodiversity indicators, and habitat classification.
Recommended citation: Leblanc, C., Picek, L., Palard, R., Deneu, B., Servajean, M., Bonnet, P., & Joly, A. (2025). Mapping biodiversity at very-high resolution in Europe. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 2349-2358).
Download Paper
Published in Conference on Neural Information Processing Systems, 2024
This paper presents GeoPlant, a novel European-scale dataset designed to advance species distribution modeling by integrating 5M Presence-Only records, 90k Presence-Absence surveys, environmental rasters, and high-resolution satellite imagery to predict over 10,000 plant species.
Recommended citation: Picek, L., Botella, C., Servajean, M., Leblanc, C., Palard, R., Larcher, T., ... & Joly, A. (2024, December). GeoPlant: Spatial Plant Species Prediction Dataset. In NEURIPS 2024.
Download Paper
Published in Conference and Labs of the Evaluation Forum, 2022
This paper presents an approach to species distribution modeling using convolutional neural networks, integrating aerial imagery and environmental data to predict species presence across diverse geographical locations.
Recommended citation: Leblanc, C., Joly, A., Lorieul, T., Servajean, M., & Bonnet, P. (2022, September). Species Distribution Modeling based on aerial images and environmental features with Convolutional Neural Networks. In CLEF (Working Notes) (pp. 2123-2150).
Download Paper