Publications

Selected publications

• Botella, C., Joly, A., Bonnet, P., Monestiez, P., & Munoz, F. (2018). A Deep Learning Approach to Species Distribution Modelling. In Multimedia Tools and Applications for Environmental & Biodiversity Informatics (pp. 169-199). Springer, Cham.
  Main contribution: This work uses deep learning for spatialized species prediction (deepSDMs) for the first time, originating this research branch that is currently active internationally. The proposed approach solves the overfitting problem of these complex models by sharing the learning of a common vector embedding across multiple species (up to ~1000 plant species in metropolitan France) and demonstrates that this improves overall predictions compared to the state of the art. Furthermore, this multi-species approach is combined with convolutional neural networks predicting from a stack of local environmental maps as input variables, further improving predictions, particularly for rarely observed species.
• Botella, C., Joly, A., Monestiez, P., Bonnet, P., & Munoz, F. (2020) Bias in presence-only niche models related to sampling effort and species niches: lessons for background points selection. PLOS One, 15(5), e0232078.
  Main contribution: Calibrating species distribution models (SDMs) on opportunistic data induces bias due to spatial variations in sampling effort. To correct this bias, a popular robust method approximates sampling effort by the set of observations from a target group of species. However, this heuristic lacked theoretical guarantees and flaws had been identified empirically. In this article, I studied the statistical bias of this approach mathematically and through simulation, comparing it to the naive approach that ignores bias under common assumptions. I expressed the bias of both approaches and showed that the 'target group' correction resolved the bias due to sampling effort but introduced a new bias due to variations in the cumulative abundance of the target group species. I showed that this bias is minimized by choosing the target group to control these abundance variations, providing robust application conditions for this method.
• Botella, C., Gaüzère, P., O'Connor, L., Ohlmann, M., Renaud, J., Dou, Y., ... & Thuiller, W. (2024). Land‐use intensity influences European tetrapod food webs. Global change biology, 30(2), e17167.
  Main contribution: This study demonstrates how land-use intensification modifies the architecture of European terrestrial vertebrate food webs. The main scientific novelty lies in the reconstruction of more than 67,000 local food webs across the continent, combining opportunistic presence data (GBIF, iNaturalist) with a knowledge base of European vertebrate trophic interactions. I show that intensification systematically reduces the proportion of top predators and affects network structure (e.g., decreased compartmentalization). This pioneering approach demonstrates the value of massive citizen science data for the biogeography of biotic interactions, offering a new perspective on the ecological impacts of human activities.
• Botella, C., Bonnet, P., Hui, C., Joly, A., & Richardson, D. M. (2022). Dynamic species distribution modeling reveals the pivotal role of human-mediated long-distance dispersal in plant invasion. Biology, 11(9), 1293.
  Main contribution: This methodological proof of concept demonstrates that it is possible to calibrate a mechanistic ecological model of invasion dynamics using opportunistic data (citizen science and natural history collections) collected in space and time. The approach is applied here to the invasion of the shrub Plectranthus barbatus in South Africa, and this Bayesian dynamic model allowed testing key hypotheses about invasion mechanisms. The analysis revealed as a main ecological result that human-mediated long-distance dispersal was the primary driver of the species' rapid expansion, responsible for a massive wave of spread from urban areas of initial introduction. Without this mechanism, the current population would have only reached 30% of its current equilibrium level.
• Deneu, B., Servajean, M., Bonnet, P., Botella, C., Munoz, F., & Joly, A. (2021). Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment. PLoS computational biology, 17(4), e1008856.
  Main contribution: This study shows that deepSDMs based on Convolutional Neural Networks (CNNs) can exploit the spatial structure of the local environmental landscape to improve their predictions. The main contribution lies in the design of a series of ablation experiments. We compared CNN performance when fed with full environmental tensors (stacks of maps centered on a point representing the local landscape) versus degraded versions of this data where spatial information was removed. The results show that it is indeed the spatial configuration of environmental variables around the prediction point, and not just their statistical distribution, that allows for optimal performance. This ability to capture local landscape influence proved crucial for improving predictions, particularly for rare species.
• Picek, L., Botella, C., Servajean, M., Leblanc, C., Palard, R., Larcher, T., ... & Joly, A. (2024). Geoplant: Spatial plant species prediction dataset. Advances in Neural Information Processing Systems, 37, 126653-126676.
  Main contribution: This article presents GeoPlant, a dataset and continental benchmark for species distribution modeling. Its main contribution is to offer an integrated and standardized resource combining over 5 million opportunistic observations (PO) and 90,000 exhaustive surveys (PA) for more than 10,000 plant species, associated with multimodal predictors: Sentinel-2 satellite images, climate and satellite (Landsat) time series, and other environmental variables (soil, land use). GeoPlant constitutes a robust and accessible benchmark for evaluating SDMs, particularly deep learning approaches, by providing independent reference data (PA) for evaluation without sampling bias or spatial autocorrelation, as well as a rich set of baseline models to facilitate objective comparison and innovation in large-scale biodiversity mapping.

Articles

• Botella, C., Joly, A., Bonnet, P., Monestiez, P., & Munoz, F. (2018). Species distribution modeling based on the automated identification of citizen observations. Applications in Plant Sciences, 6(2), e1029. https://doi.org/10.1002/aps3.1029
• Botella, C., Joly, A., Monestiez, P., Bonnet, P., & Munoz, F. (2020) Bias in presence-only niche models related to sampling effort and species niches: Lessons for background point selection. PLOS ONE. https://doi.org/10.1371/journal.pone.0232078
• Botella, C., Joly, A., Bonnet, P., Munoz, F., & Monestiez, P. (2021). Jointly estimating spatial sampling effort and habitat suitability for multiple species from opportunistic presence-only data. Methods in Ecology and Evolution, 12(5), 933-945. https://doi.org/10.1111/2041-210X.13565 Download appendices
• Deneu, B., Servajean, M., Bonnet, P., Botella, C., Munoz, F., & Joly, A. (2021). Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment. PLoS computational biology, 17(4), e1008856. https://doi.org/10.1371/journal.pcbi.1008856
• Botella, C., Dray, S., Matias, C., Miele, V., & Thuiller, W. (2021). An appraisal of graph embeddings for comparing trophic network architectures. Methods in Ecology and Evolution, 13(1), 203-216. https://doi.org/10.1111/2041-210X.13738
• Gauzere, P., O Connor, L., Botella, C., Poggiato, G., Munkemuller, T., Pollock, L. J., ... & Thuiller, W. (2022). The diversity of biotic interactions complements functional and phylogenetic facets of biodiversity. Current Biology, 32(9), 2093-2100. https://doi.org/10.1016/j.cub.2022.03.009
• Botella, C., Bonnet, P., Hui, C., Joly, A., & Richardson, D. M. (2022). Dynamic Species Distribution Modeling Reveals the Pivotal Role of Human-Mediated Long-Distance Dispersal in Plant Invasion. Biology, 11(9), 1293. https://doi.org/10.3390/biology11091293
• De Beer, I., Hui, C., Botella, C. & Richardson, D.M. (2023). Drivers of community turnover of narrow-ranged versus widespread naturalised woody plants in South Africa. Frontiers in Ecology And Evolution, 11, 103. https://doi.org/10.3389/fevo.2023.1106197
• Van der Colff, D., Kumschick, S., Foden, W., Raimondo, D., Botella, C., von Staden, L. & Wilson, J.R.U. (2023). Drivers, predictors, and probabilities of plant extinctions in South Africa. Biodiversity and Conservation. https://doi.org/10.1007/s10531-023-02696-7
• ter Huurne, M. B., Potgieter, L. J., Botella, C., & Richardson, D. M. (2023). Melaleuca (Myrtaceae): Biogeography of an important genus of trees and shrubs in a changing world. South African Journal of Botany, 162, 230-244. https://doi.org/10.1016/j.sajb.2023.08.052
• Gauzere, P., Botella, C., Poggiato, G., O’Connor, L., Di Marco, M., Dragonetti, C., ... & Thuiller, W. (2023). Dissimilarity of vertebrate trophic interactions reveals spatial uniqueness but functional redundancy across Europe. Current Biology, 33(23), 5263-5271. https://doi.org/10.1016/j.cub.2023.10.069
• Botella, C., Gauzere, P., O'Connor, L., Ohlmann, M., Renaud, J., Dou, Y., Graham, C., Verburg, P., Maiorano, L., Thuiller, W. (2024). Land-use intensity influences European tetrapod food-webs. Global change biology, 30(2), e17167. https://doi.org/10.1111/gcb.17167
• Gaüzère, P., Botella, C., Poggiato, G., Clark, J., & Thuiller, W. (2024). Interspecific interactions influence bird population responses to global changes. Authorea. https://doi.org/10.22541/au.170726586.65992236/v1
• González‐Moreno, P., Anđelković, A. A., Adriaens, T., Botella, C., Demetriou, J., Bastos, R., Bertolino, S., López‐Cañizares, C., Essl, F., & Fišer, Ž. (2025). Citizen science platforms can effectively support early detection of invasive alien species according to species traits. People and Nature, 7(1), 278-294. https://doi.org/10.1002/pan3.10767
• Kumschick, S., Journiac, L., Boulesnane-Genguant, O., Botella, C., Pouteau, R., & Rouget, M. (2025). Mapping potential environmental impacts of alien species in the face of climate change. Biological Invasions, 27(1), 43. https://doi.org/10.1007/s10530-024-03490-4
• Boulesnane-Guengant, O., Rouget, M., Becker-Scarpitta, A., Botella, C., & Kumschick, S. (2025). Spatialising the ecological impacts of alien species into risk maps. Global Ecology and Conservation, 61, e03660. https://doi.org/10.1016/j.gecco.2025.e03660
• Espitalier, V., Lombardo, J. C., Goëau, H., Botella, C., Høye, T. T., Dyrmann, M., Bonnet, P., & Joly, A. (2025). Adapting a global plant identification model to detect invasive alien plant species in high-resolution road side images. Ecological Informatics, 89, 103129. https://doi.org/10.1016/j.ecoinf.2025.103129
• Xu, J., Low, K., Botella, C., Deneu, B., Shasha, D., & Joly, A. (2025). Cascading predictions from common to uncommon species improves species distribution models for plants. Ecological Informatics, 103424. https://doi.org/10.1016/j.ecoinf.2025.103424
• Ryckewaert, M., Marcos, D., Botella, C., Servajean, M., Bonnet, P., & Joly, A. (2026). Applying the maximum entropy principle to neural networks enhances multi‐species distribution models. Methods in Ecology and Evolution. https://doi.org/10.1111/2041-210x.70262
• Gigot-Léandri, S., Morand, G., Joly, A., Munoz, F., Mouillot, D., Botella, C., & Servajean, M. (2026). How to Optimize Multispecies Set Predictions in Presence-Absence Modeling? ArXiv PREPRINT. https://doi.org/10.48550/arXiv.2602.11771

Book chapters

• Botella, C., Joly, A., Bonnet, P., Monestiez, P., & Munoz, F. (2018). A Deep Learning Approach to Species Distribution Modelling. In Multimedia Tools and Applications for Environmental & Biodiversity Informatics (pp. 169-199). Springer, Cham. https://doi.org/10.1007/978-3-319-76445-0_10 Direct download.
• Joly, A., Goeau, H., Botella, C., Glotin, H., Bonnet, P., Vellinga, W.P., Planqué, R. & Muller, H. (2018). Overview of LifeCLEF 2018: A Large-Scale Evaluation of Species Identification and Recommendation Algorithms in the Era of AI: 9th International Conference of the CLEF Association, CLEF 2018, Avignon, France, September 10-14, 2018, Proceedings. https://doi.org/10.1007/978-3-319-98932-7_24
• Joly, A., Goeau, H., Botella, C., Kahl, S., Servajean, M., Glotin, H., ... & Muller, H. (2019, September). Overview of LifeCLEF 2019: identification of amazonian plants, South & North American birds, and niche prediction. In International Conference of the Cross-Language Evaluation Forum for European Languages (pp. 387-401). Springer, Cham. https://doi.org/10.1007/978-3-030-28577-7_29
• Deneu, B., Servajean, M., Botella, C., & Joly, A. (2019). Evaluation of deep species distribution models using environment and co-occurrences. In International Conference of the Cross-Language Evaluation Forum for European Languages (pp. 213-225). Springer, Cham.
• Joly, A., Goeau, H., Kahl, S., Deneu, B., Servajean, M., Cole, E., ... & Muller, H. (2020, September). Overview of LifeCLEF 2020: a system-oriented evaluation of automated species identification and species distribution Prediction. In International Conference of the Cross-Language Evaluation Forum for European Languages (pp. 342-363). Springer, Cham. https://doi.org/10.1007/978-3-030-58219-7_23
• Richardson, D. M., Binggeli, P., & Botella, C. (2023). Australian Acacia Species in Africa. Wattles: Australian Acacia Species Around the World, 181-200. https://doi.org/10.1079/9781800622197.0012
• Botella, C., Marchante, H., Celesti-Grapow, L., Brundu, G., Geerts, S., Ramirez-Albores, J., Gonzalez-Moreno, P., Ritter, M. & Richardson, D.M. (2023) The global distribution of Acacia. In Wattles, Australian Acacia species around the world. CABI. https://doi.org/10.1079/9781800622197.0009
• Joly, A., Picek, L., Kahl, S., Goëau, H., Espitalier, V., Botella, C., Marcos, D., Estopinan, J., Leblanc, C., & Larcher, T. (2024). Overview of lifeclef 2024: Challenges on species distribution prediction and identification. International Conference of the Cross-Language Evaluation Forum for European Languages, 183-207.

Datasets

• Cole, E., Deneu, B., Lorieul, T., Servajean, M., Botella, C., Morris, D., ... & Joly, A. (2020). The geolifeclef 2020 dataset. arXiv preprint https://doi.org/10.48550/arXiv.2004.04192
• Botella, C., Deneu, B., Marcos, D., Servajean, M., Estopinan, J., Larcher, T., ... & Joly, A. (2023). The GeoLifeCLEF 2023 Dataset to evaluate plant species distribution models at high spatial resolution across Europe. arXiv preprint. https://doi.org/10.48550/arXiv.2308.05121
• Picek, L., Botella, C., Servajean, M., Leblanc, C., Palard, R., Larcher, T., Deneu, B., Marcos, D., Bonnet, P., & Joly, A. (2024). Geoplant: Spatial plant species prediction dataset. Advances in Neural Information Processing Systems, 37, 126653-126676. https://doi.org/10.52202/079017-4023

Scientific outreach

• Castagneyrol, B., Botella, C. & Fontaine, B. (2022). Sciences citoyennes et qualité des données sur la biodiversité: Un faux problème? Numéro spécial #1, art. 6. Novae, INRAE. https://doi.org/10.17180/novae-2022-ns01-art06
• Streito, J. C., Papaix, J., Chartois, M., Botella, C., Pierre, E., Armand, J. M., ... & Rossi, J. P. (2023). Les citoyens, sentinelles de la surveillance phytosanitaire?. In Crises sanitaires en agriculture: Les espèces invasives sous surveillance (pp. 151-166). Quae. Link

Working notes

• Botella, C., Bonnet, P., Munoz, F., Monestiez, P., & Joly, A. (2018, September). Overview of GeoLifeCLEF 2018: location-based species recommendation. In CLEF 2018. Download pdf.
• Deneu, B., Servajean, M., Botella, C., & Joly, A. (2018, September). Location-based species recommendation using co-occurrences and environment-GeoLifeCLEF 2018 challenge. In CLEF 2018. Download pdf.
• Botella, C., Servajean, M., Bonnet, P., & Joly, A. (2019, September). Overview of GeoLifeCLEF 2019: plant species prediction using environment and animal occurrences. In Working Notes of CLEF 2019-Conference and Labs of the Evaluation Forum (No. 2380). HAL Link
• Deneu, B., Lorieul, T., Cole, E., Servajean, M., Botella, C., Bonnet, P., & Joly, A. (2020). Overview of LifeCLEF location-based species prediction task 2020 (GeoLifeCLEF). CEUR-WS. Agritrop Link
• Botella, C., Deneu, B., Gonzalez, D. M., Servajean, M., Larcher, T., Leblanc, C., ... & Joly, A. (2023). Overview of GeoLifeCLEF 2023: Species Composition Prediction with High Spatial Resolution at Continental Scale Using Remote Sensing. In Working Notes of CLEF 2023-Conference and Labs of the Evaluation Forum. temporary_link

Updated on March 2026.