preprint · ArXiv.org · 2025

Multi-scale species richness estimation with deep learning

Victor Boussange, Bert Wuyts, Philipp Brun, Johanna Malle, Gabriele Midolo, Jeanne Portier, Théophile Sanchez, Niklaus E. Zimmermann, Irena Axmanová, Helge Bruelheide, Milan Chytrý, Stephan Kambach, Zdeňka Lososová, Martin Večeřa, Idoia Biurrun, Klaus Ecker, Jonathan Lenoir, Jens‐Christian Svenning, Dirk Nikolaus Karger

Cited by 0Open access

Abstract

Biodiversity assessments depend critically on the spatial scale at which species richness is measured. How species richness accumulates with sampling area is influenced by natural and anthropogenic processes whose effects vary across spatial scales. These accumulation dynamics, described by the species-area relationship (SAR), are challenging to assess because most biodiversity surveys cover sampling areas far smaller than the scales at which these processes operate. Here, we combine sampling theory with deep learning to estimate species richness at arbitrary spatial scales across geographic space from existing ecological surveys. We apply our model, named MuScaRi, to ~350k vegetation surveys across Europe. Validated against independent regional plant inventories, MuScaRi reduces root mean squared error of vascular plant richness estimates by 61% relative to conventional estimators, yields substantially less biased predictions, and produces multi-scale richness maps alongside spatially explicit estimates of the species accumulation rate, a key indicator for biodiversity conservation. By encompassing the full spectrum of ecologically relevant spatial scales within a single unified framework, MuScaRi provides an essential tool for robust biodiversity assessments and forecasts under global change.

Cite this paper

APA 7

Boussange, V., Wuyts, B., Brun, P., Malle, J., Midolo, G., Portier, J., Sanchez, T., Zimmermann, N. E., Axmanová, I., Bruelheide, H., Chytrý, M., Kambach, S., Lososová, Z., Večeřa, M., Biurrun, I., Ecker, K., Lenoir, J., Svenning, J., & Karger, D. N. (2025). Multi-scale species richness estimation with deep learning. ArXiv.org. https://doi.org/10.48550/arxiv.2507.06358

MLA 9

Boussange, Victor, et al. “Multi-scale species richness estimation with deep learning.” ArXiv.org, 2025, https://doi.org/10.48550/arxiv.2507.06358.

Chicago

Boussange, Victor, Bert Wuyts, Philipp Brun, Johanna Malle, Gabriele Midolo, Jeanne Portier, Théophile Sanchez, et al. 2025. “Multi-scale species richness estimation with deep learning.” ArXiv.org. https://doi.org/10.48550/arxiv.2507.06358.

Harvard

Boussange, V. et al. (2025) ‘Multi-scale species richness estimation with deep learning’, ArXiv.org. Available at: https://doi.org/10.48550/arxiv.2507.06358.

BibTeX

@misc{boussange2025multi,
  title = {{Multi-scale species richness estimation with deep learning}},
  author = {Boussange, Victor and Wuyts, Bert and Brun, Philipp and Malle, Johanna and Midolo, Gabriele and Portier, Jeanne and Sanchez, Théophile and Zimmermann, Niklaus E. and Axmanová, Irena and Bruelheide, Helge and Chytrý, Milan and Kambach, Stephan and Lososová, Zdeňka and Večeřa, Martin and Biurrun, Idoia and Ecker, Klaus and Lenoir, Jonathan and Svenning, Jens‐Christian and Karger, Dirk Nikolaus},
  journal = {ArXiv.org},
  year = {2025},
  doi = {10.48550/arxiv.2507.06358}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.