Submit a preprint

Direct submissions to PCI Ecology from bioRxiv.org are possible using the B2J service

584

Predicting species distributions in the open ocean with convolutional neural networksuse asterix (*) to get italics
Gaétan Morand, Alexis Joly, Tristan Rouyer, Titouan Lorieul, Julien BardePlease use the format "First name initials family name" as in "Marie S. Curie, Niels H. D. Bohr, Albert Einstein, John R. R. Tolkien, Donna T. Strickland"
2024
<p>As biodiversity plummets due to anthropogenic disturbances, the conservation of oceanic species is made harder by limited knowledge of their distributions and migrations. Indeed, tracking species distributions in the open ocean is particularly challenging due to the scarcity of observations and the complex and variable nature of the ocean system. In this study, we propose a new method that leverages deep learning, specifically convolutional neural networks (CNNs), to capture spatial features of environmental variables. This novelty eliminates the need to predefine these features before modelling and creates opportunities to discover unexpected correlations. Our aim is to present the results of the first trial of this method in the open ocean, discuss limitations and provide feedback for future improvements or adjustments.</p> <p>In this case study, we considered 38 taxa comprising pelagic fishes, elasmobranchs, marine mammals, marine turtles and birds. We trained a model to predict probabilities from the environmental conditions at any specific point in space and time, using species occurrence data from the Global Biodiversity Information Facility (GBIF) and environmental data from various sources. These variables included sea surface temperature, chlorophyll concentration, salinity and fifteen others.</p> <p>During the testing phase, the model was applied to environmental data at locations where species occurrences were recorded. The classifier accurately predicted the observed taxon as the most likely taxon in 69% of cases and included the observed taxon among the top three most likely predictions in 89% of cases. These findings show the adequacy of deep learning for species distribution modelling in the open ocean.</p> <p>Additionally, this purely correlative model was then analysed with explicability tools to understand which variables had an influence on the model's predictions. While variable importance was species-dependent, we identified finite-size Lyapunov exponents (FSLEs), sea surface temperature, pH and salinity as the most influential variables, in that order. These insights can prove valuable for future species-specific ecology studies.</p>
https://doi.org/10.5281/zenodo.8188512You should fill this box only if you chose 'All or part of the results presented in this preprint are based on data'. URL must start with http:// or https://
https://doi.org/10.5281/zenodo.10809445You should fill this box only if you chose 'Scripts were used to obtain or analyze the results'. URL must start with http:// or https://
https://doi.org/10.5281/zenodo.10809445You should fill this box only if you chose 'Codes have been used in this study'. URL must start with http:// or https://
deeplearning;megafauna;openocean;pelagicspecies;speciesdistributionmodels
NonePlease indicate the methods that may require specialised expertise during the peer review process (use a comma to separate various required expertises).
Marine ecology, Species distributions
Elija Cole [elijah.cole.cs@gmail.com], Sara Beery [sbeery@caltech.edu], Austin Smith [amsmith11@usf.edu], Wilfried Thuiller [wilfried.thuiller@univ-grenoble-alpes.fr], Rutger Aldo Vos [rutgeraldo@gmail.com], Briannyn Lee Woods [bree.woods@utas.edu.au], Néstor M. Robinson [robinson.biol@gmail.com], Fabrice Not suggested: sakina-dorothee.ayata@locean.ipsl.fr, Fabrice Not suggested: Mick Follows: mick@mit.edu, Sakina-Dorothee Ayata suggested: Fabio Benedetti, ETHZ, Switzerland, fabio.benedetti@usys.ethz.ch, Sakina-Dorothee Ayata suggested: Alexandre Schickele, ETHZ, Switzerland, alexandre.schickele@usys.ethz.ch, Sakina-Dorothee Ayata suggested: Joost de Vries, Univ. Bristol, United Kingdom, joost.devries@bristol.ac.uk, Sakina-Dorothee Ayata suggested: Guillem Chust, AZTI, Spain, gchust@azti.es, Jean-Olivier Irisson suggested: Christophe Botella christophe.botella@gmail.com, but may be considered as conflict of interest with some coauthors., Jean-Christophe POGGIALE suggested: I'm sorry but I already have several reviews to do and I'm thus now too busy., Benjamin Kellenberger [benjamin.kellenberger@yale.edu] suggested: Apologies for the decline, but I have co-authored a publication with Alexis Joly recently, This was only a small collaboration, though, so if this does not matter I can still accept., Benjamin Kellenberger [benjamin.kellenberger@yale.edu] suggested: Alternative reviewer suggestion: Elijah Cole (ecole@caltech.edu), Sakina-Dorothee Ayata suggested: Jérémy Fix (LORIA, Metz) : Jeremy.Fix@centralesupelec.fr, Sakina-Dorothee Ayata suggested: Cedric Pradalier (GeorgiaTech Lorraine, Metz) : cedric.pradalier@georgiatech-metz.fr No need for them to be recommenders of PCIEcology. Please do not suggest reviewers for whom there might be a conflict of interest. Reviewers are not allowed to review preprints written by close colleagues (with whom they have published in the last four years, with whom they have received joint funding in the last four years, or with whom they are currently writing a manuscript, or submitting a grant proposal), or by family members, friends, or anyone for whom bias might affect the nature of the review - see the code of conduct
e.g. John Doe [john@doe.com]
2023-08-13 07:25:28
François Munoz
Jean-Olivier Irisson