Broad-scale species distribution models applied to data-poor areas.

• Published in: Progress in Oceanography
• Main Authors: Guillaumot, Charlène, Artois, Jean, Saucède, Thomas, Demoustier, Laura, Moreau, Camille, Eléaume, Marc, Agüera, Antonio, Danis, Bruno
• Other Authors: Laboratoire de Biologie Marine, Université libre de Bruxelles (ULB), Spatial Epidemiology Lab (SpELL), Biogéosciences UMR 6282 (BGS), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS), Institut de Systématique, Evolution, Biodiversité (ISYEB ), Muséum national d'Histoire naturelle (MNHN)-École Pratique des Hautes Études (EPHE), Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université des Antilles (UA), Danish Shellfish Center, DTU-aqua, Work supported by a “Fonds pour la formation à la Recherche dans l’Industrie et l’Agriculture” (FRIA) grant and by the Belgian Science Policy Office(BELSPO, contract n°BR/132/A1/vERSO).
• Format: Article in Journal/Newspaper
• Language: English
• Published: HAL CCSD 2019
• Subjects: Boosted Regression Trees (BRTs); Presence-only; Cross-validation; Extrapolation; Modelling evaluation; [SDE.BE]Environmental Sciences/Biodiversity and Ecology; Southern Ocean
• Online Access: https://hal.science/hal-02270076; https://hal.science/hal-02270076/document; https://hal.science/hal-02270076/file/S0079661118301939.pdf; https://doi.org/10.1016/j.pocean.2019.04.007

10 pages International audience Species distribution models (SDMs) have been increasingly used over the past decades to characterise the spatial distribution and the ecological niche of various taxa. Validating predicted species distribution is important, especially when producing broad-scale models (i.e. at continental or oceanic scale) based on limited and spatially aggregated presence-only records. In the present study, several model calibration methods are compared and guidelines are provided to perform relevant SDMs using a Southern Ocean marine species, the starfish Odontaster validus Koehler, 1906, as a case study. The effect of the spatial aggregation of presence-only records on modelling performance is evaluated and the relevance of a target-background sampling procedure to correct for this effect is assessed. The accuracy of model validation is estimated using k-fold random and spatial cross-validation procedures. Finally, we evaluate the relevance of the Multivariate Environmental Similarity Surface (MESS) index to identify areas in which SDMs accurately interpolate and conversely, areas in which models extrapolate outside the environmental range of occurrence records.Results show that the random cross-validation procedure (i.e. a widely applied method, for which training and test records are randomly selected in space) tends to over-estimate model performance when applied to spatially aggregated datasets. Spatial cross-validation procedures can compensate for this over-estimation effect but different spatial cross-validation procedures must be tested for their ability to reduce over-fitting while providing relevant validation scores. Model predictions show that SDM generalisation is limited when working with aggregated datasets at broad spatial scale. The MESS index calculated in our case study show that over half of the predicted area is highly uncertain due to extrapolation. Our work provides methodological guidelines to generate accurate model assessments at broad spatial scale when using ...