Finding the right fit: Comparative cetacean distribution models using multiple data sources and statistical approaches

International audienceAim: Accurate predictions of cetacean distributions are essential to their conservation but are limited by statistical challenges and a paucity of data. This study aimed at comparing the capacity of various statistical algorithms to deal with biases commonly found in nonsystematic cetacean surveys and to evaluate the potential for citizen science data to improve habitat modelling and predictions. An endangered population of humpback whales (Megaptera novaeangliae) in their breeding ground was used as a case study. Location: New Caledonia, Oceania. Methods: Five statistical algorithms were used to model the habitat preferences of humpback whales from 1,360 sightings collected over 14 years of nonsystematic research surveys. Three different background sampling approaches were tested when developing models from 625 crowdsourced sightings to assess methods accounting for citizen science spatial sampling bias. Model evaluation was conducted through cross-validation and prediction to an independent satellite tracking dataset. Results: Algorithms differed in complexity of the environmental relationships modelled , ecological interpretability and transferability. While parameter tuning had a great effect on model performances, GLMs generally had low predictive performance , SVMs were particularly hard to interpret, and BRTs had high descriptive power but showed signs of overfitting. MAXENT and especially GAMs provided a valuable complexity trade-off, accurate predictions and were ecologically intelligible. Models showed that humpback whales favoured cool (22–23°C) and shallow waters (0–100 m deep) in coastal as well as offshore areas. Citizen science models converged with research survey models, specifically when accounting for spatial sampling bias. Main conclusions: Marine megafauna distribution models present specific challenges that may be addressed through integrative evaluation, independent testing and appropriately tuned statistical algorithms. Specifically, controlling overfitting is a priority when predicting cetacean distributions for large-scale conservation perspectives. Citizen science data appear to be a powerful tool to describe cetacean habitat