Cross‐validation matters in species distribution models: a case study with goatfish species

In an era of ongoing biodiversity, it is critical to map biodiversity patterns in spaceand time for better-informing conservation and management. Species distributionmodels (SDMs) are widely applied in various types of such biodiversity assessments.Cross-validation represents a prevalent approach to assess the discrimination capacityof a target SDM algorithm and determine its optimal parameters. Several alternativecross-validation methods exist; however, the influence of choosing a specific cross-validation method on SDM performance and predictions remains unresolved. Here,we tested the performance of random versus spatial cross-validation methods for SDMusing goatfishes (Actinopteri: Syngnathiformes: Mullidae) as a case study, which arerecognized as indicator species for coastal waters. Our results showed that the randomversus spatial cross-validation methods resulted in different optimal model parameter-izations in 57 out of 60 modeled species. Significant difference existed in predictiveperformance between the random and spatial cross-validation methods, and the twocross-validation methods yielded different projected present-day spatial distributionand future projection patterns of goatfishes under climate change exposure. Despitethe disparity in species distributions, both approaches consistently suggested the Indo-Australian Archipelago as the hotspot of goatfish species richness and also as the mostvulnerable area to climate change. Our findings highlight that the choice of cross-validation method is an overlooked source of uncertainty in SDM studies. Meanwhile,the consistency in richness predictions highlights the usefulness of SDMs in marine conservation. These findings emphasize that we should pay special attention to the selection of cross-validation methods inSDM studies.