Using joint species distribution modelling to predict distributions of seafloor taxa and identify vulnerable marine ecosystems in New Zealand waters

Abstract Effective ecosystem-based management of bottom-contacting fisheries requires understanding of how disturbances from fishing affect seafloor fauna over a wide range of spatial and temporal scales. Using an extensive dataset of faunal abundances collected using a towed camera system, with spatially explicit predictor variables including bottom-trawl fishing effort, we developed spatial predictions of abundance for 67 taxa using Hierarchical Modelling of Species Communities . The model fit metrics varied by taxon: the mean ten-fold cross-validated AUC score was 0.70 ± 0.1 (standard deviation) for presence-absence and an R 2 of 0.11 ± 0.1 (standard deviation) for abundance models. Spatial predictions of probability of occurrence and abundance (individuals per km 2 ) varied by taxon, but there were key areas of overlap, with highest predicted taxon richness in areas of the continental shelf break and slope. The resulting joint predictions represent significant advances on previous predictions because they are of abundance, allow the exploration of co-occurrence patterns and provide credible estimates of taxon richness (including for rare species that are often not included in community-level species distribution assessments). Habitat-forming taxa considered to be Vulnerable Marine Ecosystem (VME) indicators (those taxa that are physically or functionally fragile to anthropogenic impacts) were identified in the dataset. Spatial estimates of likely VME distribution (as well as associated estimates of uncertainty) were predicted for the study area. Identifying areas most likely to represent a VME (rather than simply VME indicator taxa) provides much needed quantitative estimates of vulnerable habitats, and facilitates an evidence-based approach to managing potential impacts of bottom-trawling.