Species distribution models for deep-water coral habitats that account for spatial uncertainty in trap-camera fishery data

Abstract

Bottom-contact fisheries present risks to vulnerable marine ecosystems (VMEs) such as deep-water coral and sponge communities. Managing these risks requires better knowledge about VME spatial distribution within fishing areas. In this paper, we develop predictive species distribution models for alcyonacean (Order Alcyonacea) corals at SGaan Kinghlas-Bowie Seamount (SK-B) in British Columbia, Canada, based on direct presence/absence observations obtained from deep-water cameras attached to commercial fishing gear. We obtained in situ presence/absence observations of deep-water corals (Order Alcyonacea, Order Antipatharia, Order Pennatulacea, Family Stylasteridae) and sponges (Class Hexactinellida, Class Demospongiae) at 124 locations during commercial fishing trips at the SK-B marine protected area. We developed species distribution models for alcyonacean corals at SK-B and compared the performance of models using 4 different estimators of trap landing position (surface drop position and 3 Bayesian estimators) to account for spatial uncertainty in observation locations. We found that the different estimators for landing position affected variable selection, model performance, and model predictions. The best-fitting models using the 4 different landing position estimators had mean AUC values ranging from 0.71 to 0.78 and maximum kappa values ranging from 0.36 to 0.47. This study demonstrates how collaborative research surveys with commercial fisheries can provide fine-scale spatial data for coral and sponge habitat mapping using an approach that is scalable for benthic habitat risk assessment for large, possibly remote, areas where fisheries operate.