Multi-Scale Approach for Predicting Fish Species Distributions across Coral Reef Seascapes

Abstract

Two of the major limitations to effective management of coral reef ecosystems are a lack of information on the spatial distribution of marine species and a paucity of data on the interacting environmental variables that drive distributional patterns. Advances in marine remote sensing, together with the novel integration of landscape ecology and advanced niche modelling techniques provide an unprecedented opportunity to reliably model and map marine species distributions across many kilometres of coral reef ecosystems. We developed a multi-scale approach using three-dimensional seafloor morphology and across-shelf location to predict spatial distributions for five common Caribbean fish species. Seascape topography was quantified from high resolution bathymetry at five spatial scales (5–300 m radii) surrounding fish survey sites. Model performance and map accuracy was assessed for two high performing machine-learning algorithms: Boosted Regression Trees (BRT) and Maximum Entropy Species Distribution Modelling (MaxEnt). The three most important predictors were geographical location across the shelf, followed by a measure of topographic complexity. Predictor contribution differed among species, yet rarely changed across spatial scales. BRT provided ‘outstanding’ model predictions (AUC = >0.9) for three of five fish species. MaxEnt provided ‘outstanding’ model predictions for two of five species, with the remaining three models considered ‘excellent’ (AUC = 0.8–0.9). In contrast, MaxEnt spatial predictions were markedly more accurate (92% map accuracy) than BRT (68% map accuracy). We demonstrate that reliable spatial predictions for a range of key fish species can be achieved by modelling the interaction between the geographical location across the shelf and the topographic heterogeneity of seafloor structure. This multi-scale, analytic approach is an important new cost-effective tool to accurately delineate essential fish habitat and support conservation prioritization in marine protected area design, zoning in marine spatial planning, and ecosystem-based fisheries management.

Utilizing Underwater Three-Dimensional Modeling to Enhance Ecological and Biological Studies of Coral Reefs

“…Surface rugosity, surface complexity, slope, and curvature have been shown to drive vegetation distribution on terrestrial landscapes and influence the distribution, biomass and diversity of vertebrate and invertebrate species in marine systems (Friedlander and Parrish 1998, Kostylev et al 2005, Guinan et al 2009, Pittman et al 2009, Pittman and Brown 2011. We quantified these metrics for four coral species found commonly in Hawaiʻi that represent distinct morphological phenotypes (Porites lobata -massive/lobate, Porites compressa -branching, Montipora capitata -plating, Montipora flabellate -encrusting).…”

“…This process enables quantification of intricate 3D features such as surface complexity (3D/2D surface area), slope, volume and curvature. These metrics are known to be important predictors of organismal abundance, biomass and diversity, and also affect benthic current velocities associated with the food particle supply for suspension feeding corals (Kostylev et al 2005, Guinan et al 2009, Pittman et al 2009, Pittman and Brown 2011. The ability to characterize these topographic features will greatly enhance both biological and ecological investigations of coral reef ecosystems.…”

Modeling the coastal ecosystem complex: present situation and challenges

“…These are generally statistical models that are constructed using observed habitat-organism relationships. Various statistical algorithms, including generalized linear models, generalized additive models, and maximum entropy models, are used to predict the distribution of marine organisms (Jones et al 2012;Murase et al 2009;Pittman and Brown 2011;Reiss et al 2011). Although SD models are powerful tools for evaluating the spatial distribution of organisms in diverse habitats, they are usually empirical and most of them cannot provide mechanistic predictions.…”

Prognosis Essay Scoring and Article Relevancy Using Multi-Text Features and Machine Learning

“…GBMs have shown considerable success in not only practical applications, but also in various machine-learning and data-mining challenges [54][55][56][57]. The functionality of the GBM algorithm is described briefly in Algorithm 3.…”