Predicting bottlenose dolphin distribution along Liguria coast (northwestern Mediterranean Sea) through different modeling techniques and indirect predictors. (1st March 2015)

• Record Type: Journal Article
• Authors: Marini, C.; Fossa, F.; Paoli, C.; Bellingeri, M.; Gnone, G.; Vassallo, P.
• Is Part Of: Journal of environmental management. Volume 150(2015:Mar.)
• Page Start: 9
• Page End: 20
• Publication Date: 2015-03-01
• Subjects: Tursiops truncatus -- Habitat modeling -- GLM -- GAM -- Random forest -- Pelagos sanctuary -- Ligurian coast; Environmental policy -- Periodicals; Environmental management -- Periodicals; Environment -- Periodicals; Ecology -- Periodicals; 363.705
• DOI: 10.1016/j.jenvman.2014.11.008
• Languages: English
• ISSNs: 0301-4797

Abstract

Abstract: Habitat modeling is an important tool to investigate the quality of the habitat for a species within a certain area, to predict species distribution and to understand the ecological processes behind it. Many species have been investigated by means of habitat modeling techniques mainly to address effective management and protection policies and cetaceans play an important role in this context. The bottlenose dolphin ( Tursiops truncatus ) has been investigated with habitat modeling techniques since 1997. The objectives of this work were to predict the distribution of bottlenose dolphin in a coastal area through the use of static morphological features and to compare the prediction performances of three different modeling techniques: Generalized Linear Model (GLM), Generalized Additive Model (GAM) and Random Forest (RF). Four static variables were tested: depth, bottom slope, distance from 100 m bathymetric contour and distance from coast. RF revealed itself both the most accurate and the most precise modeling technique with very high distribution probabilities predicted in presence cells (90.4% of mean predicted probabilities) and with 66.7% of presence cells with a predicted probability comprised between 90% and 100%. The bottlenose distribution obtained with RF allowed the identification of specific areas with particularly high presence probability along the coastal zone; the recognition of these core areas may be the starting point to develop effective management practices to improve T. truncatus protection. Highlights: We tested three modeling techniques for the Tursiops truncatus distribution prediction. Main variables affecting T. truncatus distribution were identified. Model based on random forest revealed the highest accuracy and precision. Spot areas of very high predicted distribution values have been identified.