Publication Repository

A novel method for mapping reefs and subtidal rocky habitats using artificial neural networks

Show simple item record

dc.contributor Australian Institute Of Marine Science
dc.contributor Sch Earth & Environm Sci
dc.contributor University Of Adelaide
dc.contributor So Seas Ecol Labs
dc.contributor Australian Inst Marine Sci
dc.contributor Univ Adelaide
dc.contributor Inst Environm
dc.contributor Australian Institute Of Marine Science (aims) en
dc.contributor.author FORDHAM, DAMIEN A.
dc.contributor.author WATTS, MICHAEL J.
dc.contributor.author LI, YUXIAO
dc.contributor.author RUSSELL, BAYDEN D.
dc.contributor.author MELLIN, CAMILLE
dc.contributor.author CONNELL, SEAN D.
dc.date.accessioned 2017-03-21T00:47:44Z
dc.date.accessioned 2017-03-21T00:47:44Z
dc.date.accessioned 2013-02-28T06:41:27Z
dc.date.accessioned 2019-05-09T01:09:58Z
dc.date.available 2013-02-28T06:41:27Z
dc.date.available 2017-03-21T00:47:44Z
dc.date.available 2017-03-21T00:47:44Z
dc.date.available 2019-05-09T01:09:58Z
dc.date.issued 2011-08-10
dc.identifier 8922 en
dc.identifier.citation Watts MJ, Li Y, Russell BD, Mellin C, Connell SD and Fordham DA (2011) A novel method for mapping reefs and subtidal rocky habitats using artificial neural networks. Ecological Modelling. 222: 2606-2614. en
dc.identifier.issn 0304-3800
dc.identifier.uri http://epubs.aims.gov.au/11068/8922
dc.description Link to abstract/full text - http://dx.doi.org/10.1016/j.ecolmodel.2011.04.024 en
dc.description.abstract Reefs and subtidal rocky habitats are sites of high biodiversity and productivity which harbour commercially important species of fish and invertebrates. Although the conservation management of reef associated species has been informed using species distribution models (SDM) and community based approaches, to date their use has been constrained to specific regions where the locality and spatial extent of reefs is well known. Much of the world's subtidal habitats remain either undiscovered or unmapped, including coasts of intense human use. Consequently, to facilitate a stronger understanding of species-environmental relationships there is an urgent need for a cost and time effective standard method to map reefs at fine spatial resolutions across broad geographical extents. We used bathymetric data (similar to 250 m resolution) to calculate the local slope and curvature of the seabed. We then constructed artificial neural networks (ANNs) to forecast the probability of reef occurrence within grid cells as a function of bathymetric and slope variables. Testing over an independent data set not used in training showed that ANNs were able to accurately predict the location of reefs for 86% of all grid cells (Kappa = 0.63) without over fitting. The ANN with greatest support, combining bathymetric values of the target grid cell with the slope of adjacent grid cells, was used to map inshore reef locations around the Southern Australian coastline (similar to 250 m resolution). Broadly, our results show that reefs are identifiable from coarse-scale bathymetry data of the seabed. We anticipate that our research technique will strengthen systematic conservation planning tools in many regions of the world, by enabling the identification of rocky substratum and mapping in localities that remain poorly surveyed due to logistics or monetary constraints. (C) 2011 Elsevier B.V. All rights reserved.
dc.description.sponsorship The research was funded by Australian Research Council grants awarded to D.A. Fordham and S.D. Connell.
dc.description.uri http://dx.doi.org/10.1016/j.ecolmodel.2011.04.024 en
dc.language English
dc.language en en
dc.relation.ispartof Ecological Modelling - pages: 222: 2606-2614 en
dc.relation.ispartof Null
dc.subject Artificial Neural Networks
dc.subject Abundance
dc.subject Environmental Sciences & Ecology
dc.subject Input Variables
dc.subject Reefs
dc.subject Prediction
dc.subject Bathymetry
dc.subject Littoral-zone
dc.subject Subtidal Rocky Habitat
dc.subject Fresh-water Fish
dc.subject Ecology
dc.subject Species Distributions
dc.subject Models
dc.subject Nets
dc.subject Aquatic Insects
dc.subject River
dc.title A novel method for mapping reefs and subtidal rocky habitats using artificial neural networks
dc.type journal article en
dc.identifier.doi 10.1016/j.ecolmodel.2011.04.024
dc.identifier.wos WOS:000294105500002


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Publication


Browse

My Account