Can multilayer perceptron ensembles model the ecological niche of freshwater fish species?
The potential of Multilayer Perceptron (MLP) Ensembles to explore the ecology of freshwater fish species was tested by applying the technique to redfin barbel (Barbus haasi Mertens, 1925), an endemic and montane species that inhabits the North-East quadrant of the Iberian Peninsula. Two different ML...
Published in: | Ecological Modelling |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
E.T.S.I. Montes (UPM)
2015
|
Subjects: | |
Online Access: | https://oa.upm.es/41387/ |
id |
ftunivpmadrid:oai:oa.upm.es:41387 |
---|---|
record_format |
openpolar |
spelling |
ftunivpmadrid:oai:oa.upm.es:41387 2023-05-15T16:08:38+02:00 Can multilayer perceptron ensembles model the ecological niche of freshwater fish species? Muñoz-Mas, Rafael Martínez Capel, Francisco Alcaraz Hernández, Juan Diego Mouton, A.M. 2015-08 application/pdf https://oa.upm.es/41387/ eng eng E.T.S.I. Montes (UPM) https://www.sciencedirect.com/science/article/pii/S0304380015001763?via%3Dihub info:eu-repo/semantics/altIdentifier/doi/10.1016/j.ecolmodel.2015.04.025 https://oa.upm.es/41387/ https://creativecommons.org/licenses/by-nc-nd/3.0/es/ info:eu-repo/semantics/openAccess CC-BY-NC-ND Ecological Modelling, ISSN 0304-3800, 2015-08, No. 309 Biología Hidrología info:eu-repo/semantics/article Artículo PeerReviewed 2015 ftunivpmadrid https://doi.org/10.1016/j.ecolmodel.2015.04.025 2022-06-06T18:19:30Z The potential of Multilayer Perceptron (MLP) Ensembles to explore the ecology of freshwater fish species was tested by applying the technique to redfin barbel (Barbus haasi Mertens, 1925), an endemic and montane species that inhabits the North-East quadrant of the Iberian Peninsula. Two different MLP Ensembles were developed. The physical habitat model considered only abiotic variables, whereas the biotic model also included the density of the accompanying fish species and several invertebrate predictors. The results showed that MLP Ensembles may outperform single MLPs. Moreover, active selection of MLP candidates to create an optimal subset of MLPs can further improve model performance. The physical habitat model confirmed the redfin barbel preference for middle-to-upper river segments whereas the importance of depth confirms that redfin barbel prefers pool-type habitats. Although the biotic model showed higher uncertainty, it suggested that redfin barbel, European eel and the considered cyprinid species have similar habitat requirements. Due to its high predictive performance and its ability to deal with model uncertainty, the MLP Ensemble is a promising tool for ecological modelling or habitat suitability prediction in environmental flow assessment. Article in Journal/Newspaper European eel Archivo Digital UPM (Universidad Politécnica de Madrid) Ecological Modelling 309-310 72 81 |
institution |
Open Polar |
collection |
Archivo Digital UPM (Universidad Politécnica de Madrid) |
op_collection_id |
ftunivpmadrid |
language |
English |
topic |
Biología Hidrología |
spellingShingle |
Biología Hidrología Muñoz-Mas, Rafael Martínez Capel, Francisco Alcaraz Hernández, Juan Diego Mouton, A.M. Can multilayer perceptron ensembles model the ecological niche of freshwater fish species? |
topic_facet |
Biología Hidrología |
description |
The potential of Multilayer Perceptron (MLP) Ensembles to explore the ecology of freshwater fish species was tested by applying the technique to redfin barbel (Barbus haasi Mertens, 1925), an endemic and montane species that inhabits the North-East quadrant of the Iberian Peninsula. Two different MLP Ensembles were developed. The physical habitat model considered only abiotic variables, whereas the biotic model also included the density of the accompanying fish species and several invertebrate predictors. The results showed that MLP Ensembles may outperform single MLPs. Moreover, active selection of MLP candidates to create an optimal subset of MLPs can further improve model performance. The physical habitat model confirmed the redfin barbel preference for middle-to-upper river segments whereas the importance of depth confirms that redfin barbel prefers pool-type habitats. Although the biotic model showed higher uncertainty, it suggested that redfin barbel, European eel and the considered cyprinid species have similar habitat requirements. Due to its high predictive performance and its ability to deal with model uncertainty, the MLP Ensemble is a promising tool for ecological modelling or habitat suitability prediction in environmental flow assessment. |
format |
Article in Journal/Newspaper |
author |
Muñoz-Mas, Rafael Martínez Capel, Francisco Alcaraz Hernández, Juan Diego Mouton, A.M. |
author_facet |
Muñoz-Mas, Rafael Martínez Capel, Francisco Alcaraz Hernández, Juan Diego Mouton, A.M. |
author_sort |
Muñoz-Mas, Rafael |
title |
Can multilayer perceptron ensembles model the ecological niche of freshwater fish species? |
title_short |
Can multilayer perceptron ensembles model the ecological niche of freshwater fish species? |
title_full |
Can multilayer perceptron ensembles model the ecological niche of freshwater fish species? |
title_fullStr |
Can multilayer perceptron ensembles model the ecological niche of freshwater fish species? |
title_full_unstemmed |
Can multilayer perceptron ensembles model the ecological niche of freshwater fish species? |
title_sort |
can multilayer perceptron ensembles model the ecological niche of freshwater fish species? |
publisher |
E.T.S.I. Montes (UPM) |
publishDate |
2015 |
url |
https://oa.upm.es/41387/ |
genre |
European eel |
genre_facet |
European eel |
op_source |
Ecological Modelling, ISSN 0304-3800, 2015-08, No. 309 |
op_relation |
https://www.sciencedirect.com/science/article/pii/S0304380015001763?via%3Dihub info:eu-repo/semantics/altIdentifier/doi/10.1016/j.ecolmodel.2015.04.025 https://oa.upm.es/41387/ |
op_rights |
https://creativecommons.org/licenses/by-nc-nd/3.0/es/ info:eu-repo/semantics/openAccess |
op_rightsnorm |
CC-BY-NC-ND |
op_doi |
https://doi.org/10.1016/j.ecolmodel.2015.04.025 |
container_title |
Ecological Modelling |
container_volume |
309-310 |
container_start_page |
72 |
op_container_end_page |
81 |
_version_ |
1766404666429538304 |