Random forests to evaluate biotic interactions in fish distribution models
Random forests to evaluate biotic interactions in fish distribution models
Previous research indicated that high predictive performance in species distribution modelling can be obtained by combining both biotic and abiotic habitat variables. However, models developed for fish often only address physical habitat characteristics, thus omitting potentially important biotic factors. Therefore, we assessed the impact of biotic variables on fish habitat preferences in four selected stretches of the upper Cabriel River (E Spain). The occurrence of Squalius pyrenaicus and Luciobarbus guiraonis was related to environmental variables describing biotic interactions (inferred by relationships among fish abundances) and channel hydro-morphological characteristics. Random Forests (RF) models were trained and then validated using independent datasets. To build RF models, the conditional variable importance was used together with the model improvement ratio technique. The procedure showed effectiveness in identifying a parsimonious set of not correlated variables, which minimize noise and improve model performance in both training and validation phases. Water depth, channel width, fine substrate and water-surface gradient were selected as most important habitat variables for both fish. Results showed clear habitat overlapping between fish species and suggest that competition is not a strong factor in the study area.
173-183
Vezza, P.
b8f933f4-bd6e-468b-835c-ada608d08ecc
Martinez-Capel, F.
8807606a-3389-4f8a-874c-4ca346575e09
Muñoz-Mas, R.
cde898b8-e30e-4c6d-9819-dec8378726c9
Mouton, A.
ac5730ce-83b5-4d71-820b-eb5bc6ba8839
May 2015
Vezza, P.
b8f933f4-bd6e-468b-835c-ada608d08ecc
Martinez-Capel, F.
8807606a-3389-4f8a-874c-4ca346575e09
Muñoz-Mas, R.
cde898b8-e30e-4c6d-9819-dec8378726c9
Mouton, A.
ac5730ce-83b5-4d71-820b-eb5bc6ba8839
Vezza, P., Martinez-Capel, F., Muñoz-Mas, R. and Mouton, A.
(2015)
Random forests to evaluate biotic interactions in fish distribution models.
Environmental Modelling & Software, 67, .
(doi:10.1016/j.envsoft.2015.01.005).
Abstract
Previous research indicated that high predictive performance in species distribution modelling can be obtained by combining both biotic and abiotic habitat variables. However, models developed for fish often only address physical habitat characteristics, thus omitting potentially important biotic factors. Therefore, we assessed the impact of biotic variables on fish habitat preferences in four selected stretches of the upper Cabriel River (E Spain). The occurrence of Squalius pyrenaicus and Luciobarbus guiraonis was related to environmental variables describing biotic interactions (inferred by relationships among fish abundances) and channel hydro-morphological characteristics. Random Forests (RF) models were trained and then validated using independent datasets. To build RF models, the conditional variable importance was used together with the model improvement ratio technique. The procedure showed effectiveness in identifying a parsimonious set of not correlated variables, which minimize noise and improve model performance in both training and validation phases. Water depth, channel width, fine substrate and water-surface gradient were selected as most important habitat variables for both fish. Results showed clear habitat overlapping between fish species and suggest that competition is not a strong factor in the study area.
Text
article/pii/S1364815215000249
- Other
Restricted to Repository staff only
More information
Accepted/In Press date: 8 January 2015
e-pub ahead of print date: 21 February 2015
Published date: May 2015
Organisations:
Water & Environmental Engineering Group
Identifiers
Local EPrints ID: 403143
URI: http://eprints.soton.ac.uk/id/eprint/403143
ISSN: 1364-8152
PURE UUID: 349a8d02-36c7-414c-81b4-6a86ad18a0fe
Catalogue record
Date deposited: 24 Nov 2016 16:25
Last modified: 15 Mar 2024 03:35
Export record
Altmetrics
Contributors
Author:
P. Vezza
Author:
F. Martinez-Capel
Author:
R. Muñoz-Mas
Author:
A. Mouton
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics