Predicting assemblages and species richness of endemic fish in the upper Yangtze River

He, Yongtao; Wang, Jianwei; Lek-Ang, Sithan; Lek, Sovan

doi:10.1016/j.scitotenv.2010.04.052

Cited by 42 publications

(45 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On contrary, ecological predictions for the endemic fish species which showed better defined climate and habitat requirements should be more accurately. These results will benefit a lot to the conservation of biodiversity for fish species in China, since there are numerous of endemic and specialized fish species lived in the lakes across China, and urgent stages were planned to conserve the fish species based on the prediction results (He et al, 2010). However, it is worth noting that in our study, temperature range size didn't show a significantly affect on the model performance, this founding contradicted some former results in fish species (Grenouillet et al, 2011).…”

Section: Discussioncontrasting

confidence: 78%

“…Nevertheless, it was not so surprise cause RF model gives the predictions by generating thousands of trees and aggregated with an average (Breiman, 2001), and the algorithm allow the model to avoid over-fit, this procedure could improve the predictive performance and reduce the variance (Elith et al, 2008). Thus, RF could be a robust technical modelling for species distribution prediction (He et al, 2010;Cheng et al, 2012;Grenouillet et al, 2011). Actually, plenty of publications have noted the algorithm which Random Forest relied on, they thus present the ensemble modelling framework which aggregated several single models and given the average or consensus results (Araújo and New, 2007).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Uncertainty in ensemble modelling of large-scale species distribution: Effects from species characteristics and model techniques

Guo

Lek

et al. 2015

Ecological Modelling

Self Cite

View full text Add to dashboard Cite

Section: Discussioncontrasting

confidence: 78%

Section: Discussionmentioning

confidence: 99%

Uncertainty in ensemble modelling of large-scale species distribution: Effects from species characteristics and model techniques

Guo

Lek

et al. 2015

Ecological Modelling

Self Cite

View full text Add to dashboard Cite

“…According to IUCN, 56% of freshwater Mediterranean species are threatened (Smith and Darwall, 2006) and, given the high degree of endemicity of biota and its high vulnerability to habitat alteration, more research is currently needed on local and native fish populations (Corbacho and Sánchez, 2001;Doadrio, 2002). The conservation of fish diversity is one of the most critical issues facing the preservation of Mediterranean biodiversity (Smith and Darwall, 2006); and, due to its sensitivity to human disturbances, fish species richness is widely used as a primary indicator of ecological change and as a criterion for the selection of conservation areas (van Jaarsveld et al, 1998;Lek et al, 2005;He et al, 2010). Increasing knowledge about the relationships between environmental features and fish populations is therefore essential for the design of effective habitat conservation and river restoration actions.…”

Section: Introductionmentioning

confidence: 99%

A comparison of artificial neural networks and random forests to predict native fish species richness in Mediterranean rivers

Olaya-Marín

Martínez‐Capel

Vezza

2013

Knowl. Managt. Aquatic Ecosyst.

View full text Add to dashboard Cite

Key-words:Artificial neural networks, random forests, native fish, species richness, Mediterranean rivers Machine learning (ML) techniques have become important to support decision making in management and conservation of freshwater aquatic ecosystems. Given the large number of ML techniques and to improve the understanding of ML utility in ecology, it is necessary to perform comparative studies of these techniques as a preparatory analysis for future model applications. The objectives of this study were (i) to compare the reliability and ecological relevance of two predictive models for fish richness, based on the techniques of artificial neural networks (ANN) and random forests (RF) and (ii) to evaluate the conformity in terms of selected important variables between the two modelling approaches. The effectiveness of the models were evaluated using three performance metrics: the determination coefficient (R 2 ), the mean squared error (MSE) and the adjusted determination coefficient (R 2 adj ) and both models were developed using a k-fold crossvalidation procedure. According to the results, both techniques had similar validation performance (R 2 = 68% for RF and R 2 = 66% for ANN). Although the two methods selected different subsets of input variables, both models demonstrated high ecological relevance for the conservation of native fish in the Mediterranean region. Moreover, this work shows how the use of different modelling methods can assist the critical analysis of predictions at a catchment scale. RÉSUMÉUne comparaison des réseaux de neurones et des forêts aléatoires pour prédire la richesse en espèces de poissons indigènes dans les rivières méditerranéennes Les techniques d'apprentissage automatique (ML) sont devenues importantes pour aider à la décision dans la gestion et la conservation des écosystèmes aquatiques d'eau douce. Étant donné le grand nombre de techniques ML pour amélio-rer la compréhension de l'utilité des ML en écologie, il est nécessaire de réaliser des études comparatives de ces techniques comme analyse préparatoire pour des applications de modèles futurs. Les objectifs de cette étude étaient : (i) de comparer la fiabilité et la pertinence écologique de deux modèles prédictifs pour la richesse de poisson, basé sur les techniques de réseaux de neurones artificiels (ANN) et les forêts aléatoires (RF) et (ii) d'évaluer la conformité en termes de sélection des variables importantes entre les deux approches de modélisa-tion. L'efficacité des modèles a été évaluée au moyen de trois indicateurs de Article published by EDP Sciences E.J. Olaya-Marín et al.: Knowl. Managt. Aquatic Ecosyst. (2013) 409, 07 performance : le coefficient de détermination (R 2 ), l'erreur quadratique moyenne (MSE) et le coefficient de détermination ajusté (R 2 adj ) et les deux modèles ont été développés en utilisant une procédure de validation croisée k-fold. Selon les résul-tats, les deux techniques ont des performances de validation similaires (R 2 = 68 % pour RF et R 2 = 66 % pour ANN). Bien que les deux...

show abstract

“…To model species distribution, Random Forests (RF, Breiman, 2001), a statistical method based on an automatic combination of decision trees, is currently considered a promising technique in ecology (Cutler et al, 2007;Franklin, 2010;Drew et al, 2011;Cheng et al, 2012). RF has been applied in freshwater fish studies (Buisson et al, 2010;Grenouillet et al, 2011;Markovic et al, 2012) and several authors have shown that, compared to other methodologies, RF often reach top performance in building predictive models of species distribution (Svetnik et al, 2003;Siroky, 2009;He et al, 2010;Mouton et al, 2011). Moreover, RF has been recently included in mesohabitat simulation tools, i.e., MesoHABSIM (Parasiewicz et al, 2013;Vezza et al, 2014a) to model fish ecological response to hydro-morphological alterations.…”

mentioning

confidence: 99%

Random forests to evaluate biotic interactions in fish distribution models

Vezza

Muñoz‐Mas

Martínez‐Capel

et al. 2015

Environmental Modelling & Software

View full text Add to dashboard Cite

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 interspecific interactions (inferred by relationships among fish abundances) and channel hydro-morphological characteristics. Random Forests (RF) models were trained and then validated using independent datasets. In both training and validation phases, RF showed high performance. 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 interspecific competition is not a strong factor in the study area.

show abstract

Predicting assemblages and species richness of endemic fish in the upper Yangtze River

Cited by 42 publications

References 63 publications

Uncertainty in ensemble modelling of large-scale species distribution: Effects from species characteristics and model techniques

Uncertainty in ensemble modelling of large-scale species distribution: Effects from species characteristics and model techniques

A comparison of artificial neural networks and random forests to predict native fish species richness in Mediterranean rivers

Random forests to evaluate biotic interactions in fish distribution models

Contact Info

Product

Resources

About