No abstract

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...

No abstract

Luciobarbus guiraonis (Eastern Iberian barbel) is an endemic fish species restricted to Spain, mainly distributed in the Júcar River Basin District. Its study is important because there is little knowledge about its biology and ecology. To improve the knowledge about the species distribution and habitat requirements, nonlinear modelling was carried out to predict the presence/absence and density of the Eastern Iberian barbel, based on 155 sampling sites distributed throughout the Júcar River Basin District (Eastern Iberian Peninsula). We used multilayer feed-forward artificial neural networks (ANN) to represent nonlinear relationships between L. guiraonis descriptors and variables regarding the physical habitat and biological components (macroinvertebrates, fish, riparian forest). The gradient descent algorithm was implemented to find the optimal model parameters; the importance of the ANN’s input variables was determined by the partial derivatives method. The predictive power of the model was evaluated with the Cohen’s kappa (k), the correctly classified instances (CCI), and the area under the curve (AUC) of the receiver operator characteristic (ROC) plots. The best model predicted presence/absence with a high performance (k= 0.66, CCI= 87% and AUC= 0.85); the prediction of density was moderate (CCI = 62%, AUC=0.71 and k= 0.43). The fundamental variables describing the presence/absence were; solar radiation (the highest contribution was observed between 2000 and 4200 WH/m2), drainage area (with the strongest influence between 3000 and 5.000 km2), and the proportion of exotic fish species (with relevant contribution between 50 and 100%). In the density model, the most important variables were the coefficient of variation of mean annual flows (relative importance of 50.5%) and the proportion of exotic fish species (24.4%). The models provide important information about the relation of L. guiraonis with biotic and abiotic variables, this new knowledge can help develop future studies and management plans for the conservation of this species in the Júcar River Basin District and, potentially, for the conservation of other endemic fish species of Barbus and Luciobarbus in Mediterranean rivers.

Summary This study provides length‐weight relationship (LWRs) information for two fish species (family Cyprinidae) in two headwater streams of the Júcar River Basin (Eastern Iberian Peninsula). Both species are endemic to the Iberian Peninsula and have no previous LWR estimates.