Patterning and predicting aquatic insect richness in four West-African coastal rivers using artificial neural networks

Abstract

Key-words:insect richness, artificial neural network, prediction, coastal rivers, West AfricaDespite their importance in stream management, the aquatic insect assemblages are still little known in West Africa. This is particularly true in South-Eastern Ivory Coast, where aquatic insect assemblages were hardly studied. We therefore aimed at characterising aquatic insect assemblages on four coastal rivers in South-Eastern Ivory Coast. Patterning aquatic insect assemblages was achieved using a Self-Organizing Map (SOM), an unsupervised Artificial Neural Networks (ANN) method. This method was applied to pattern the samples based on the richness of five major orders of aquatic insects (Diptera, Ephemeroptera, Coleoptera, Trichoptera and Odonata). This permitted to identify three clusters that were mainly related to the local environmental status of sampling sites. Then, we used the environmental characteristics of the sites to predict, using a multilayer perceptron neural network (MLP), trained by BackPropagation algorithm (BP), a supervised ANN, the richness of the five insect orders. The BP showed high predictability (0.90 for both Diptera and Trichoptera, 0.84 for both Coleoptera and Odonata, 0.69 for Ephemeroptera). The most contributing variables in predicting the five insect order richness were pH, conductivity, total dissolved solids, water temperature, percentage of rock and the canopy. This underlines the crucial influence of both instream characteristics and riparian context. RÉSUMÉAssemblage et prédiction de la richesse taxonomique de l'entomofaune de quatre rivières de la côte ouest-africaine par des réseaux de neurones artificiels Mots-clés :richesse taxonomique des insectes, réseau de neurones artificiels, rivières côtières, Malgré leur importance dans la gestion des hydrosystèmes, les insectes aquatiques restent peu connus en Afrique de l'Ouest et particulièrement dans le Sudest de la Côte d'Ivoire. Cette étude vise donc à caractériser les assemblages des insectes aquatiques dans quatre rivières côtières du Sud-est ivoirien. La méthode non supervisée des réseaux de neurones artificiels, cartes auto-organisatrices (SOM), a été utilisée pour établir le patron de distribution des cinq ordres les plus diversifiés. Elle a permis d'identifier trois clusters qui sont principalement en relation avec les conditions environnementales des sites d'échantillonnage. L'algorithme de rétropropagation (BP), qui est un réseau de neurones supervisé, a servi Afrique de l'Ouest à la prédiction de la richesse taxonomique des cinq ordres d'insectes à partir des caractéristiques environnementales des sites et a montré une forte prédictibilité (0,90 pour les Diptères et Trichoptères, 0,84 pour les Coléoptères et Odonates, 0,69 pour les Éphéméroptères). Les variables environnementales qui contribuent significativement à la prédiction de la richesse taxonomique des insectes aquatiques étaient le pH, la conductivité, le taux de solides dissous, la température de l'eau, le pourcentage de bloc et la canopée. Ces résultats ...

Predicting Factors That Influence Fish Guild Composition in Four Coastal Rivers (Southeast Ivory Coast) Using Artificial Neural Networks

“…Riparian vegetation helps determine what, how much and when materials from upland areas enter the hydrosystem. These conditions could favor the presence of refuges (tree branch and trunk, and roots) in the flooded vegetation and food prey (invertebrates, algae fixed to the substrate, arthropods and fruits) falling from the flooded vegetation (Casatti et al, 2003;de Melo et al, 2009;Edia et al, 2010). Leaves incorporated into the channel substrate help the establishment of a varied fauna that can be used as food by fish (Uieda and Uieda, 2001).…”

“…explanatory importance) of each predictive variable with partial derivatives (PaD) algorithm (Dimopoulos et al, 1995, Gevrey et al, 2003. For more details concerning the BP algorithm and its applications, see Rumelhart et al (1986), Lek and Guégan (1999), Lek et al (2000), Gevrey et al (2003), Park et al (2003), Edia et al (2010). An environmental descriptor was regarded as significant to the model when its contribution was higher than 10% (Brosse and Lek, 2002).…”

“…In order to preserve water quality and the diversity of biological communities, it appears therefore necessary to manage these hydrosystems. Such management requires the knowledge of how environmental variables affect the richness, taxonomic and trophic guild structure of these communities (Smogor and Angermeier, 1999;Edia et al, 2010). Although tropical hydrosystems in West Africa are important habitats, only a few studies have been carried out on trophic organization of the ecosystems (Villanueva, 2004;Da Costa and Tito De Moraïs, 2007;Traoré et al, 2008).…”

The rainy season increases the abundance and richness of the aquatic insect community in a Neotropical reservoir

“…Moreover, the site is included in the Cerrado biome, which has two well-defined seasons: dry in winter and wet in summer, with most of the rainfall occurring from November to March (De Filippo et al, 1999). Aquatic insects were collected using a Petersen grab device (Davanso and Henry, 2006) at deep sites to obtain three samples at each site; a hand net (mesh 250 µm) was used at shallow sites (Edia et al, 2010), with a sampling effort of five minutes per collection point. The two methodologies were used because they are complementary and faithfully represent the aquatic insect community.…”

Diversity, distribution and habitat requirements of aquatic insect communities in tropical mountain streams (South-eastern Guinea, West Africa)

“…In this study, we focussed on mountain streams in the Simandou Range located in the south-east of the Republic of Guinea (West Africa). Long-term biomonitoring surveys of aquatic insects were carried out in several large rivers of West Africa during the Onchocerciasis (River Blindness) Control Programme (Le´veˆque et al, 2003) and recent studies have been carried out in Ivory Coast (Edia et al, 2010;Kouame´et al, 2011;Diomande´et al, 2014), Ghana (Benbow et al, 2014) and Nigeria (Olomukoro and Ezemonye, 2007;Arimoro et al, 2011). To our knowledge, aquatic insects in streams of Guinea in general and particularly those from the Simandou streams remain largely undocumented.…”