Implementation of artificial neural networks in patterning and prediction of exergy in response to temporal dynamics of benthic macroinvertebrate communities in streams

DNA barcodes and their characteristic diagnostic sites analysis of Schizothoracinae fishes in Qinghai province

The Qinghai-Tibetan Plateau (QTP), the source and upper reaches of many Asian rivers, are crisscrossed by rivers and dotted with lakes. Schizothoracinae fishes, species native to the QTP, are distributed widely through these rivers and lakes. Over the past decades, ecological protection has become increasingly intense. The rapid acquisition of the genetic information and accurate gene sequence database are assumed to play an important role in the conservation of species diversity and biodiversity. In this study, 153 COI sequences (648bp in length) covering 13 species in 8 genera of Schizothoracinae fishes in Qinghai Province were used to determine whether barcode could identify Schizothoracinae species accurately. The average Kimura two parameter (K2P) genetic distances within and among species were 0.35% and 8.83%, respectively. The maximum K2P distance within species was observed in Gymnocypris eckloni (1.36%) while minimum K2P distance among species was observed between Chuanchia labiosa and Schizopygopsis pylzovi (0.23%). Overlaps existed in K2P distance intra- and inter- species based on both the genes. Eleven groups with 9 single-species groups and 2 multi-species groups were identified through Automatic Barcode Gap Discovery System, which were consistent with the overlaps of K2P distance. 96.7% as the accurate ratio for COI barcode was calculated and high solution was observed in the phylogenetic trees based on COI gene and Cyt b gene. Except for the similar results based on two genes above, COI barcode was more economical than Cyt b gene. The SOM model successfully predicted characteristic-diagnostic sites at species level: 36 characteristic-diagnostic sites from eight species, in which 12 from Gmnodiptychus pachycgeilus, 2 from Platypharodon extremus, 7 from Ptychobarbus kaznakovi, 2 from Schizopygopsis anteroventris, 2 from Schizopygopsis malacanthus, 3 from Schizopygopsis malacanthus chengi, 3 from Schizothorax dolichonema and 5 from Schizothorax lantsangensis. Our results show that Schizothoracinae fishes can be identified validly by using COI DNA barcode. Thirty-six characteristic-diagnostic sites were proposed to be applied into works of species identification for the Schizothoracinae fishes in Qinghai Province.

Application of artificial neural network models to analyse the relationships between Gammarus pulex L. (Crustacea, Amphipoda) and river characteristics

This study aimed at analysing the relationship between river characteristics and abundance of Gammarus pulex. To this end, four methods which can identify the relative contribution and/or the contribution profile of the input variables in neural networks describing the habitat preferences of this species were compared: (i) the "PaD" ("Partial Derivatives") method consists of a calculation of the partial derivatives of the output in relation to the input variables; (ii) the "Weights" method is a computation using the connection weights of the backpropagation Artificial Neural Networks; (iii) the "Perturb" method analyses the effect of a perturbation of the input variables on the output variable; (iv) the "Profile" method is a successive variation of one input variable while the others are kept constant at a fixed set of values. The dataset consisted of 179 samples, collected over a three-year period in the Zwalm river basin in Flanders, Belgium. Twenty-four environmental variables as well as the log-transformed abundance of Gammarus pulex were used in this study. The different contribution methods gave similar results concerning the order of importance of the input variables. Moreover, the stability of the methods was confirmed by gradually removing variables. Only in a limited number of cases a shift in the relative importance of the remaining input variables could be observed. Nevertheless, differences in sensitivity and stability of the methods were detected, probably as a result of the different calculation procedures. In this respect, the "PaD" method made a more severe discrimination between minor and major contributing environmental variables in comparison to the "Weights", "Profile" and "Perturb" methods. From an ecological point of view, the input variables "Ammonium" and to a smaller extent "COD", were selected by these methods as dominant river characteristics for the prediction of the abundance of Gammarus pulex in this study area.

Typology of diatom communities and the influence of hydro-ecoregions: a study on the French hydrosystem scale

By comparing diatom communities in natural and disturbed sites, indicators for different types and levels of anthropogenic disturbance can be found. As a first step, this study aims to describe the different natural and disturbed community types found throughout the French hydrosystem. 836 diatom samples were analysed with an unsupervised neural network, the self-organising-map, a well accepted method for community ordination. 11 different communities were identified, 5 corresponding to non-impacted or slightly impacted conditions and representing the diatom natural variability of our dataset. These 5 communities corresponded to 5 different hydro-ecoregions, i.e. 5 river types with similar geological context and range in altitude. The 6 other communities were typical of rivers under anthropogenic pressure. The influence of natural conditions within the hydro-ecoregions was overwhelmed by the nature and the intensity of the pollution at the sampling stations. This work was done in the context of the application and enforcement of the Water Framework Directive.

Hierarchical community classification and assessment of aquatic ecosystems using artificial neural networks

Benthic macroinvertebrate communities in stream ecosystems were assessed hierarchically through two-level classification methods of unsupervised learning. Two artificial neural networks were implemented in combination. Firstly, the self-organizing map (SOM) was used to reduce the dimension of community data, and secondly, the adaptive resonance theory (ART) was subsequently applied to the SOM to further classify the groups in different scales. Hierarchical grouping in community data efficiently reflected the impact of the environmental factors such as topographic conditions, levels of pollution, and sampling location and time across different scales. New community data not included in the training process were used to test the trained network model. The input data were appropriately grouped at different hierarchical levels by the trained networks, and correspondingly revealed the impact of environmental disturbances and temporal dynamics of communities. The hierarchical clusters based on a two-level classification method could be useful for assessing ecosystem quality and community variations caused by environmental disturbances.