Long-term changes in fish assemblages of the Widawka and Grabia Rivers (Poland): pattern recognition with a Kohonen artificial neural network

Kruk, Andrzej

doi:10.1051/limn:2007004

Cited by 13 publications

(16 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The assemblage definition based on the dominance of species (Echelle et al, 1972;Johnson et al, 1977;Ryder and Kerr, 1978;Matthews, 1998) was supported by the data from this study as well as others conducted in the European temperate zone (Kruk, 2007a;Kruk et al, 2007). We could not find any significant impact of impoudment on differentiation and numbers of assemblages except for the clearly separated assemblage distingushed on the basis of samples collected in the Furnas Stream, but only from samples collected in the post-impoudment period.…”

Section: Discussionsupporting

confidence: 87%

“…Additionally, samples assigned to nearby neurons differed considerably if those neurons belonged to different clusters, which were identified with use of a hierarchical cluster analysis (Ward linkage, Euclidean distance). The SOM software also allows for visualization of species importance in the output neurons (named component planes) in the form of a greyness gradient (Kruk, 2007a). Summing up, the Kohonen algorithm recognized the structure of the data set, distinguished clusters, neurons and assigned fish samples to them Kruk, 2007a).…”

Section: Discussionmentioning

confidence: 99%

“…The SOM software also allows for visualization of species importance in the output neurons (named component planes) in the form of a greyness gradient (Kruk, 2007a). Summing up, the Kohonen algorithm recognized the structure of the data set, distinguished clusters, neurons and assigned fish samples to them Kruk, 2007a).…”

Section: Discussionmentioning

confidence: 99%

“…More details regarding the Kohonen algorithm are available in papers which applied the algorithm for community studies (Chon et al, 1996;Giraudel et al, 2000;Park et al, 2003;Penczak et al, 2004;Kruk, 2006Kruk, , 2007a. We would like to stress that the SOM description is more detailed in our former papers which are cited here.…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Impacts of a reservoir on fish assemblages of small tributaries of the Corumbá river, Brazil

Penczak

Agostinho

Gomes

et al. 2008

River Research & Apps

View full text Add to dashboard Cite

Fish community surveys were conducted in five tributaries of the Corumbá River before and after damming. Electrofishing samples were collected monthly in the pre-impoundment period (March 1996 to August 1996 and 15 in the post-impoundment period (September 1996 to February 1999. A self-organizing map (SOM, an Artificial Neural Network algorithm) was used to represent the patterns of fish assemblages. Samples collected in both the pre-and post-impoundment periods were randomly dispersed on the SOM, and, therefore, a clear and significant pattern of separation between samples collected during these two time periods was not found. Mean and maximum water depth, which is correlated with ground water level, did not significantly separate the pre-and post-impoundment samples. However, we found significant differences between the two periods for water temperature, pH, conductivity, DO and current velocity, but abundances of fish species (summarized in the clusters identified by the SOM) did not differ significantly. Instead, the validity of the clusters distinguished by the SOM was confirmed by significant differences in some biotic variables: species richness, equitability and log transformed total abundance. Indicator species values identified the most preferred cluster (and respective complex of environmental factors) for a given species. Only one cluster did not contain any significant species indicator values, but it was dominated by samples from the Furnas Stream, which was the only effluent that could be entered by fish from the main river channel after the damming owing to its location below the dam, which has no fish ladder.

show abstract

Section: Discussionsupporting

confidence: 87%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Impacts of a reservoir on fish assemblages of small tributaries of the Corumbá river, Brazil

Penczak

Agostinho

Gomes

et al. 2008

River Research & Apps

View full text Add to dashboard Cite

show abstract

“…(), and Li et al . () as well as in our former papers that applied the SOM for ordering fish population data (Penczak et al ., ; Kruk, ; Kruk et al ., ; Kruk and Penczak, ).…”

Section: Methodsmentioning

confidence: 98%

The Role of Streams of Different Sizes in Recovery of Fish Fauna in the Pilica River Catchment

et al. 2013

Self Cite

View full text Add to dashboard Cite

Fish and lampreys were sampled by electrofishing in the Pilica River tributaries (the Vistula catchment, Poland) in 1992–1994 and 2003–2005. The patterns in fish assemblages were recognized on the basis of fish biomass using Kohonen's self‐organizing map (SOM) technique, combined with the indicator values (IndVal) for assessment of associations of fish species with particular SOM regions (and respective environmental conditions). Although the fish samples were clustered mostly according to the stream features (size, regulation, and pollution), a weaker temporal gradient indicated a recovery of the ichthyofauna in some smaller streams. The larger tributaries served as sources of colonisers for both the Pilica and the smaller streams. The differences between SOM subclusters in the quality of the aquatic environment were effectively presented with certain biological measures, including the dominances of potentially large species and non‐psammophilous rheophils, which are proposed as good bioindicators. It is worth mentioning that some closely related species (ide and dace, silver bream and bream, golden loach and spined loach, and Ukrainian lamprey and brook lamprey) were significantly associated with different SOM regions (and respective environmental conditions), perhaps in this way avoiding competition. Copyright © 2013 John Wiley & Sons, Ltd.

show abstract

Natural Regeneration of Fish Assemblages in the Pilica River After a Reduction of Point‐source Pollution

Kruk

Penczak

2012

River Research & Apps

Self Cite

View full text Add to dashboard Cite

Electrofishing was conducted along the Pilica River, the biggest West tributary of the Vistula, Poland. This paper presents a comparison between the 1990s (1994-1995, 63 sites) and 2000s (2003-2005, 64 sites), that is, because the water quality started improving after 1989. In the Pilica, there is an increased risk of masking relationships between fish distribution and abiotic factors because a dam without a fish pass was constructed in the middle course of the river in 1973, perhaps resulting in fewer possibilities for potential colonizers reaching river fragments fit for colonization. The main aim of this study was to check if natural fish fauna regeneration took place in the river following a significant sewage input reduction. The fish samples were classified with a Kohonen artificial neural network and assigned to two main clusters (X and Y) and, respectively, two pairs of subclusters (X 1 , X 2 ; Y 1 , Y 2 ) of neurons. No species attained its significantly highest biomass and/or frequency (expressed as IndVal) in X 2 (in which samples from the 1990s dominated), whereas 21 species did so in Y 1 or Y 2 (containing almost all of the samples from the 2000s), better testifying to the aquatic environment at the sites where the samples assigned to two latter subclusters come from. Moreover, significantly higher values for Y 1 and/or Y 2 when compared with X 2 were recorded in the richness of the fish species, the total fish biomass and total rheophilic fish biomass. In summary, the positive reaction of ichthyofauna to the improvement of the water quality, stated after 1989, was not recorded during the sampling in 1994-1995, but with a considerable delay in [2003][2004][2005]. It should be emphasized that the improvement in fish assemblages was recorded in the Pilica both upstream and downstream from the dam reservoir. A good ecological status was recorded even for some samples from the 1990s. They were collected in the lower river course, where the fish could move freely from the Vistula. This testifies the combined role of the presence of potential colonizers and the functioning ecological corridors for fish assemblages in a river system under human impact.

show abstract

Long-term changes in fish assemblages of the Widawka and Grabia Rivers (Poland): pattern recognition with a Kohonen artificial neural network

Cited by 13 publications

References 57 publications

Impacts of a reservoir on fish assemblages of small tributaries of the Corumbá river, Brazil

Impacts of a reservoir on fish assemblages of small tributaries of the Corumbá river, Brazil

The Role of Streams of Different Sizes in Recovery of Fish Fauna in the Pilica River Catchment

Natural Regeneration of Fish Assemblages in the Pilica River After a Reduction of Point‐source Pollution

Contact Info

Product

Resources

About