Neural networks in fisheries research

Suryanarayana, I.; Braibanti, A.; Rao, R. Sambasiva; Ramam, V. Anantha; Sudarsan, D; Rao, G. Nageswara

doi:10.1016/j.fishres.2008.01.012

Cited by 61 publications

(42 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most common NN type used in the field of fish biology and fisheries research has been multi-layer perception (MLP; Suryanarayana et al, 2008). However, a GRNN model was selected here because it does not face the frequently encountered local minima problem in feed forward back-propagation algorithms (Cigizoglu, 2005).…”

Section: Data Analysesmentioning

confidence: 99%

Response of fish assemblages to water quality in boreal rivers

Sutela

Vehanen²,

Jounela³

2010

Hydrobiologia

View full text Add to dashboard Cite

The relationship between fluvial fish assemblages and environmental variables including water quality was studied by nonmetric multidimensional scaling (NMS) and generalised regression neural network (GRNN). Fish assemblages in the studied boreal rivers in Central Finland showed a higher response to water quality than to other environmental variables such as altitude and river width. Of the water quality parameters, total phosphorus, oxygen saturation in winter and solids had the highest influence on fish assemblages. Brown trout (Salmo trutta L.) responded to water quality strongly by favouring pristine waters. Among other fish species, the responses were lighter, and the relative contribution of environmental variables varied. Percentage of fishless sites, i.e. no catch in electrofishing, was 4.4% when pH C 6, and 38.2% when pH \ 6. However, the most effective way to influence the fish assemblage composition, and to raise the fish-based FIFI integrity index value, would be to reduce loading of solids and phosphorus, rather than depressing acidification.

show abstract

Section: Data Analysesmentioning

confidence: 99%

Response of fish assemblages to water quality in boreal rivers

Sutela

Vehanen²,

Jounela³

2010

Hydrobiologia

View full text Add to dashboard Cite

show abstract

“…These techniques have frequently been used for major groups of aquatic organisms, i.e., fish (Suryanarayana et al, 2008;Penczak et al, 2012), macroinvertebrates (Lencioni et al, 2007;Kim et al, 2008), algae (Lee et al, 2003;Jeong et al, 2006) whereas macrophyte data have been treated by ANNs relatively rarely (Samecka-Cymerman et al, 2007). Neural networks introduced new aspects into analyses of relationships between organisms and their habitat.…”

Section: Introductionmentioning

confidence: 99%

Artificial neural network modelling of macrophyte indices based on physico-chemical characteristics of water

et al. 2013

View full text Add to dashboard Cite

The study focused on modelling of macropyte indices against physico-chemical parameters of waters by artificial neural networks. Several macrophyte diversity indices were analysed (species richness-N, the Shannon index-H 0 , the Simpson index-D, and the Pielou index-J) as well as the ecological status index (the Macrophyte Index for Rivers-MIR). The aim of the study was to verify knowledge about potential application of macrophytes in the environmental monitoring. A Multi-Layer Perceptron type of network was used in the analyses. The study included 260 river sites located throughout Poland. Alkalinity, conductivity, pH, nitrate and ammonium nitrogen, reactive and total phosphorus, and biochemical oxygen demand were used as the explanatory variables. The quality of the constructed models was assessed using calculated errors (RMSE and NRMSE) and r Pearson's linear correlation coefficient. The neural network for the MIR index was characterised by the highest quality. Neural networks for other diversity indices (N, H 0 , D, and J) did not provide adequate results for modelling, which shows their ineffectiveness biological monitoring. Sensitivity analysis revealed the influence of each variable to the models. It indicated that modelled values of MIR are most strongly influenced by total phosphorus and alkalinity.

show abstract

“…This nonsupervised artificial neural network method allows the analysis of complex data sets (Kohonen, 2001) and is a powerful tool for describing species distribution and assemblages (Lek et al, 2005;Suryanarayana et al, 2008). The SOM consists of input and output layers connected with computational weights (i.e.…”

Section: Discussionmentioning

confidence: 99%

Spatio‐temporal variations in fish assemblages in a tropical regulated lower river course: an environmental guild

Jutagate

Lek

Sawusdee

et al. 2011

River Research & Apps

View full text Add to dashboard Cite

Fish assemblage patterns were studied in the lower river reach of the Uthokawiphatprasit anti-salt dam, 6 km upstream from the Pak Panang River mouth, Southern Thailand, where the dam was opened occasionally depending on the upstream water level. Matrix data of the presence-absence of 71 fish species in 102 surveys was used in the analysis by applying a self-organizing map (SOM) model. The trained SOM (lattice 8 Â 7) showed that after 6 years of operation, five assemblage patterns were distinguished. These patterns described the probability of the occurrence of fish in each fish environmental guild, which according to changes in flow and water geomorphology. Clusters Ia and Ib were mostly the surveys in upstream stations and occupied by fish in potamonic guilds, whereas the fish in the estuarine guild and marine guilds showed a high probability of occurring in clusters IIa, IIb and IIc, which belonged to the surveys in downstream stations. The surveys of the stations near the dam (i.e. stations 5 and 6) during the opening phase were contained in cluster IIb. The Kruskal-Wallis test showed that there was no statistical difference in the probability of occurrence among assemblages of the diadromous, catadromous and semi-anadromous fishes but not the amphidromous fishes, which had a low probability of occurrence in clusters Ia and Ib. The fish assemblages were arrayed along a longitudinal gradient, where salinity and pH were the most important controlling variables and explained 94.0% of the total inertia.

show abstract

Neural networks in fisheries research

Cited by 61 publications

References 85 publications

Response of fish assemblages to water quality in boreal rivers

Response of fish assemblages to water quality in boreal rivers

Artificial neural network modelling of macrophyte indices based on physico-chemical characteristics of water

Spatio‐temporal variations in fish assemblages in a tropical regulated lower river course: an environmental guild

Contact Info

Product

Resources

About