A data-mining framework for exploring the multi-relation between fish species and water quality through self-organizing map.

The steep slopes of rivers can easily lead to large variations in river water quality during typhoon seasons in Taiwan, which may poses significant impacts on riverine eco-hydrological environments. This study aims to investigate the relationship between fish communities and water quality by using artificial neural networks (ANNs) for comprehending the upstream eco-hydrological system in northern Taiwan. We collected a total of 276 heterogeneous datasets with 8 water quality parameters and 25 fish species from 10 sampling sites. The self-organizing feature map (SOM) was used to cluster, analyze and visualize the heterogeneous datasets. Furthermore, the structuring index (SI) was adopted to determine the relative importance of each input variable of the SOM and identify the indicator factors. The clustering results showed that the SOM could suitably reflect the spatial characteristics of fishery sampling sites. Besides, the patterns of water quality parameters and fish species could be distinguishably (visually) classified into three eco-water quality groups: 1) typical upstream freshwater fishes that depended the most on dissolved oxygen (DO); 2) typical middle-lower reach riverine freshwater fishes that depended the most on total phosphorus (TP) and ammonia nitrogen; and 3) low lands or pond (reservoirs) freshwater fishes that depended the most on water temperature, suspended solids and chemical oxygen demand. According to the results of the SI, the representative indicators of water quality parameters and fish species consisted of DO, TP and Onychostoma barbatulum. This grouping result suggested that the methodology can be used as a guiding reference to comprehensively relate ecology to water quality. Our methods offer a cost-effective alternative to more traditional methods for identifying key water quality factors relating to fish species. In addition, visualizing the constructed topological maps of the SOM could produce detailed inter-relation between water quality and the fish species of stream habitat units.

[1]  Monique Polit,et al.  KSOM and MLP neural networks for on-line estimating the efficiency of an activated sludge process , 2006 .

[2]  Young-Seuk Park,et al.  Application of a self-organizing map to select representative species in multivariate analysis: A case study determining diatom distribution patterns across France , 2006, Ecol. Informatics.

[3]  T. Villmann,et al.  Topology Preservation in Self-Organizing Maps , 1999 .

[4]  A. Ghilarov,et al.  Ecosystem functioning and intrinsic value of biodiversity. , 2000 .

[5]  G. Lamberti,et al.  Scale-dependent influences on water quality, habitat, and fish communities in streams of the Kalamazoo River Basin, Michigan (USA) , 2006, Aquatic Sciences.

[6]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[7]  Gary K. Meffe,et al.  Principles of Conservation Biology , 1995 .

[8]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[9]  F. Chang,et al.  Assessing the natural and anthropogenic influences on basin-wide fish species richness. , 2016, The Science of the total environment.

[10]  J. Renno,et al.  Historical biogeography of South American freshwater fishes , 2006 .

[11]  陳 義雄,et al.  臺灣淡水魚類原色圖鑑 = A photographic guide to the inlandwater fishes of Taiwan , 2005 .

[12]  Christopher N. K. Mooers,et al.  Performance evaluation of the self‐organizing map for feature extraction , 2006 .

[13]  Li-Chiu Chang,et al.  Assessing the effort of meteorological variables for evaporation estimation by self-organizing map neural network , 2010 .

[14]  Deborah V. Chapman,et al.  Water Quality Assessments: A Guide to the Use of Biota, Sediments and Water in Environmental Monitoring , 1996 .

[15]  Berta Galán,et al.  Assessment of Self-Organizing Map artificial neural networks for the classification of sediment quality. , 2008, Environment international.

[16]  D. Campana,et al.  Channel degradation and restoration of an Alpine river and related morphological changes , 2014 .

[17]  Georgina M. Mace,et al.  Economic Analysis for Ecosystem Service Assessments , 2011 .

[18]  Kate A Brauman,et al.  Linking water quality and well-being for improved assessment and valuation of ecosystem services , 2012, Proceedings of the National Academy of Sciences.

[19]  M. Huijbregts,et al.  On the importance of trait interrelationships for understanding environmental responses of stream macroinvertebrates , 2016 .

[20]  S. Jähnig,et al.  Limiting factors and thresholds for macroinvertebrate assemblages in European rivers: Empirical evidence from three datasets on water quality, catchment urbanization, and river restoration , 2012 .

[21]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[22]  E. G. Xu,et al.  Spatial and temporal assessment of environmental contaminants in water, sediments and fish of the Salton Sea and its two primary tributaries, California, USA, from 2002 to 2012. , 2016, The Science of the total environment.

[23]  Naeem,et al.  Ecosystems and Human Well-Being: Biodiversity Synthesis , 2005 .

[24]  D. R. Khanna,et al.  Determination of water quality index for the evaluation of surface water quality for drinking purpose , 2013 .

[25]  Meiying Xu,et al.  Phylogenetic diversity, composition and distribution of bacterioplankton community in the Dongjiang River, China. , 2012, FEMS microbiology ecology.

[26]  Edwin E. Herricks,et al.  Exploring the ecological response of fish to flow regime by soft computing techniques , 2016 .

[27]  A. Alobaidy,et al.  Evaluating Raw and Treated Water Quality of Tigris River within Baghdad by Index Analysis , 2010 .

[28]  Michele Scardi,et al.  Modeling landings profiles of fishing vessels: An application of Self-Organizing Maps to VMS and logbook data , 2016 .

[29]  Juha Vesanto,et al.  SOM-based data visualization methods , 1999, Intell. Data Anal..

[30]  Edwin E. Herricks,et al.  A self-organizing radial basis network for estimating riverine fish diversity , 2013 .

[31]  Edwin E. Herricks,et al.  AI techniques for optimizing multi-objective reservoir operation upon human and riverine ecosystem demands , 2015 .

[32]  Mark A. J. Huijbregts,et al.  Comparing responses of freshwater fish and invertebrate community integrity along multiple environmental gradients , 2014 .

[33]  Sang-Hyun Park,et al.  Clustering of ant communities and indicator species analysis using self-organizing maps. , 2014, Comptes rendus biologies.

[34]  J. Castro,et al.  The Evolving Science of Stream Restoration , 2013 .

[35]  陳 義雄,et al.  台灣淡水及河口魚類誌 = The freshwater and estuarine fishes of Taiwan , 1999 .

[36]  Su-Ting Cheng,et al.  An integrated modeling approach to evaluate the performance of an oxygen enhancement device in the Hwajiang wetland, Taiwan , 2012 .

[37]  Edwin E. Herricks,et al.  Identifying natural flow regimes using fish communities , 2011 .

[38]  V. Simić,et al.  The utility of two marine community indices to assess the environmental degradation of lotic systems using fish communities. , 2016, The Science of the total environment.

[39]  Kuolin Hsu,et al.  Self‐organizing linear output map (SOLO): An artificial neural network suitable for hydrologic modeling and analysis , 2002 .

[40]  Young-Seuk Park,et al.  Response of Fish Communities to Various Environmental Variables across Multiple Spatial Scales , 2012, International journal of environmental research and public health.

[41]  Catarina I. Gonçalves,et al.  Ecological quality assessment of transitional waters based on fish assemblages in Portuguese estuaries: the Estuarine Fish Assessment Index (EFAI) , 2012 .

[42]  M. Pedro-Monzonís,et al.  Water accounting for stressed river basins based on water resources management models. , 2016, The Science of the total environment.

[43]  Li-Chiu Chang,et al.  Enforced self-organizing map neural networks for river flood forecasting , 2007 .

[44]  K. Pearson.  Mathematical Contributions to the Theory of Evolution. III. Regression, Heredity, and Panmixia , 1896 .

[45]  A. M. Kalteh,et al.  Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application , 2008, Environ. Model. Softw..

[46]  W. P. Cofino,et al.  Concepts in river ecology: implications for indicator development , 1997 .

[47]  Young-Seuk Park,et al.  Review of the Self-Organizing Map (SOM) approach in water resources: Commentary , 2009, Environ. Model. Softw..

[48]  M. Libalah,et al.  Biodiversity and Conservation of Tropical Montane Ecosystems in the Gulf of Guinea, West Africa , 2014 .

[49]  Kimmo Kiviluoto,et al.  Topology preservation in self-organizing maps , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[50]  Edwin E. Herricks,et al.  Developing fish community based ecohydrological indicators for water resources management in Taiwan , 2009, Hydrobiologia.

[51]  F. Chang,et al.  Hydrochemical, mineralogical and isotopic investigation of arsenic distribution and mobilization in the Guandu wetland of Taiwan , 2013 .

[52]  Tielin Shi,et al.  A Novel Technique for Data Visualization Based on SOM , 2005, ICANN.

[53]  R. Neves,et al.  Sensitivity of river fishes to climate change: The role of hydrological stressors on habitat range shifts. , 2016, The Science of the total environment.

[54]  Daniel P. Loucks,et al.  Water management: Current and future challenges and research directions , 2015 .

[55]  S. Lek,et al.  Applications of artificial neural networks for patterning and predicting aquatic insect species richness in running waters , 2003 .

[56]  Edwin E. Herricks,et al.  Defining the ecological hydrology of Taiwan Rivers using multivariate statistical methods , 2009 .

[57]  Pute Wu,et al.  Effects of virtual water flow on regional water resources stress: A case study of grain in China. , 2016, The Science of the total environment.

[58]  B. Cade,et al.  A gentle introduction to quantile regression for ecologists , 2003 .