Assessment of Groundwater Quality by Means of Self-Organizing Maps: Application in a Semiarid Area

Abstract The Kohonen neural network was applied to hydrochemical data from the Detritic Aquifer of the Lower Andarax, situated in a semiarid zone in the southeast of Spain. An activation map was obtained for each of the sampling points, in which the spatial distribution of the activated neurons indicated different water qualities. To extract the information contained in the activation maps, they were divided into nine quadrats. Cartesian coordinates were assigned to each quadrant (x, y), and for each sampling point, three derived variables were selected, which were assigned the values x and y of the corresponding quadrat. A classification was defined based on this simple matrix system which allows an easy and rapid means of evaluating the water quality. This assessment highlights the various processes that affect groundwater quality. The method generates output that is easier to interpret than from traditional statistical methods. The information is extracted from the activation maps without significant loss of information. The method is proposed for assessing water quality in hydrogeochemically complex areas, where large numbers of observations are made.

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

[2]  B. Helena,et al.  Temporal evolution of groundwater composition in an alluvial aquifer (Pisuerga river, Spain) by Principal Component Analysis. , 2000 .

[3]  Giles M. Foody,et al.  Applications of the self-organising feature map neural network in community data analysis , 1999 .

[4]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[5]  Dana W. Kolpin,et al.  Assessing groundwater vulnerability to agrichemical contamination in the Midwest US , 1999 .

[6]  A. G. Frenich,et al.  Application of the Kohonen neural network in coastal water management: methodological development for the assessment and prediction of water quality. , 2001, Water research.

[7]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[8]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .

[9]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[10]  Yang Li,et al.  A new method based on counterpropagation network algorithm for chemical pattern recognition , 1999 .

[11]  L. Canter,et al.  Nitrates in Groundwater , 1996 .

[12]  F. Gümrah,et al.  The Application of Artificial Neural Networks for the Prediction of Water Quality of Polluted Aquifer , 2000 .

[13]  Á. Vallejos,et al.  Factors which determine the hydrogeochemical behaviour of karstic springs. A case study from the Betic Cordilleras, Spain , 2001 .

[14]  Virginia M. Johnson,et al.  Accuracy of Neural Network Approximators in Simulation-Optimization , 2000 .

[15]  Ingrid M. Schleiter,et al.  Modelling water quality, bioindication and population dynamics in lotic ecosystems using neural networks , 1999 .

[16]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[17]  M. Karydis.  Scaling methods in assessing environmental quality: A methodological approach to eutrophication , 1992, Environmental monitoring and assessment.

[18]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[19]  A. Vengosh,et al.  Saline groundwater in Israel: its bearing on the water crisis in the country , 1994 .

[20]  Gerrit Kateman,et al.  USING ARTIFICIAL NEURAL NETWORKS FOR SOLVING CHEMICAL PROBLEMS .2. KOHONEN SELF-ORGANIZING FEATURE MAPS AND HOPFIELD NETWORKS , 1994 .

[21]  R. Reyment,et al.  Statistics and Data Analysis in Geology. , 1988 .