Hydrology and Earth System Sciences www.hydrol-earth-syst-sci.net 1027-5606 1607-7938 11 4 2007 10.5194/hess-11-1309-2007 http://www.hydrol-earth-syst-sci.net/11/1309/2007/ http://www.hydrol-earth-syst-sci.net/11/1309/2007/hess-11-1309-2007.html http://www.hydrol-earth-syst-sci.net/11/1309/2007/hess-11-1309-2007.pdf 1309 1321 2007-05-11 Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map L. Peeters luk.peeters@geo.kuleuven.be F. Bação V. Lobo A. Dassargues Applied Geology and Mineralogy, KULeuven, Belgium Instituto Superior de Estat\'istica e Gestão de Informação, Universidade Nova de Lisboa, Campus de Campolide, Lisboa, Portugal Portuguese Naval Academy, Almada, Portugal Hydrogeology & Environmental Geology, ArGEnCo, University of Liege, Belgium The use of unsupervised artificial neural network techniques like the self-organizing map (SOM) algorithm has proven to be a useful tool in exploratory data analysis and clustering of multivariate data sets. In this study a variant of the SOM-algorithm is proposed, the GEO3DSOM, capable of explicitly incorporating three-dimensional spatial knowledge into the algorithm. The performance of the GEO3DSOM is compared to the performance of the standard SOM in analyzing an artificial data set and a hydrochemical data set. The hydrochemical data set consists of 131 groundwater samples collected in two detritic, phreatic, Cenozoic aquifers in Central Belgium. Both techniques succeed very well in providing more insight in the groundwater quality data set, visualizing the relationships between variables, highlighting the main differences between groups of samples and pointing out anomalous wells and well screens. The GEO3DSOM however has the advantage to provide an increased resolution while still maintaining a good generalization of the data set. Alvisi, S., Mascellani, G., Franchini, M., and Bardossy, A.: Water level forecasting through fuzzy logic and artificial neural network approaches, Hydrol. Earth Syst. Sci. 10, 1–17, 2006. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology: Artificial neural networks in hydrology. II: Hydrologic applications, J. Hydrol. Eng., 5(2), 124–137, 2000. Baç\~ao, F., Lobo, V., and Painho, M.: The self-organizing map, the Geo-SOM, and relevant variants for geosciences, Computers and Geosciences, 31(2), 155–163, 2005a. Bação, F., Lobo, V., and Painho, M.: Self-organizing maps as substitute for K-means clustering, in: International conference on computational science, edited by: Sunderarm, V. S., van Albada, G., Sloot, P., and Dongarra, J. J., International conference on computational science 2005, Lecture Notes in Computer Science, Springer-Verlag Berlin, Berlin, 3516, 476–483, 2005b. Chang, H. C., Kopaska-Merkel, D. C., and Chen H. C.: Identification of lithofacies using Kohonen self-organizing maps, Computers and Geosciences, 28(2), 223–229, 2002. Coppola, E., Szidarovsky, F., Poulton, M., and Charles, E.: Artificial neural network approach for predicting transient water levels in a multilayered groundwater system under variable state, pumping and climate conditions, J. Hydrol. Eng., 8(6), 348–360. 2003. Davis, J C.: Statistics and data analysis in geology, John Wiley & Sons, Inc, New York, 1986. Databank Ondergrond Vlaanderen: http://dov.vlaanderen.be, 2006. Güler, C., Thyne, G D., and McCray, J E.: Evaluation of graphical and multivariate statistical methods for classification of water chemistry data, Hydrogeology J., 10(4), 455–474, 2002. Himberg, J.: A SOM Based Cluster Visualization and Its Application for False Coloring, Proceedings of International Joint Conference on Neural Networks (IJCNN2000), 3, 587–592, 2000. Hong, Y S. and Rosen, M R.: Intelligent characterisation and diagnosis of the groundwater quality in an urban fractured-rock aquifer using an artificial neural network, Urban Water, 3(3), 193–204, 2001. Jain, A. K., Mao, J., and Mohiuddin, K.: Artificial Neural Networks: a tutorial, IEEE Computer, 26(3), 31–44, 1996. Kaski, S.: Data exploration using Self-Organizing Maps, Acta Polytechnica Scandinavica: Mathematics, computing and management in engineering, Series No 82, 57, 1997. Kohonen, T.: Self-organizing maps. Springer, Berlin, 1995. Koua, E. L., Maceachren, A., and Kraak, M.-J.: Evaluating the usability of visualization methods in an exploratory geovisualization environment, Int. J. Geographical Information Sci., 20(4), 425-448, 2006. Lacassie, J. P., Roser, B., Ruiz del Solar, J., and Herve, F.: Discovering geochemical patterns using self-organizing neural networks: a new perspective for sedimentary provenance analysis, Sedimentary Geology, 165(1–2), 175–191, 2004. Laga, P., Louwye, S., and Geets, S.: Paleogene and Neogene lithostratigraphic units (Belgium), Geologica Belgica, 4(1–2), 135–152, 2001. Lagrou, D., Dreesen, R., and Broothaers, L.: Comparative quantitative petrographical analysis of Cenozoic aquifer sands in Flanders (N Belgium): overall trends and quality assessment, Materials Characterization, 53, 317–326, 2004. Lambrakis, N., Antonakos, A., and Panagopoulos, G.: The use of multicomponent statistical analysis in hydrogeological environmental research, Water Res., 38(7), 1862–1872, 2004. Lischeid, G.: Taming awfully large data sets: using self- organizing maps for analyzing spatial and temporal trends of water quality data, Geophys. Res. Abstr., 5, 01879, 2003. Love, D., Hallbauer, D., Amos, A., and Hranova, R.: Factor analysis as a tool in groundwater quality management: two southern African case studies, Phys. Chem. Earth, 29(15–18), 1135–1143, 2004. Mercier, G., Hubert-Moy, L., Houet, T., and Gouéry, P.: Estimation and monitoring of bare soil/vegetation ratio with SPOT VEGETATION and HRVIR, IEEE Trans. Geosci. Rem. Sens., 43(2), 348–354, 2005. Mingoti, S. A. and Lima, J. O.: Comparing SOM neural network with Fuzzy c-means, K-means and traditional hierarchical clustering algorithms, European J. Operational Res., 174, 1742–1759, 2006. Ozerdem, M. S., Ustundag, B., and Demirer, R. M.: Self-organized maps based neural networks for detection of possible earthquake precursory electric field patterns, Advances in Engineering Software, 37(4), 207–217, 2006. Openshaw, S. and Turton, I.: A parallel Kohonen algorithm for the classification of large spatial datasets, Computers and Geosciences, 22(9), 1019–1026, 1996. Penn, B. S.: Using self-organizing maps to visualize high-dimensional data, Computers and Geosciences, 31(5), 531–544, 2005. Poulton, M. M., Sternberg, B. K., and Glass, C. E.: Location of subsurface targets in geophysical data using neural networks, Geophys., 57(12), (1534–1544), 1992. Richardson, A. J., Risien, C., and Shillington, F. A.: Using self-organizing maps to identify patterns in satellite imagery, Progress in Oceanography, 59(2-3), 223–239, 2003. Sanchez-Martos, F., Aguilera, P A., Garrido-Frenich, A., Torres, J. A., and Pulido-Bosch, A.: Assessment of groundwater quality by means of self-organizing maps: application in a semi-arid area, Environ. Manage., 30(5), 716–726, 2002. Skupin, A. and Hagelman, R.: Attribute space visualization of demographic change, Eleventh ACM international symposium on Advances in geographic information systems, New Orleans, Louisiana, USA, 2003. Takatsuka, M.: An application of the self-organizing map and interactive 3-D visualisation to geospatial data, GeoComputation'01 (6th International Conference on GeoComputation, Brisbane, Australia, 2001. Ultsch, A. and Herrmann, L.: The architecture of emergent self-organizing maps to reduce projection errors, in: ESANN2005 13th European Symposium on Artificial Neural Networks, Bruges, Belgium, 1–6, 2005. Vesanto, J., Himberg, J., Alhoniemi, E., and Parhankangas, J.: Self-organizing map in Matlab: the SOM Toolbox, in: Matlab DSP Conference, Espoo, Finland, 35–40, 1999.