Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen’s Self-Organizing Map

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 5 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 141 groundwater samples collected in two detritic, phreatic, Cenozoic aquifers in Central Belgium. The standard SOM proves to be more adequate in representing the structure of the data set and to 10 explore relationships between variables. The GEO3DSOM on the other hand performs better in creating spatially coherent groups based on the data.