Spatial data mining methods for example those based on artificial neural networks (ANN) allow extraction of information from databases and detection of otherwise hidden patterns occurring in these data and in consequence acquiring new knowledge on the analysed phenomena or processes. One of these techniques is the multivariate statistical analysis, which facilitates identification of patterns otherwise difficult to observe. In the paper an attempt of applying self-organising maps (SOM) to explore and analyse spatial data related to studies of ground subsidence associated with underground mining has been described. The study has been carried out on a selected part of a former underground coal mining area in SW Poland with the aim to analyse the influence of particular ground deformation factors on the observed subsidence and the relationships between these factors. The research concerned the uppermost coal panels and the following factors: mining system, time of mining activity and inclination, thickness and depth below the ground of the exploited coal panels. It has been found that the exploratory spatial data analysis can be used to identify relationships in multidimensional data related to mining induced ground subsidence. The proposed approach may be found useful in identification of areas threatened by mining related subsidence and in creating scenarios of developing deformation zones and therefore aid spatial development of mining grounds.