Impact areas in spatial analysis are determined by using density clustering methods which have an elevated computational complexity. We propose an al-ternative method based on the Extended Fuzzy C-Means (EFCM) method which has the following advantages: robustness to noise and outliers, linear computational complexity, automatic determination of the optimal number of clusters. In this method we derive dynamic buffer areas as hypersphere volume prototypes which become circles in the case of bi-dimensional pattern data: for example, event point data in Geographic Information Systems (GIS). In spatial analysis these circles can represent buffer areas around unknown epicenters (for example, crime events, desease localizations, car incidents). We...