Multivariate time series clustering on geophysical data recorded at Mt. Etna from 1996 to 2003

► In this work we propose a novel tool for geophysical time series analysis. ► The analysis is based on efficient representation of different kinds of data acquired at Mt. Etna. ► The Self Organized Map approach highlights clusters existing in data space. ► Clustering result is related to the activity of Mt. Etna before and after the 2001 flank eruption.