Clustering of volcanic ash arising from different fragmentation mechanisms using Kohonen self-organizing maps

Orkun Ersoy (1) , Erkan Aydar (1) , Alain Gourgaud (2, 3) , Harun Artuner (4) , Hasan Bayhan (1)

1 Department of Geological Engineering
2 LMV - Laboratoire Magmas et Volcans
3 LMV-ENSMSE - Laboratoire Magmas et Volcans
4 Department of Computer Science and Engineering

In this study, we present the visualization and clustering capabilities of self-organizing maps (SOM) for analyzing highdimensional data. We used SOM because they implement an orderly mapping of a high-dimensional distribution onto a regular low-dimensional grid. We used surface texture parameters of volcanic ash that arose from different fragmentation mechanisms as input data. We found that SOM cluster 13-dimensional data more accurately than conventional statistical classifiers. The component planes constructed by SOM are more successful than statistical tests in determining the distinctive parameters.

Mots clés: Neural networks; Kohonen self-organizing maps; Volcanic ash; Nemrut

Domaines: Volcanologie

Orkun Ersoy, Erkan Aydar, Alain Gourgaud, Harun Artuner, Hasan Bayhan. Clustering of volcanic ash arising from different fragmentation mechanisms using Kohonen self-organizing maps. Computers & Geosciences, 2007, 33 (6), pp.821-828. ⟨10.1016/j.cageo.2006.10.008⟩. ⟨hal-00328999⟩