Application of Support Vector Machine to the classification of volcanic tremor at Etna, Italy

We applied an automatic pattern recognition technique,
known as Support Vector Machine (SVM), to classify
volcanic tremor data recorded during different states of
activity at Etna volcano, Italy. The seismic signal was
recorded at a station deployed 6 km southeast of the summit
craters from 1 July to 15 August, 2001, a time span
encompassing episodes of lava fountains and a 23 day-long
effusive activity. Trained by a supervised learning algorithm,
the classifier learned to recognize patterns belonging to four
classes, i.e., pre-eruptive, lava fountains, eruptive, and posteruptive.
Training and test of the classifier were carried out
using 425 spectrogram-based feature vectors. Following
cross-validation with a random subsampling strategy,
SVM correctly classified 94.7 ± 2.4% of the data. The
performance was confirmed by a leave-one-out strategy,
with 401 matches out of 425 patterns. Misclassifications
highlighted intrinsic fuzziness of class memberships of
the signals, particularly during transitional phases.
Citation: Masotti, M., S. Falsaperla, H. Langer, S. Spampinato,
and R. Campanini (2006), Application of Support Vector Machine
to the classification of volcanic tremor at Etna, Italy, Geophys. Res.
Lett., 33, L20304, doi:10.1029/2006GL027441.

Angelini, E., et al. (2006), Testing the performances of different image
representations for mass classification in digital mammograms, Int. J.
Mod. Phys. C, 17(1), 113– 131, doi:10.1142/S0129183106009199.
Bazzani, A., et al. (2001), An SVM classifier to separate false signals from
microcalcifications in digital mammograms, Phys. Med. Biol., 46(6),
1651– 1663, doi:10.1088/0031-9155/46/6/305.
Behncke, B., and M. Neri (2003), The July –August 2001 eruption of
Mt. Etna (Sicily), Bull. Volcanol., 65, 461–476, doi:10.1007/s00445-
003-0274-1.
Campanini, R., et al. (2004), A novel featureless approach to mass detection
in digital mammograms based on support vector machines, Phys. Med.
Biol., 49(6), 961– 976, doi:10.1088/0031-9155/49/6/007.
Duda, R. O., P. E. Hart, and D. G. Stork (2000), Pattern Classification, 654
pp., John Wiley, Hoboken, N. J.
Efron, B., and R. J. Tibshirani (1993), An Introduction to the Bootstrap,
CRC Press, Boca Raton, Fla.
Falsaperla, S., et al. (2005), Volcanic tremor at Mt. Etna, Italy, preceding
and accompanying the eruption of July– August, 2001, Pure Appl. Geophys.,
162, 2111–2132, doi:10.1007/s00024-005-2710-y.
Hastie, T., R. Tibshirani, and J. Friedman (2002), The Elements of Statistical
Learning, 533 pp., Springer, New York.
Langer, H., S. Falsaperla, and G. Thompson (2003), Application of Artificial
Neural Networks for the classification of the seismic transients at
Soufrie`re Hills volcano, Montserrat, Geophys. Res. Lett., 30(21), 2090,
doi:10.1029/2003GL018082.
Scarpetta, S., et al. (2005), Automatic classification of seismic signals at
Mt. Vesuvius volcano, Italy, using neural networks, Bull. Seismol. Soc.
Am., 95(1), 185– 196, doi:10.1785/0120030075.
Vapnik, V. (1998), Statistical Learning Theory, John Wiley, Hoboken, N. J.
Weston, J., and C. Watkins (1999), Multi-class support vector machines,
in Proceedings of ESANN99, edited by M. Verleysen. pp. 219– 224,
D. Facto Press, Brussels.
R. Campanini and M. Masotti, Medical Imaging Group, Department of
Physics, University of Bologna, Viale Berti-Pichat 6/2, I-40127, Bologna,
Italy.
S. Falsaperla, H. Langer, and S. Spampinato, Istituto Nazionale di
Geofisica e Vulcanologia, Sezione di Catania, P.zza Roma 2, I-95123
Catania, Italy. (falsaperla@ct.ingv.it)