Klassifizierung von Infraschallsignalen am Ätna mithilfe von Mustererkennungsverfahren

The ongoing activity of Mount Etna and the proximity to the nearby population requires constant monitoring. Infrasound recordings play an important role in volcanic observation because explosive activity near or above ground as well as shallow tremor processes are easier to identify with airborne sound waves than with seismic waves that are significantly scattered and refracted in the volcano edifice. However, infrasound signals are often blurred by noise, in case of Mount Etna, mostly wind induced noise. manual distinction of noisy data from real volcanogenic signals brings along a considerable effort and requires expert knowledge. At Mount Etna five summit craters are currently known with fluctuating levels of activity. This leads to a wide variety of infrasound signal patterns interfered by changing noise levels. In order to distinguish waveforms of noise from signals of volcanic origin we apply unsupervised pattern recognition techniques. We show that by extracting features from the amplitude spectrum different infrasound regimes can be distinguished with Self-Organizing maps (SOMs). This technique provides an option to color-code the results for an intuitive interpretation and allows even for a more detailed recognition of transitional activity regimes. We create a reference data set from multiple months of infrasound waveforms to include as many activity regimes as possible to train the SOM. This enables a fast classification of new data.
poster