Neural classification of infrasonic signals associated with hazardous volcanic eruptions

Infrasound signals released as a result of volcanic eruptions contain information regarding the intensity of the eruptions, presence of ash emissions, and certain characteristics of the volcano itself. Knowledge of the eruption intensity can provide an estimate of the height of the ash column. This paper focuses on exploiting the infrasonic characteristics of volcanoes by extracting unique cepstral-based features from the volcano's infrasound signature. These volcano feature vectors are then used to train and test a neural-classifier that is developed to distinguish the ash-generating eruptive activity from three volcanoes, namely, Mount St. Helens-USA, Tungurahua-Ecuador, and Kasatochi-Alaska. The neural-classifier is able to correctly distinguish the eruptive activity of each of the three volcanoes with a correct classification rate (CCR) of approximately 97%.