An Active Learning Approach for Classifying Explosion Quakes

In this work, an Active Learning approach for improving the classification of passed seismo-volcanic events is proposed. Here we study the specific case of Explosion Quakes from Stromboli Volcano versus other seismo-volcanic events, recorded as seismograms, and the use of Random Forest as a Classification method. In conformity with the active learning paradigm, the approach recalls the human intervention for the annotation of uncertain data. The uncertainty is established by the event probabilities, predicted by a trained random forest classifier. The human intervention consists of editing and relabelling the data into these main three classes: Explosion Quakes, Non-Explosion Quakes or Non-Classifiable. The edited events are added as new training examples with the purpose of improving future predictions. The results demonstrate that the proposed active learning approach improves the probability distribution of the events after the human intervention, in particular, after a cut-out phase of the signals with low probabilities.