Automatic Classification of Volcano Seismic Signatures

Abstract

The prediction of volcanic eruptions and the evaluation of associated risks remain a timely and unresolved issue. This paper presents a method to automatically classify seismic events linked to volcanic activity. As increased seismic activity is an indicator of volcanic unrest, automatic classification of volcano seismic events is of major interest for volcano monitoring. The proposed architecture is based on supervised classification, whereby a prediction model is built from an extensive data set of labeled observations. Relevant events should then be detected. Three steps are involved in the building of the prediction model: (i) signals preprocessing, (ii) representation of the signals in the feature space, and (iii) use of an automatic classifier to train the model. Our main contribution lies in the feature space where the seismic observations are represented by 102 features gathered from both acoustic and seismic fields. Ideally, observations are separable in the feature space, depending on their class. The architecture is tested on 109,609 seismic events that were recorded between June 2006 and September 2011 at Ubinas Volcano, Peru. Six main classes of signals are considered: long‐period events, volcanic tremors, volcano tectonic events, explosions, hybrid events, and tornillos. Our model reaches 93.5% ± 0.50% accuracy, thereby validating the presented architecture and the features used. Furthermore, we illustrate the limited influence of the learning algorithm used (i.e., random forest and support vector machines) by showing that the results remain accurate regardless of the algorithm selected for the training stage. The model is then used to analyze 6 years of data.

Deep Learning for Geophysics: Current and Future Trends

“…All rights reserved. used to detect six classes: long-period events, volcanic tremors, volcano-tectonic events, explosions, hybrid events, and tornados (Malfante et al 2018). Uncertainty is also considered in volcano-seismic monitoring (Bueno et al 2019).…”

“…More categories of signals are required to identify in specific tasks, such as in volcano seismic detection (Titos et al, 2019). Volcano seismic signals can be classified into six classes: long-period events, volcanic tremors, volcano-tectonic events, explosions, hybrid events, and tornados (Malfante et al, 2018). Uncertainty is also considered in volcano-seismic monitoring (Bueno et al, 2019).…”

Features Engineering and Features Extraction of Volcano-Tectonic (VT) Earthquake

“…In the 1960s to early 1970s, monitoring of volcanoes using seismic methods successfully recorded some type of earthquake that occurred around the volcano [2]. Naming and identifying earthquake types is done based on the similarity of source mechanisms and the uniqueness of statistical parameters [3]. One of the earthquakes that characterize volcanoes is volcano-tectonic (VT) earthquake.…”

Hierarchical exploration of continuous seismograms with unsupervised learning

“…Finding the most relevant features should be done according to the task at hand and can be done thanks to prior knowledge on the data or by defining proper algorithms to learn the most relevant features. We distinguish classical machine-learning algorithms that rely on human-defined features (Maggi et al, 2017;Malfante et al, 2018) or representationlearning algorithms where the features are learned from the data to optimize a given task (LeCun et al, 2015;Ross et al, 2018;Rouet-Leduc et al, 2020). While classical machine learning provides less accuracy in most cases, it provides interpretability since the features are known, which is an interesting aspect.…”