Using CNN To Classify Spectrograms of Seismic Events From Llaima Volcano (Chile)

The monitoring of volcanoes is mainly performed by sensors installed on their structures, aiming at recording seismic activities and reporting them to observatories to be later analyzed by specialists. However, due to the high volume of data continuously collected, the use of automatic techniques is an important requirement to support real time analyses. In this sense, a basic but challenging task is the classification of seismic activities to identify signals yielded by different sources as, for instance, the movement of magmatic fluids. Although there exists several approaches proposed to perform such task, they were mainly designed to deal with raw signals. In this paper, we present a 2D approach developed considering two main steps. Firstly, spectrograms for every collected signal are calculated by using Fourier Transform. Secondly, we set a deep neural network to discriminate seismic activities by analyzing the spectrogram shapes. As a consequence, our classifier provided outstanding results with accuracy rates greater than 95%.

[1]  C. Cassisi,et al.  Probabilistic Reasoning Over Seismic Time Series: Volcano Monitoring by Hidden Markov Models at Mt. Etna , 2016, Pure and Applied Geophysics.

[2]  Millaray Curilem,et al.  Improving the Classification of Volcanic Seismic Events Extracting New Seismic and Speech Features , 2017, CIARP.

[3]  Juan Pablo Bello,et al.  A Software Framework for Musical Data Augmentation , 2015, ISMIR.

[4]  M. Masotti,et al.  Application of Support Vector Machine to the classification of volcanic tremor at Etna, Italy , 2006 .

[5]  Christopher D. Stephens,et al.  Earthquake classification, location, and error analysis in a volcanic environment: implications for the magmatic system of the 1989–1990 eruptions at redoubt volcano, Alaska , 1994 .

[6]  Gordon Erlebacher,et al.  A Wavelet Toolkit for Visualization and Analysis of Large Data Sets in Earthquake Research , 2004 .

[7]  Maria Marinaro,et al.  Automatic Classification of Seismic Signals at Mt. Vesuvius Volcano, Italy, Using Neural Networks , 2005 .

[8]  Mario Michael Krell,et al.  Rotational data augmentation for electroencephalographic data , 2017, 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[11]  Niall McLaughlin,et al.  Data-augmentation for reducing dataset bias in person re-identification , 2015, 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[12]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[13]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[14]  Stefan B. Williams,et al.  Convolutional neural networks for passive monitoring of a shallow water environment using a single sensor , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Navdeep Jaitly,et al.  Vocal Tract Length Perturbation (VTLP) improves speech recognition , 2013 .

[16]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Néstor Becerra Yoma,et al.  Automatic detection of volcano-seismic events by modeling state and event duration in hidden Markov models , 2016 .

[18]  Luca D'Auria,et al.  Neural analysis of seismic data: applications to the monitoring of Mt. Vesuvius , 2013 .

[19]  Roberto Carniel,et al.  Detecting dynamical regimes by Self-Organizing Map (SOM) analysis: an example from the March 2006 phreatic eruption at Raoul Island, New Zealand Kermadec Arc , 2013 .

[20]  H. Langer,et al.  Automatic classification and a-posteriori analysis of seismic event identification at Soufriere Hills volcano, Montserrat , 2006 .

[21]  Guillermo Cortés,et al.  The classification of seismo-volcanic signals using Hidden Markov Models as applied to the Stromboli and Etna volcanoes , 2009 .

[22]  Manfred Joswig,et al.  Chances and limits of single-station seismic event clustering by unsupervised pattern recognition , 2015 .

[23]  Bernard A. Chouet,et al.  Long-period volcano seismicity: its source and use in eruption forecasting , 1996, Nature.

[24]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[25]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[26]  N. Chandrasekar,et al.  Improving Seismic Monitoring System for Small to Intermediate Earthquake Detection , 2010 .

[27]  M. I. Seht,et al.  Detection and identification of seismic signals recorded at Krakatau volcano (Indonesia) using artificial neural networks , 2008 .

[28]  Jean-Philippe Malet,et al.  Automatic identification of rockfalls and volcano-tectonic earthquakes at the Piton de la Fournaise volcano using a Random Forest algorithm , 2017 .

[29]  Ángel de la Torre,et al.  Parallel System Architecture (PSA): An efficient approach for automatic recognition of volcano-seismic events , 2014, Journal of Volcanology and Geothermal Research.

[30]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Néstor Becerra Yoma,et al.  Pattern recognition applied to seismic signals of Llaima volcano (Chile): An evaluation of station-dependent classifiers , 2016 .