Journal cover Journal topic
Earth Surface Dynamics An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 3.176 IF 3.176
  • IF 5-year value: 3.108 IF 5-year 3.108
  • CiteScore value: 3.06 CiteScore 3.06
  • SNIP value: 0.978 SNIP 0.978
  • SJR value: 1.421 SJR 1.421
  • IPP value: 2.88 IPP 2.88
  • h5-index value: 13 h5-index 13
  • Scimago H index value: 13 Scimago H index 13
Discussion papers
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 06 Aug 2018

Research article | 06 Aug 2018

Review status
This discussion paper is a preprint. A revision of the manuscript is under review for the journal Earth Surface Dynamics (ESurf).

Systematic Identification of External Influences in Multi-Year Micro-Seismic Recordings Using Convolutional Neural Networks

Matthias Meyer1, Samuel Weber2, Jan Beutel1, and Lothar Thiele1 Matthias Meyer et al.
  • 1Computer Engineering and Networks Laboratory, ETH Zurich, Zurich, Switzerland
  • 2Department of Geography, University of Zurich, Zurich, Switzerland

Abstract. Natural hazards, e.g. due to slope instabilities, are a significant risk for the population of mountainous regions. Monitoring of micro-seismic signals can be used for process analysis and risk assessment. However, these signals are subject to external influences, e.g anthropogenic or natural noise. Successful analysis depends strongly on the capability to cope with such external influences. For correct slope characterization it is thus important to be able to identify, quantify and take these influences into account.

In long-term monitoring scenarios manual identification is infeasible due to large data quantities demanding accurate automated analysis methods. In this work we present a systematic strategy to identify multiple external influences, characterize their impact on micro-seismic analysis and develop methods for automated identification. We apply the developed strategy to a real-word, multi-sensor, multi-year micro-seismic monitoring experiment on the Matterhorn Hörnliridge (CH). We present a convolutional neural network for micro-seismic data to detect external influences originating in mountaineers, a major unwanted influence, with an error rate of less than 1%, which is 3× lower than comparable algorithms. Moreover, we present an ensemble classifier for the same task obtaining an error rate of 0.79% and an F1 score of 0.9383 by using images and micro-seismic data. Applying the classifiers to the experiment data reveals that approximately 1/4 of events detected with an event detector are not due to seismic activity but due to anthropogenic mountaineering influences and that time periods with mountaineer activity have a 9× higher event rate. Due to these findings we argue that a systematic identification of external influences, like presented in this paper, is a prerequisite for a qualitative analysis.

Matthias Meyer et al.
Interactive discussion
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Matthias Meyer et al.
Data sets

Micro-seismic and image dataset acquired at Matterhorn Hörnligrat, Switzerland M. Meyer, S. Weber, J. Beutel, S. Gruber, T. Gsell, A. Hasler, and A. Vieli

Model code and software

Code for classifier training and evaluation using the micro-seismic and image dataset acquired at Matterhorn Hörnligrat, Switzerland M. Meyer and S. Weber

Matthias Meyer et al.
Total article views: 733 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
639 84 10 733 11 11
  • HTML: 639
  • PDF: 84
  • XML: 10
  • Total: 733
  • BibTeX: 11
  • EndNote: 11
Views and downloads (calculated since 06 Aug 2018)
Cumulative views and downloads (calculated since 06 Aug 2018)
Viewed (geographical distribution)  
Total article views: 730 (including HTML, PDF, and XML) Thereof 728 with geography defined and 2 with unknown origin.
Country # Views %
  • 1
No saved metrics found.
No discussed metrics found.
Latest update: 12 Dec 2018
Publications Copernicus
Special issue