Use of artificial neural networks for classification of noisy seismic signals

Кислов, К. В.; Гравиров, В. В.

doi:10.3103/s0747923917010054

Cited by 22 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The creation of such an annotated subset, despite being time and labor consuming, is therefore an overhead which is outweighted by the 15 benefits of a better analysis. For data annotation two main approaches can be followed, annotating the phenomena of interest Ruano et al, 2014;Kislov and Gravirov, 2017), we would be restricted to find seismic events in the sensor being influenced by compounding factors and thus no ground truth information except for experience by professionals can be used.…”

Section: Labelingmentioning

confidence: 99%

“…The most recent advanced methods are based on machine learning techniques (Reynen and Audet, 2017). The use of neural networks (Kislov and Gravirov, 2017;Perol et al, 2018) shows promising results with the drawback that large 30 datasets containing ground truth (verified seismic events) are required to train these networks. In earthquake research these large database of known seismic events exist, but are difficult to obtain in slope stability analysis where effects are strictly local to a given field site, inhomogeneities are commonly found on a small scale and each field site differs in its characteristics with respect to signal attenuation and impulse response.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Interactive Figures

Meyer¹

2018

Preprint

View full text Add to dashboard Cite

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. 5In 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 un-10 wanted influence, with an error rate of less than 1 %, which is 3x 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 9x higher event rate. Due to these findings we argue that a systematic identification of external 15 influences, like presented in this paper, is a prerequisite for a qualitative analysis.

show abstract

Section: Labelingmentioning

confidence: 99%

mentioning

confidence: 99%

Interactive Figures

Meyer¹

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Nevertheless, there are several reasons why ANNs are still not widely used. They are: difficult and long learning process, the necessity of taking into account characteristics of each seismic station of the monitoring network, difficulties in evaluation of quality and reliability of probabilistic classification results (Kislov and Gravirov, 2017). Because cryoseisms are present in seismograms as strong impulses with high signal-to-noise ratio, we applied an "STA/LTA" algorithm for their detection and simple neural network for their classification using selected characteristics of the records (length, central frequencies, etc.…”

Section: Introductionmentioning

confidence: 99%

Development of events detector for monitoring cryoseisms in upper soils

Afonin¹,

Kozlovskaya²

2020

Preprint

View full text Add to dashboard Cite

In this article, we describe the first results of the development of the seismic events detector with an artificial neural network (ANN) based identification. Such a detector is necessary for studying seismic events induced by soil freezing that can be hazardous for urban and mining infrastructures. We used the data of about 300 such seismic events recorded by seismic station OUL of Northern Finland Seismological Network for testing the detector and neural network learning. We processed about two months of continuous data and found out, that in some cases the number of detected and identified seismic events per day depends on air temperature variation.

show abstract

“…For example, template-matching approaches such as cross-correlation methods (Gibbons and Ringdal, 2006) use event examples to find similar events, failing if events differ significantly in "shape" or if the transmission medium is very inhomogeneous (Weber et al, 2018b). The most recent supervised methods are based on machine learning techniques (Reynen and Audet, 2017;Olivier et al, 2018) including the use of neural networks (Kislov and Gravirov, 2017;Perol et al, 2018;Li et al, 2018;. These learning approaches show promising results with the drawback that large datasets containing ground truth (verified events) are required to train these automated classifiers.…”

Section: Introductionmentioning

confidence: 99%

Systematic identification of external influences in multi-year microseismic recordings using convolutional neural networks

et al. 2019

View full text Add to dashboard Cite

Passive monitoring of ground motion can be used for geophysical process analysis and natural hazard assessment. Detecting events in microseismic signals can provide responsive insights into active geophysical processes. However, in the raw signals, microseismic events are superimposed by external influences, for example, anthropogenic or natural noise sources that distort analysis results. In order to be able to perform event-based geophysical analysis with such microseismic data records, it is imperative that negative influence factors can be systematically and efficiently identified, quantified and taken into account. Current identification methods (manual and automatic) are subject to variable quality, inconsistencies or human errors. Moreover, manual methods suffer from their inability to scale to increasing data volumes, an important property when dealing with very large data volumes as in the case of long-term monitoring.In this work, we present a systematic strategy to identify a multitude of external influence sources, characterize and quantify their impact and develop methods for automated identification in microseismic signals. We apply the strategy developed to a real-world, multi-sensor, multi-year microseismic monitoring experiment performed at the Matterhorn Hörnligrat (Switzerland). We develop and present an approach based on convolutional neural networks for microseismic data to detect external influences originating in mountaineers, a major unwanted influence, with an error rate of less than 1 %, 3 times 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 jointly using time-lapse image and microseismic data on an annotated subset of the monitoring data. Applying these classifiers to the whole experimental dataset reveals that approximately one-fourth of events detected by an event detector without such a preprocessing step are not due to seismic activity but due to anthropogenic influences and that time periods with mountaineer activity have a 9 times higher event rate. Due to these findings, we argue that a systematic identification of external influences using a semi-automated approach and machine learning techniques as presented in this paper is a prerequisite for the qualitative and quantitative analysis of long-term monitoring experiments.Published by Copernicus Publications on behalf of the European Geosciences Union.

show abstract

Use of artificial neural networks for classification of noisy seismic signals

Cited by 22 publications

References 23 publications

Interactive Figures

Interactive Figures

Development of events detector for monitoring cryoseisms in upper soils

Systematic identification of external influences in multi-year microseismic recordings using convolutional neural networks

Contact Info

Product

Resources

About