Application of real time recurrent neural network for detection of small natural earthquakes in Poland

Wiszniowski, Jan; Plesiewicz, Beata; Trojanowski, Jacek

doi:10.2478/s11600-013-0140-2

Cited by 40 publications

(24 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can learn from the complex features of images (Mousavi et al, 2019; Perol et al, 2018), simulate seismic waves (Moseley et al, 2018), classify volcanic ash particles (Shoji et al, 2018), and pick P and S waves in long seismograms (Zhu & Beroza, 2019). In addition, recurrent neural network (RNN) is very helpful to learn the pattern of sequential data (Wang et al, 2017; Wiszniowski et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Detecting Slow Slip Events From Seafloor Pressure Data Using Machine Learning

Wei

Watts

et al. 2020

Geophysical Research Letters

View full text Add to dashboard Cite

Detecting slow slip events (SSEs) at offshore subduction zones is important to understand the slip behavior on offshore subduction megathrusts, where tsunamis can be generated. The most widely used method to detect SSEs is to measure the vertical seafloor deformation caused by SSEs using seafloor pressure data. However, due to the small signal‐to‐noise ratio and instrumental drift, such detection is very difficult. In this study, we trained a machine learning model using synthetic data to detect SSEs and applied it to real pressure data in New Zealand between 2014 and 2015. Our method detected five events, two of which are confirmed by the onshore GPS records. Besides, our model performs better than the traditional matched filter method. We conclude that machine learning could be used to detect SSEs in real seafloor pressure data. The method can be applied to other regions, especially where near trench GPS is not available.

show abstract

Section: Introductionmentioning

confidence: 99%

Detecting Slow Slip Events From Seafloor Pressure Data Using Machine Learning

Wei

Watts

et al. 2020

Geophysical Research Letters

View full text Add to dashboard Cite

show abstract

“…It had already been studied on regional events by Wiszniowski (2000) but it got accommodated for local events (Wiszniowski et al 2014). This method is able to assess relations of seismic signal in frequency domains as well as in time of seismic phases.…”

Section: Detection Methodsmentioning

confidence: 99%

Seismic Monitoring of Poland–Description and Results of Temporary Seismic Project with Mobile Seismic Network

2015

Self Cite

View full text Add to dashboard Cite

A b s t r a c tThe paper describes a temporary seismic project aimed at developing the national database of natural seismic activity for seismic hazard assessment, officially called "Monitoring of Seismic Hazard of Territory of Poland" (MSHTP). Due to low seismicity of Poland, the project was focused on events of magnitude range 1-3 in selected regions in order to maximize the chance of recording any natural event. The project used mobile seismic stations and was divided into two stages.Five-year measurements brought over one hundred natural seismic events of magnitudes M L range 0.5-3.8. Most of them were located in the Podhale region in the Carpathians. Together with previously recorded events this made it possible to conduct a preliminary study on ground motion prediction equation for this region. Only one natural event, of magnitude M L = 3.8, was recorded outside the Carpathians in a surprising location in central-west Poland.

show abstract

“…A RcNN for the real time detection of small magnitude (below 2.5 Mw) earthquakes is presented in [52]. In this case, the distribution of seismic stations in populated areas yields data with significant levels of noise.…”

Section: Rcnnmentioning

confidence: 99%

“…This requires a special detection method capable of recognizing small events without using preprocessing based on standard pass-band filtering. Instead, [52] applies a filter bank of STA/LTA ratios of the vertical component of seismic waveforms, with an elaborate design to keep all important frequencies of the signal, including the highest range, where disturbances are less significant. Thus, this RcNN is low prone to false detection occurrences.…”

Section: Rcnnmentioning

confidence: 99%

Artificial Neural Networks as Emerging Tools for Earthquake Detection

Rojas

Otero

Alvarado

et al. 2019

CyS

View full text Add to dashboard Cite

As seismic networks continue to spread and monitoring sensors become more efficient, the abundance of data highly surpasses the processing capabilities of earthquake interpretation analysts. Earthquake catalogs are fundamental for fault system studies, event modellings, seismic hazard assessment, forecasting, and ultimately, for mitigating the seismic risk. These have fueled the research for the automation of interpretation tasks such as event detection, event identification, hypocenter location, and source mechanism analysis. Over the last forty years, traditional algorithms based on quantitative analyses of seismic traces in the time or frequency domain, have been developed to assist interpretation. Alternatively, recent advances are related to the application of Artificial Neural Networks (ANNs), a subset of machine learning techniques that is pushing the state-of-the-art forward in many areas. Appropriated trained ANN can mimic the interpretation abilities of best human analysts, avoiding the individual weaknesses of most traditional algorithms, and spending modest computational resources at the operational stage. In this paper, we will survey the latest ANN applications to the automatic interpretation of seismic data, with a special focus on earthquake detection, and the estimation of onset times. For a comparative framework, we give an insight into the labor of human interpreters, who may face uncertainties in the case of small magnitude earthquakes.

show abstract

Application of real time recurrent neural network for detection of small natural earthquakes in Poland

Cited by 40 publications

References 26 publications

Detecting Slow Slip Events From Seafloor Pressure Data Using Machine Learning

Detecting Slow Slip Events From Seafloor Pressure Data Using Machine Learning

Seismic Monitoring of Poland–Description and Results of Temporary Seismic Project with Mobile Seismic Network

Artificial Neural Networks as Emerging Tools for Earthquake Detection

Contact Info

Product

Resources

About