Single Layer Recurrent Neural Network for detection of swarm-like earthquakes in W-Bohemia/Vogtland - the method

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985530%3A_____%2F16%3A00462100" target="_blank" >RIV/67985530:_____/16:00462100 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1016/j.cageo.2016.05.011" target="_blank" >http://dx.doi.org/10.1016/j.cageo.2016.05.011</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.cageo.2016.05.011" target="_blank" >10.1016/j.cageo.2016.05.011</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Single Layer Recurrent Neural Network for detection of swarm-like earthquakes in W-Bohemia/Vogtland - the method

Popis výsledku v původním jazyce

In this paper, we present a new method of local event detection of swarm-like earthquakes based on neural networks. The proposed algorithm uses unique neural network architecture. It combines features used in other neural network concepts such as the Real Time Recurrent Network and Nonlinear Auto regressive Neural Network to achieve good performance of detection. We use the recurrence combined with various delays applied to recurrent inputs so the network remembers history of many samples. This method has been tested on data from a local seismic network in West Bohemia with promising results. We found that phases not picked in training data diminish the detection capability of the neural network and proper preparation of training data is therefore fundamental. To train the network we define a parameter called the learning importance weight of events and show that it affects the number of acceptable solutions achieved by many trials of the Back Propagation Through Time algorithm. We also compare the individual training of stations with training all of them simultaneously, and we conclude that results of joint training are better for some stations than training only one station.

Název v anglickém jazyce

Single Layer Recurrent Neural Network for detection of swarm-like earthquakes in W-Bohemia/Vogtland - the method

Popis výsledku anglicky

In this paper, we present a new method of local event detection of swarm-like earthquakes based on neural networks. The proposed algorithm uses unique neural network architecture. It combines features used in other neural network concepts such as the Real Time Recurrent Network and Nonlinear Auto regressive Neural Network to achieve good performance of detection. We use the recurrence combined with various delays applied to recurrent inputs so the network remembers history of many samples. This method has been tested on data from a local seismic network in West Bohemia with promising results. We found that phases not picked in training data diminish the detection capability of the neural network and proper preparation of training data is therefore fundamental. To train the network we define a parameter called the learning importance weight of events and show that it affects the number of acceptable solutions achieved by many trials of the Back Propagation Through Time algorithm. We also compare the individual training of stations with training all of them simultaneously, and we conclude that results of joint training are better for some stations than training only one station.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

DC - Seismologie, vulkanologie a struktura Země

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Computers and Geosciences

ISSN

0098-3004

e-ISSN

—

Svazek periodika

93

Číslo periodika v rámci svazku

August

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

12

Strana od-do

138-149

Kód UT WoS článku

000379561600015

EID výsledku v databázi Scopus

2-s2.0-84971672812