Arrival times by Recurrent Neural Network for induced seismic events from a permanent network
We have developed a Recurrent Neural Network (RNN)-based phase picker for data obtained from a local seismic monitoring array specifically designated for induced seismicity analysis. The proposed algorithm was rigorously tested using real-world data from a network encompassing nine three-component s...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-08-01
|
Series: | Frontiers in Big Data |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fdata.2023.1174478/full |
_version_ | 1797754540676612096 |
---|---|
author | Petr Kolar Umair bin Waheed Leo Eisner Petr Matousek |
author_facet | Petr Kolar Umair bin Waheed Leo Eisner Petr Matousek |
author_sort | Petr Kolar |
collection | DOAJ |
description | We have developed a Recurrent Neural Network (RNN)-based phase picker for data obtained from a local seismic monitoring array specifically designated for induced seismicity analysis. The proposed algorithm was rigorously tested using real-world data from a network encompassing nine three-component stations. The algorithm is designed for multiple monitoring of repeated injection within the permanent array. For such an array, the RNN is initially trained on a foundational dataset, enabling the trained algorithm to accurately identify other induced events even if they occur in different regions of the array. Our RNN-based phase picker achieved an accuracy exceeding 80% for arrival time picking when compared to precise manual picking techniques. However, the event locations (based on the arrival picking) had to be further constrained to avoid false arrival picks. By utilizing these refined arrival times, we were able to locate seismic events and assess their magnitudes. The magnitudes of events processed automatically exhibited a discrepancy of up to 0.3 when juxtaposed with those derived from manual processing. Importantly, the efficacy of our results remains consistent irrespective of the specific training dataset employed, provided that the dataset originates from within the network. |
first_indexed | 2024-03-12T17:34:52Z |
format | Article |
id | doaj.art-b3460dd4df164cad87da822fa4322fa3 |
institution | Directory Open Access Journal |
issn | 2624-909X |
language | English |
last_indexed | 2024-03-12T17:34:52Z |
publishDate | 2023-08-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Big Data |
spelling | doaj.art-b3460dd4df164cad87da822fa4322fa32023-08-04T12:21:39ZengFrontiers Media S.A.Frontiers in Big Data2624-909X2023-08-01610.3389/fdata.2023.11744781174478Arrival times by Recurrent Neural Network for induced seismic events from a permanent networkPetr Kolar0Umair bin Waheed1Leo Eisner2Petr Matousek3Institute of Geophysics of the Czech Academy of Sciences, Prague, CzechiaDepartment of Geosciences, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaSeismik s.r.o., Prague, CzechiaSeismik s.r.o., Prague, CzechiaWe have developed a Recurrent Neural Network (RNN)-based phase picker for data obtained from a local seismic monitoring array specifically designated for induced seismicity analysis. The proposed algorithm was rigorously tested using real-world data from a network encompassing nine three-component stations. The algorithm is designed for multiple monitoring of repeated injection within the permanent array. For such an array, the RNN is initially trained on a foundational dataset, enabling the trained algorithm to accurately identify other induced events even if they occur in different regions of the array. Our RNN-based phase picker achieved an accuracy exceeding 80% for arrival time picking when compared to precise manual picking techniques. However, the event locations (based on the arrival picking) had to be further constrained to avoid false arrival picks. By utilizing these refined arrival times, we were able to locate seismic events and assess their magnitudes. The magnitudes of events processed automatically exhibited a discrepancy of up to 0.3 when juxtaposed with those derived from manual processing. Importantly, the efficacy of our results remains consistent irrespective of the specific training dataset employed, provided that the dataset originates from within the network.https://www.frontiersin.org/articles/10.3389/fdata.2023.1174478/fullRecurrent Neural Networkautomatic arrival time detectionlocationmagnitudehydraulic fracturinginduced seismicity |
spellingShingle | Petr Kolar Umair bin Waheed Leo Eisner Petr Matousek Arrival times by Recurrent Neural Network for induced seismic events from a permanent network Frontiers in Big Data Recurrent Neural Network automatic arrival time detection location magnitude hydraulic fracturing induced seismicity |
title | Arrival times by Recurrent Neural Network for induced seismic events from a permanent network |
title_full | Arrival times by Recurrent Neural Network for induced seismic events from a permanent network |
title_fullStr | Arrival times by Recurrent Neural Network for induced seismic events from a permanent network |
title_full_unstemmed | Arrival times by Recurrent Neural Network for induced seismic events from a permanent network |
title_short | Arrival times by Recurrent Neural Network for induced seismic events from a permanent network |
title_sort | arrival times by recurrent neural network for induced seismic events from a permanent network |
topic | Recurrent Neural Network automatic arrival time detection location magnitude hydraulic fracturing induced seismicity |
url | https://www.frontiersin.org/articles/10.3389/fdata.2023.1174478/full |
work_keys_str_mv | AT petrkolar arrivaltimesbyrecurrentneuralnetworkforinducedseismiceventsfromapermanentnetwork AT umairbinwaheed arrivaltimesbyrecurrentneuralnetworkforinducedseismiceventsfromapermanentnetwork AT leoeisner arrivaltimesbyrecurrentneuralnetworkforinducedseismiceventsfromapermanentnetwork AT petrmatousek arrivaltimesbyrecurrentneuralnetworkforinducedseismiceventsfromapermanentnetwork |