A robust neural network-based approach for microseismic event detection

Handle URI:
http://hdl.handle.net/10754/625376
Title:
A robust neural network-based approach for microseismic event detection
Authors:
Akram, Jubran; Ovcharenko, Oleg; Peter, Daniel ( 0000-0002-3397-5379 )
Abstract:
We present an artificial neural network based approach for robust event detection from low S/N waveforms. We use a feed-forward network with a single hidden layer that is tuned on a training dataset and later applied on the entire example dataset for event detection. The input features used include the average of absolute amplitudes, variance, energy-ratio and polarization rectilinearity. These features are calculated in a moving-window of same length for the entire waveform. The output is set as a user-specified relative probability curve, which provides a robust way of distinguishing between weak and strong events. An optimal network is selected by studying the weight-based saliency and effect of number of neurons on the predicted results. Using synthetic data examples, we demonstrate that this approach is effective in detecting weaker events and reduces the number of false positives.
KAUST Department:
King Abdullah University of Science and Technology (KAUST)
Citation:
Akram J, Ovcharenko O, Peter D (2017) A robust neural network-based approach for microseismic event detection. SEG Technical Program Expanded Abstracts 2017. Available: http://dx.doi.org/10.1190/segam2017-17761195.1.
Publisher:
Society of Exploration Geophysicists
Journal:
SEG Technical Program Expanded Abstracts 2017
Issue Date:
17-Aug-2017
DOI:
10.1190/segam2017-17761195.1
Type:
Conference Paper
Sponsors:
The research reported in this publication was supported by funding from King Abdullah University of Science and Technology (KAUST). For computer time, this research used the resources of the Supercomputing Laboratory, Information Technology Division and Extreme Computing Research Center at King Abdullah University of Science and Technology (KAUST) in Thuwal, Saudi Arabia.
Additional Links:
http://library.seg.org/doi/10.1190/segam2017-17761195.1
Appears in Collections:
Conference Papers

Full metadata record

DC FieldValue Language
dc.contributor.authorAkram, Jubranen
dc.contributor.authorOvcharenko, Olegen
dc.contributor.authorPeter, Danielen
dc.date.accessioned2017-08-23T11:54:05Z-
dc.date.available2017-08-23T11:54:05Z-
dc.date.issued2017-08-17en
dc.identifier.citationAkram J, Ovcharenko O, Peter D (2017) A robust neural network-based approach for microseismic event detection. SEG Technical Program Expanded Abstracts 2017. Available: http://dx.doi.org/10.1190/segam2017-17761195.1.en
dc.identifier.doi10.1190/segam2017-17761195.1en
dc.identifier.urihttp://hdl.handle.net/10754/625376-
dc.description.abstractWe present an artificial neural network based approach for robust event detection from low S/N waveforms. We use a feed-forward network with a single hidden layer that is tuned on a training dataset and later applied on the entire example dataset for event detection. The input features used include the average of absolute amplitudes, variance, energy-ratio and polarization rectilinearity. These features are calculated in a moving-window of same length for the entire waveform. The output is set as a user-specified relative probability curve, which provides a robust way of distinguishing between weak and strong events. An optimal network is selected by studying the weight-based saliency and effect of number of neurons on the predicted results. Using synthetic data examples, we demonstrate that this approach is effective in detecting weaker events and reduces the number of false positives.en
dc.description.sponsorshipThe research reported in this publication was supported by funding from King Abdullah University of Science and Technology (KAUST). For computer time, this research used the resources of the Supercomputing Laboratory, Information Technology Division and Extreme Computing Research Center at King Abdullah University of Science and Technology (KAUST) in Thuwal, Saudi Arabia.en
dc.publisherSociety of Exploration Geophysicistsen
dc.relation.urlhttp://library.seg.org/doi/10.1190/segam2017-17761195.1en
dc.rightsArchived with thanks to SEG Technical Program Expanded Abstracts 2017en
dc.subjectborehole geophysicsen
dc.subjectmicroseismicen
dc.subjectneural networksen
dc.subjectprocessingen
dc.subjectalgorithmen
dc.titleA robust neural network-based approach for microseismic event detectionen
dc.typeConference Paperen
dc.contributor.departmentKing Abdullah University of Science and Technology (KAUST)en
dc.identifier.journalSEG Technical Program Expanded Abstracts 2017en
dc.eprint.versionPublisher's Version/PDFen
kaust.authorAkram, Jubranen
kaust.authorOvcharenko, Olegen
kaust.authorPeter, Danielen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.