Deep neural networks for creating reliable PmP database with a case study in Southern California
Recent progresses in artificial intelligence and machine learning make it possible to automatically identify seismic phases from exponentially growing seismic data. Despite some exciting successes in automatic picking of the first P- and S-wave arrivals, auto-identification of later seismic phase...
Saved in:
Main Authors: | , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/170958 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-170958 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1709582023-10-23T15:34:54Z Deep neural networks for creating reliable PmP database with a case study in Southern California Ding, Wen Li, Tianjue Yang, Xu Ren, Kui Tong, Ping School of Physical and Mathematical Sciences Asian School of the Environment Earth Observatory of Singapore Science::Physics Artificial Neural Network Seismic Data Recent progresses in artificial intelligence and machine learning make it possible to automatically identify seismic phases from exponentially growing seismic data. Despite some exciting successes in automatic picking of the first P- and S-wave arrivals, auto-identification of later seismic phases such as the Moho-reflected PmP waves remains a significant challenge in matching the performance of experienced analysts. The main difficulty of machine-identifying PmP waves is that the identifiable PmP waves are rare, making the problem of identifying the PmP waves from a massive seismic database inherently unbalanced. In this work, by utilizing a high-quality PmP dataset (10,192 manual picks) in southern California, we develop PmPNet, a deep-neural-network-based algorithm to automatically identify PmP waves efficiently; by doing so, we accelerate the process of identifying the PmP waves. PmPNet applies similar techniques in the machine learning community to address the unbalancement of PmP datasets. The architecture of PmPNet is a residual neural network (ResNet)-autoencoder with additional predictor block, where encoder, decoder, and predictor are equipped with ResNet connection. We conduct systematic research with field data, concluding that PmPNet can efficiently achieve high precision and high recall simultaneously to automatically identify PmP waves from a massive seismic database. Applying the pre-trained PmPNet to the seismic database from January 1990 to December 1999 in southern California, we obtain nearly twice more PmP picks than the original PmP dataset, providing valuable data for other studies such as mapping the topography of the Moho discontinuity and imaging the lower crust structures of southern California. Ministry of Education (MOE) National Research Foundation (NRF) Published version The work of W. Ding and K. Ren was partially supported by the NSF grants DMS-1937254 and EAR-2000850. T. Li and P. Tong were partly supported by Singapore MOE AcRF Tier-2 Grant (MOE2019-T2-2-112) and the National Research Foundation Singapore and the Singapore Ministry of Education under the Research Centers of Excellence Initiative (Project Code Number: 04MNS001953A620). X. Yang was partially supported by the NSF grants DMS-1818592 and DMS-2109116. 2023-10-20T05:11:26Z 2023-10-20T05:11:26Z 2022 Journal Article Ding, W., Li, T., Yang, X., Ren, K. & Tong, P. (2022). Deep neural networks for creating reliable PmP database with a case study in Southern California. Journal of Geophysical Research: Solid Earth, 127(4). https://dx.doi.org/10.1029/2021JB023830 2169-9356 https://hdl.handle.net/10356/170958 10.1029/2021JB023830 2-s2.0-85128750951 4 127 en MOE2019-T2-2-112 04MNS001953A620 DMS-1937254 EAR-2000850 Journal of Geophysical Research: Solid Earth © 2022. American Geophysical Union. All Rights Reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1029/2021JB023830 application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Science::Physics Artificial Neural Network Seismic Data |
spellingShingle |
Science::Physics Artificial Neural Network Seismic Data Ding, Wen Li, Tianjue Yang, Xu Ren, Kui Tong, Ping Deep neural networks for creating reliable PmP database with a case study in Southern California |
description |
Recent progresses in artificial intelligence and machine learning make it
possible to automatically identify seismic phases from exponentially growing
seismic data. Despite some exciting successes in automatic picking of the first
P- and S-wave arrivals, auto-identification of later seismic phases such as the
Moho-reflected PmP waves remains a significant challenge in matching the
performance of experienced analysts. The main difficulty of machine-identifying
PmP waves is that the identifiable PmP waves are rare, making the problem of
identifying the PmP waves from a massive seismic database inherently
unbalanced. In this work, by utilizing a high-quality PmP dataset (10,192
manual picks) in southern California, we develop PmPNet, a
deep-neural-network-based algorithm to automatically identify PmP waves
efficiently; by doing so, we accelerate the process of identifying the PmP
waves. PmPNet applies similar techniques in the machine learning community to
address the unbalancement of PmP datasets. The architecture of PmPNet is a
residual neural network (ResNet)-autoencoder with additional predictor block,
where encoder, decoder, and predictor are equipped with ResNet connection. We
conduct systematic research with field data, concluding that PmPNet can
efficiently achieve high precision and high recall simultaneously to
automatically identify PmP waves from a massive seismic database. Applying the
pre-trained PmPNet to the seismic database from January 1990 to December 1999
in southern California, we obtain nearly twice more PmP picks than the original
PmP dataset, providing valuable data for other studies such as mapping the
topography of the Moho discontinuity and imaging the lower crust structures of
southern California. |
author2 |
School of Physical and Mathematical Sciences |
author_facet |
School of Physical and Mathematical Sciences Ding, Wen Li, Tianjue Yang, Xu Ren, Kui Tong, Ping |
format |
Article |
author |
Ding, Wen Li, Tianjue Yang, Xu Ren, Kui Tong, Ping |
author_sort |
Ding, Wen |
title |
Deep neural networks for creating reliable PmP database with a case study in Southern California |
title_short |
Deep neural networks for creating reliable PmP database with a case study in Southern California |
title_full |
Deep neural networks for creating reliable PmP database with a case study in Southern California |
title_fullStr |
Deep neural networks for creating reliable PmP database with a case study in Southern California |
title_full_unstemmed |
Deep neural networks for creating reliable PmP database with a case study in Southern California |
title_sort |
deep neural networks for creating reliable pmp database with a case study in southern california |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/170958 |
_version_ |
1781793727393562624 |