Options
Transfer learning: Improving neural network based prediction of earthquake ground shaking for an area with insufficient training data
Language
English
Obiettivo Specifico
5T. Sismologia, geofisica e geologia per l'ingegneria sismica
Status
Published
JCR Journal
JCR Journal
Peer review journal
Yes
Title of the book
Issue/vol(year)
1/229 (2022)
ISSN
0956-540X
Publisher
Oxford University Press
Pages (printed)
704–718
Issued date
2022
Alternative Location
Subjects
seismology
Abstract
In a recent study (Jozinovi\'c et al, 2020) we showed that convolutional
neural networks (CNNs) applied to network seismic traces can be used for rapid
prediction of earthquake peak ground motion intensity measures (IMs) at distant
stations using only recordings from stations near the epicenter. The
predictions are made without any previous knowledge concerning the earthquake
location and magnitude. This approach differs from the standard procedure
adopted by earthquake early warning systems (EEWSs) that rely on location and
magnitude information. In the previous study, we used 10 s, raw, multistation
waveforms for the 2016 earthquake sequence in central Italy for 915 events (CI
dataset). The CI dataset has a large number of spatially concentrated
earthquakes and a dense station network. In this work, we applied the CNN model
to an area around the VIRGO gravitational waves observatory sited near Pisa,
Italy. In our initial application of the technique, we used a dataset
consisting of 266 earthquakes recorded by 39 stations. We found that the CNN
model trained using this smaller dataset performed worse compared to the
results presented in the original study by Jozinovi\'c et al. (2020). To
counter the lack of data, we adopted transfer learning (TL) using two
approaches: first, by using a pre-trained model built on the CI dataset and,
next, by using a pre-trained model built on a different (seismological) problem
that has a larger dataset available for training. We show that the use of TL
improves the results in terms of outliers, bias, and variability of the
residuals between predicted and true IMs values. We also demonstrate that
adding knowledge of station positions as an additional layer in the neural
network improves the results. The possible use for EEW is demonstrated by the
times for the warnings that would be received at the station PII.
neural networks (CNNs) applied to network seismic traces can be used for rapid
prediction of earthquake peak ground motion intensity measures (IMs) at distant
stations using only recordings from stations near the epicenter. The
predictions are made without any previous knowledge concerning the earthquake
location and magnitude. This approach differs from the standard procedure
adopted by earthquake early warning systems (EEWSs) that rely on location and
magnitude information. In the previous study, we used 10 s, raw, multistation
waveforms for the 2016 earthquake sequence in central Italy for 915 events (CI
dataset). The CI dataset has a large number of spatially concentrated
earthquakes and a dense station network. In this work, we applied the CNN model
to an area around the VIRGO gravitational waves observatory sited near Pisa,
Italy. In our initial application of the technique, we used a dataset
consisting of 266 earthquakes recorded by 39 stations. We found that the CNN
model trained using this smaller dataset performed worse compared to the
results presented in the original study by Jozinovi\'c et al. (2020). To
counter the lack of data, we adopted transfer learning (TL) using two
approaches: first, by using a pre-trained model built on the CI dataset and,
next, by using a pre-trained model built on a different (seismological) problem
that has a larger dataset available for training. We show that the use of TL
improves the results in terms of outliers, bias, and variability of the
residuals between predicted and true IMs values. We also demonstrate that
adding knowledge of station positions as an additional layer in the neural
network improves the results. The possible use for EEW is demonstrated by the
times for the warnings that would be received at the station PII.
Sponsors
RISE (Union's Horizon 2020 research and innovation programme, grant agreement No.821115)
Description
This article has been accepted for publication in Geophysical Journal International ©: The Authors 2021. Published by Oxford University Press on behalf of the Royal Astronomical Society. All rights reserved. Uploaded in accordance with the publisher's self-archiving policy.
Type
article
File(s)
Loading...
Name
ggab488.pdf
Description
Open Access published article
Size
3.55 MB
Format
Adobe PDF
Checksum (MD5)
c161961a1950892596a6f907e795d1cb