Journal cover Journal topic
Geoscientific Instrumentation, Methods and Data Systems An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 1.319 IF 1.319
  • IF 5-year value: 1.299 IF 5-year 1.299
  • CiteScore value: 1.27 CiteScore 1.27
  • SNIP value: 0.740 SNIP 0.740
  • SJR value: 0.598 SJR 0.598
  • IPP value: 1.21 IPP 1.21
  • h5-index value: 12 h5-index 12
  • Scimago H index value: 6 Scimago H index 6
Volume 7, issue 3 | Copyright
Geosci. Instrum. Method. Data Syst., 7, 235-243, 2018
https://doi.org/10.5194/gi-7-235-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 16 Aug 2018

Research article | 16 Aug 2018

Backpropagation neural network as earthquake early warning tool using a new modified elementary Levenberg–Marquardt Algorithm to minimise backpropagation errors

Jyh-Woei Lin, Chun-Tang Chao, and Juing-Shian Chiou Jyh-Woei Lin et al.
  • Department of Electrical Engineering, Southern Taiwan University of Science and Technology, No. 1, Nan-Tai Street, Yungkang Dist., Tainan City, Taiwan

Abstract. A new modified elementary Levenberg–Marquardt Algorithm (M-LMA) was used to minimise backpropagation errors in training a backpropagation neural network (BPNN) to predict the records related to the Chi-Chi earthquake from four seismic stations: Station-TAP003, Station-TAP005, Station-TCU084, and Station-TCU078 belonging to the Free Field Strong Earthquake Observation Network, with the learning rates of 0.3, 0.05, 0.2, and 0.28, respectively. For these four recording stations, the M-LMA has been shown to produce smaller predicted errors compared to the Levenberg–Marquardt Algorithm (LMA). A sudden predicted error could be an indicator for Early Earthquake Warning (EEW), which indicated the initiation of strong motion due to large earthquakes. A trade-Off decision-making process with BPNN (TDPB), using two alarms, adjusted the threshold of the magnitude of predicted error without a mistaken alarm. With this approach, it is unnecessary to consider the problems of characterising the wave phases and pre-processing, and does not require complex hardware; an existing seismic monitoring network-covered research area was already sufficient for these purposes.

Publications Copernicus
Download
Short summary
This BPNN approach with two alarms was well suited, and it was not necessary to consider the problems of characterising the wave phases and pre-processing, as stated previously. Furthermore, BPNN is a mature technology, which is expected to develop rapidly in the future, and does not require complex hardware. Determining an initial location and magnitude of the event was not necessary for this technique. An existing seismic monitoring network can be used.
This BPNN approach with two alarms was well suited, and it was not necessary to consider the...
Citation
Share