English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. A new modified elementary Levenberg–Marquardt Algorithm (M-LMA) was used to minimisebackpropagation errors in training a backpropagation neural network (BPNN) topredict the records related to the Chi-Chi earthquake from four seismicstations: Station-TAP003, Station-TAP005, Station-TCU084, and Station-TCU078belonging to the Free Field Strong Earthquake Observation Network, with thelearning rates of 0.3, 0.05, 0.2, and 0.28, respectively. For these fourrecording stations, the M-LMA has been shown to produce smaller predictederrors compared to the Levenberg–Marquardt Algorithm (LMA). A sudden predictederror could be an indicator for Early Earthquake Warning (EEW), whichindicated the initiation of strong motion due to large earthquakes. Atrade-Off decision-making process with BPNN (TDPB), using two alarms,adjusted the threshold of the magnitude of predicted error without a mistakenalarm. With this approach, it is unnecessary to consider the problems ofcharacterising the wave phases and pre-processing, and does not requirecomplex hardware; an existing seismic monitoring network-covered researcharea was already sufficient for these purposes.

geoscientific instrumentation, methods and data systems

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