20.2 C
New York
Monday, August 15, 2022
- Advertisement -

    Latest Posts

    Neural network model helps predict site-specific impacts of earthquakes

    A new study published by Hiroshima University (HU) researchers in the Bulletin of the Seismological Society of America introduced a novel AI-based technique for estimating site amplification factors (AF) from data on microtremors of the ground.

    Subsurface soil conditions, which determine how earthquakes affect a site, vary substantially. Softer soils, for example, tend to amplify ground motion from an earthquake, while hard substrates may dampen it. Ambient vibrations of the ground or microtremors can be used to investigate soil conditions. Measuring microtremors provides valuable information about the AF of a site, thus its vulnerability to earthquake damage.

    “The proposed method would contribute to more accurate and more detailed seismic ground motion predictions for future earthquakes,” said lead author and HU Associate Professor Hiroyuki Miura.

    The study used 2012-2020 microtremor data from 105 sites in western Japan’s Chugoku district. The model performed well on the test data, demonstrating its potential as a predictive tool for characterizing site AF from microtremor data.

    DOI: 10.1785/0120210300

    Latest Posts

    Don't Miss