Global to push GA events into
skip to main content

Title: Real-time neural network earthquake profile predictor

A neural network has been developed that uses first-arrival energy to predict the characteristics of impending earthquake seismograph signals. The propagation of ground motion energy through the earth is a highly nonlinear function. This is due to different forms of ground motion as well as to changes in the elastic properties of the media throughout the propagation path. The neural network is trained using seismogram data from earthquakes. Presented with a previously unseen earthquake, the neural network produces a profile of the complete earthquake signal using data from the first seconds of the signal. This offers a significant advance in the real-time monitoring, warning, and subsequent hazard minimization of catastrophic ground motion.
 [1];  [1]
  1. (Castro Valley, CA)
Issue Date:
OSTI Identifier:
Regents of University of California (Oakland, CA) LLNL
Patent Number(s):
US 5490062
Contract Number:
Research Org:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Country of Publication:
United States
real-time; neural; network; earthquake; profile; predictor; developed; first-arrival; energy; predict; characteristics; impending; seismograph; signals; propagation; ground; motion; earth; highly; nonlinear; function; due; forms; changes; elastic; properties; media; throughout; path; trained; seismogram; data; earthquakes; previously; unseen; produces; complete; signal; offers; significant; advance; monitoring; warning; subsequent; hazard; minimization; catastrophic; neural network; significant advance; time monitoring; real-time monitoring; elastic properties; neural net; /702/706/