A novel Bayesian Augmented-Learning framework, quantifying the uncertainty of spectral representations stochastic processes in presence missing data, is developed. The approach combines additional information (prior domain knowledge) physical with real, yet incomplete, observations. deep learning models are trained to learn underlying process, probabilistically capturing temporal dynamics, from...

INTRODUCTION At 2:28 p.m. on 12 May, 2008, a devastating earthquake measuring 8.0 on the Richter scale hit Wenchuan County, Sichuan Province in southwest China, and resulted in the deaths of thousands of people. To date, few epidemiological studies have been conducted on the determinants of the mortality of patients hospitalised after an earthquake. This paper is aimed at identifying the contri...

The 1994 Northridge, California, earthquake is the first earthquake for which we have all of the data sets needed to conduct a rigorous regional analysis of seismic slope instability. These data sets include (1) a comprehensive inventory of triggered landslides, (2) about 200 strong-motion records of the mainshock, (3) 1:24,000-scale geologic mapping of the region, (4) extensive data on enginee...

A number of seismic response records obtained from instrumented bridge during earthquake provide opportunity to assess structural performance and integrity by evaluating structural dynamic characteristics and its possible changes due to earthquake. In this paper a methodology to identify dynamic characteristics of instrumented bridge based on earthquake-induced vibration is presented. A time do...

More and more earthquake early warning systems (EEWS) are developed or currently being tested in many active seismic regions of the world. A well-known problem with real-time procedures is the parameter saturation, which may lead to magnitude underestimation for large earthquakes. In this paper, the method used to the MW9.0 Tohoku-Oki earthquake is explored with strong-motion records of the MW7...