Earthquake Early Warning ( EEW) has come to attention,as earthquake prediction is still unreliable. The paper comprehensively illustrates the research status and important issues of EEW from the aspects of concept,com...Earthquake Early Warning ( EEW) has come to attention,as earthquake prediction is still unreliable. The paper comprehensively illustrates the research status and important issues of EEW from the aspects of concept,composition and method. By analyzing the status of EEW in China,we find that the essential requirements have been met for building earthquake early warning systems in the country in terms of government and social needs, network construction and basic research. The technical difficulties and non-technical challenges in implementing EEW in China are evaluated, and some suggestions are proposed regarding the relevant legal measures,public education and protection against earthquake disasters. so as to bring into full play the role of the EEW system in earthquake disaster prevention and reduction.展开更多
In this work a Support Vector Machine Regression（SVMR） algorithm is used to calculate local magnitude（MI） using only five seconds of signal after the P wave onset of one three component seismic station. This algor...In this work a Support Vector Machine Regression（SVMR） algorithm is used to calculate local magnitude（MI） using only five seconds of signal after the P wave onset of one three component seismic station. This algorithm was trained with 863 records of historical earthquakes, where the input regression parameters were an exponential function of the waveform envelope estimated by least squares and the maximum value of the observed waveform for each component in a single station. Ten-fold cross validation was applied for a normalized polynomial kernel obtaining the mean absolute error for different exponents and complexity parameters. The local magnitude（MI） could be estimated with 0.19 units of mean absolute error. The proposed algorithm is easy to implement in hardware and may be used directly after the field seismological sensor to generate fast decisions at seismological control centers, increasing the possibility of having an effective reaction.展开更多
基金funded by Key Projects in the National Science & Technology Pillar Program ( Grant No. 2012BAK19B04)the National Natural Science Foundation ( Grant No. 41104023)the Science & Technology Development Project of Shandong Province ( Grant No. 2011GSF12004)
文摘Earthquake Early Warning ( EEW) has come to attention,as earthquake prediction is still unreliable. The paper comprehensively illustrates the research status and important issues of EEW from the aspects of concept,composition and method. By analyzing the status of EEW in China,we find that the essential requirements have been met for building earthquake early warning systems in the country in terms of government and social needs, network construction and basic research. The technical difficulties and non-technical challenges in implementing EEW in China are evaluated, and some suggestions are proposed regarding the relevant legal measures,public education and protection against earthquake disasters. so as to bring into full play the role of the EEW system in earthquake disaster prevention and reduction.
文摘In this work a Support Vector Machine Regression（SVMR） algorithm is used to calculate local magnitude（MI） using only five seconds of signal after the P wave onset of one three component seismic station. This algorithm was trained with 863 records of historical earthquakes, where the input regression parameters were an exponential function of the waveform envelope estimated by least squares and the maximum value of the observed waveform for each component in a single station. Ten-fold cross validation was applied for a normalized polynomial kernel obtaining the mean absolute error for different exponents and complexity parameters. The local magnitude（MI） could be estimated with 0.19 units of mean absolute error. The proposed algorithm is easy to implement in hardware and may be used directly after the field seismological sensor to generate fast decisions at seismological control centers, increasing the possibility of having an effective reaction.
