One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are ...One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are important parameters for measuring ground motion intensity and assessing earthquake damage.Due to the limited available information in EEW,CAV,I_(A),and SI cannot be accurately predicted using traditional EEW methods.In this paper,we propose an end-to-end deep learning-based Ground motion Intensity prediction Network(ENGINet)for on-site EEW.The aim of the ENGINet is to predict CAV,I_(A),and SI rapidly and reliably.ENGINet is based on a convolutional neural network and recurrent neural network.The inputs of the network are three-component acceleration records,three-component velocity records,and three-component displacement records obtained by a single station.The results from the test dataset show that at 3 s after the P-wave arrival,compared with the baseline models and other traditional methods,ENGINet has better performance in predicting CAV,I_(A),and SI.Our results indicate that ENGINet can quickly and accurately predict CAV,I_(A),and SI to some extent and has good potential in EEW efforts.展开更多
基金Scientific Research Fund of Institute of Engineering Mechanics,China Earthquake Administration under Grant No.2024B08。
文摘One of the primary tasks of earthquake early warning(EEW)systems is to predict potential earthquake damage rapidly and accurately.Cumulative absolute velocity(CAV),Arias intensity(I_(A)),and spectrum intensity(SI)are important parameters for measuring ground motion intensity and assessing earthquake damage.Due to the limited available information in EEW,CAV,I_(A),and SI cannot be accurately predicted using traditional EEW methods.In this paper,we propose an end-to-end deep learning-based Ground motion Intensity prediction Network(ENGINet)for on-site EEW.The aim of the ENGINet is to predict CAV,I_(A),and SI rapidly and reliably.ENGINet is based on a convolutional neural network and recurrent neural network.The inputs of the network are three-component acceleration records,three-component velocity records,and three-component displacement records obtained by a single station.The results from the test dataset show that at 3 s after the P-wave arrival,compared with the baseline models and other traditional methods,ENGINet has better performance in predicting CAV,I_(A),and SI.Our results indicate that ENGINet can quickly and accurately predict CAV,I_(A),and SI to some extent and has good potential in EEW efforts.
