Rapid prediction of earthquake ground shaking intensity using raw waveform data and a convolutional neural network

Jozinović, Dario; Lomax, Anthony; Štajduhar, Ivan; Michelini, Alberto

doi:10.1093/gji/ggaa233

Cited by 86 publications

(99 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To prevent overfitting and ensure better generalizability, we applied L2 regularization with a regularization rate of 10 −4 to the convolutional layers and dropout with a dropout rate of 0.5 following the last fully connected layer (Srivastava et al, 2014;Jozinović et al, 2020). Moreover, the rectified linear unit (ReLU) activation function (Nair and Hinton, 2010) followed each pooling layer and fully connected layer.…”

Section: The Dcnn-m Modelmentioning

confidence: 99%

Magnitude Estimation for Earthquake Early Warning Using a Deep Convolutional Neural Network

Zhu

Song

et al. 2021

Front. Earth Sci.

View full text Add to dashboard Cite

Magnitude estimation is a vital task within earthquake early warning (EEW) systems (EEWSs). To improve the magnitude determination accuracy after P-wave arrival, we introduce an advanced magnitude prediction model that uses a deep convolutional neural network for earthquake magnitude estimation (DCNN-M). In this paper, we use the inland strong-motion data obtained from the Japan Kyoshin Network (K-NET) to calculate the input parameters of the DCNN-M model. The DCNN-M model uses 12 parameters extracted from 3 s of seismic data recorded after P-wave arrival as the input, four convolutional layers, four pooling layers, four batch normalization layers, three fully connected layers, the Adam optimizer, and an output. Our results show that the standard deviation of the magnitude estimation error of the DCNN-M model is 0.31, which is significantly less than the values of 1.56 and 0.42 for the τc method and Pd method, respectively. In addition, the magnitude prediction error of the DCNN-M model is not affected by variations in the epicentral distance. The DCNN-M model has considerable potential application in EEWSs in Japan.

show abstract

Section: The Dcnn-m Modelmentioning

confidence: 99%

Magnitude Estimation for Earthquake Early Warning Using a Deep Convolutional Neural Network

Zhu

Song

et al. 2021

Front. Earth Sci.

View full text Add to dashboard Cite

show abstract

“…. , dnum) in the set DANGER, Borderline-SMOTE1 selects its m(0 ≤ m ≤ k) nearest neighbors from set P, and attains m × dnum new synthetic examples by formula (12). Borderline-SMOTE2 selects its m nearest neighbors from the whole set T, regardless of whether this neighbor belongs to class P or belongs to class N. Another different point is that rand(0, 1) in formula ( 12) is changed to rand(0, 0.5) in the calculation of Borderline-SMOTE2, so the generated synthetic sample is closer to the minority class in DANGER.…”

Section: Over-sampling Datamentioning

confidence: 99%

“…[ 10 ] Mousavi designed a network consisting of convolutional and recurrent layers for magnitude estimation [ 11 ]. Dario Jozinovic applied a CNN model to predict the magnitude of ground motions [ 12 ]. Perol et al introduced ConvNetQuake to detect local micro-seismic earthquakes according to signal waveforms.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning-Based Electromagnetic Signal for Earthquake Magnitude Prediction

Bao

Zhao

Huang

et al. 2021

Sensors

View full text Add to dashboard Cite

The influence of earthquake disasters on human social life is positively related to the magnitude and intensity of the earthquake, and effectively avoiding casualties and property losses can be attributed to the accurate prediction of earthquakes. In this study, an electromagnetic sensor is investigated to assess earthquakes in advance by collecting earthquake signals. At present, the mainstream earthquake magnitude prediction comprises two methods. On the one hand, most geophysicists or data analysis experts extract a series of basic features from earthquake precursor signals for seismic classification. On the other hand, the obtained data related to earth activities by seismograph or space satellite are directly used in classification networks. This article proposes a CNN and designs a 3D feature-map which can be used to solve the problem of earthquake magnitude classification by combining the advantages of shallow features and high-dimensional information. In addition, noise simulation technology and SMOTE oversampling technology are applied to overcome the problem of seismic data imbalance. The signals collected by electromagnetic sensors are used to evaluate the method proposed in this article. The results show that the method proposed in this paper can classify earthquake magnitudes well.

show abstract

“…Perol et al (2018) tried to detect the earthquakes' occurrences and classify the locations of the epicenters within seven predefined regions using three-component seismic waveforms recorded on a seismic station using CNN. Jozinovic et al (2020) tried to estimate the intensity measurements of ground-shaking earthquake events within Central Italy by simultaneously using the seismic waveform data of 39 stations located close to epicenters with the input of the CNN.…”

Section: Introductionmentioning

confidence: 99%

Onsite Early Prediction of PGA Using CNN With Multi-Scale and Multi-Domain P-Waves as Input

Hsu

Huang

2021

Front. Earth Sci.

View full text Add to dashboard Cite

Although convolutional neural networks (CNN) have been applied successfully to many fields, the onsite earthquake early warning by CNN remains unexplored. This study aims to predict the peak ground acceleration (PGA) of the incoming seismic waves using CNN, which is achieved by analyzing the first 3 s of P-wave data collected from a single site. Because the amplitude of P-wave data of large and small earthquakes can differ, the multi-scale input of P-wave data is proposed in this study in order to let the CNN observe the input data in different scales. Both the time and frequency domains of the P-wave data are combined into multi-domain input, and therefore the CNN can observe the data from different aspects. Since only the maximum absolute acceleration value of the time history of seismic waves is the target output of the CNN, the absolute value of the P-wave time history data is used instead of the raw value. The proposed arrangement of the input data shows its superiority to the one directly inputting the raw P-wave data into the CNN. Moreover, the predicted PGA accuracy using the proposed CNN approach is higher than the one using the support vector regression approach that employed the extracted P-wave features as its input. The proposed CNN approach also shows that the accuracy of the predicted PGA and the alert performances are acceptable based on data from two independent and damaging earthquakes.

show abstract

Rapid prediction of earthquake ground shaking intensity using raw waveform data and a convolutional neural network

Cited by 86 publications

References 33 publications

Magnitude Estimation for Earthquake Early Warning Using a Deep Convolutional Neural Network

Magnitude Estimation for Earthquake Early Warning Using a Deep Convolutional Neural Network

A Deep Learning-Based Electromagnetic Signal for Earthquake Magnitude Prediction

Onsite Early Prediction of PGA Using CNN With Multi-Scale and Multi-Domain P-Waves as Input

Contact Info

Product

Resources

About