Stochastic simulation of ground motions based on NGA-West2 strong motion records

Tian, P. S.; Sun, Xiaodan; Li, Xin; Wan, Keyu

doi:10.29382/eqs-2019-0115-03

Cited by 3 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As demonstrated in Table 6, for the prediction of significant duration D 5-95 , compared to the models of Stafford [6] and Wang [20], the proposed fusion model (weighted averaging method) reduced the MSE value by 40.2% and 39.5% respectively, and decreased the MAE value by 25.2% and 24.3% respectively, while enhancing the overall accuracy by 3.4% and 3.3% respectively. For the prediction of significant duration D 5-75, compared to the models of Stafford and Wang, the proposed fusion model (weighted averaging method) reduced the MSE by…”

Section: Plos Onementioning

confidence: 98%

“…Comparison with existing studies. To verify the effectiveness of the proposed fusion model, we compared its significant duration predictions with those of Stafford [6] and Wang [20], both of which were based on the same data source (NGA-WEST2). Table 6 provides numerical comparisons of model evaluation indexs, including MSE, MAE, and error rate.…”

Section: Plos Onementioning

confidence: 99%

See 1 more Smart Citation

Significant duration prediction of seismic ground motions using machine learning algorithms

Li,

Gao

2024

PLoS ONE

View full text Add to dashboard Cite

This study aims to predict the significant duration (D5-75, D5-95) of seismic motion by employing machine learning algorithms. Based on three parameters (moment magnitude, fault distance, and average shear wave velocity), two additional parameters(fault top depth and epicenter mechanism parameters) were introduced in this study. The XGBoost algorithm is utilized for characteristic parameter optimization analysis to obtain the optimal combination of four parameters. We compare the prediction results of four machine learning algorithms (random forest, XGBoost, BP neural network, and SVM) and develop a new method of significant duration prediction by constructing two fusion models (stacking and weighted averaging). The fusion model demonstrates an improvement in prediction accuracy and generalization ability of the significant duration when compared to single algorithm models based on evaluation indicators and residual values. The accuracy and rationality of the fusion model are validated through comparison with existing research.

show abstract

Section: Plos Onementioning

confidence: 98%

Section: Plos Onementioning

confidence: 99%

Significant duration prediction of seismic ground motions using machine learning algorithms

Li,

Gao

2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

Simulation of the 1934 Nepal–Bihar earthquake in Kathmandu

Ghimire,

Parajuli,

Maskey

2024

Nat Hazards

View full text Add to dashboard Cite

In this study, utilizing appropriate target spectra and a special envelope function, an artificial time history is generated for the major earthquakes of 1934 and 2015 A.D. The peak ground acceleration (PGA), mean time period, predominant period, significant duration, response spectra, and Fourier spectra of the 2015 earthquake are obtained from the simulated time history These ground motion parameters of simulated earthquake are compared to those of the recorded earthquake of 2015. For the earthquake of 1934 A.D., the maximum PGA derived from the simulation and the PGA derived from the damage-based MMI scale are compared. These earthquakes' significant duration is also compared with other subduction zone earthquakes.Compared to other subduction zone earthquakes, Nepal's earthquakes have a longer significant duration.

show abstract