Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/88942
Título: | The potential of region-specific machine-learning-based ground motion models: application to Turkey |
Autor(es): | Mohammadi, Amirhossein Karimzadeh, Shaghayegh Banimahd, Seyed Amir Ozsarac, Volkan Lourenço, Paulo B. |
Palavras-chave: | Artificial neural network Extreme gradient boosting Ground motion model Inter-event and intra-event residuals Likelihood function Turkish ground motion dataset |
Data: | 2023 |
Editora: | Elsevier Science BV |
Revista: | Soil Dynamics and Earthquake Engineering |
Citação: | Mohammadi, A., Karimzadeh, S., Banimahd, S. A., Ozsarac, V., & Lourenço, P. B. (2023, September). The potential of region-specific machine-learning-based ground motion models: Application to Turkey. Soil Dynamics and Earthquake Engineering. Elsevier BV. http://doi.org/10.1016/j.soildyn.2023.108008 |
Resumo(s): | Conventional ground motion models have extensively been established worldwide based on classical regression analysis of records. Alternatively, advanced nonparametric machine-learning (ML) algorithms may capture the complex nonlinear behaviour of earthquake motions. This paper investigates the efficiency of artificial neural network (ANN) and extreme gradient boosting (XGBoost) in predicting peak ground acceleration (PGA), peak ground velocity (PGV) and pseudo-spectral acceleration (PSA) (period, T = 0.03–2.0 s) for the Turkish dataset. The dataset involves 1166 records of 383 events with a moment magnitude (Mw) of 4.0–7.6, Joyner and Boore distance (RJB) of 0–200 km, focal depth (FD) less than 35 km, and site condition as the averaged shear wave velocity of the soil on the top 30 m (VS30) of 131–1380 m/s. The performance of the models is compared against empirical models in terms of root-mean-square error (RMSE), coefficient of determination (R2), Pearson correlation coefficient (r), and inter-event and intra-event residuals. To perform residual analysis, a likelihood function is developed. Findings reveal that the XGBoost approach gives an unbiased model with a higher correlation and lower residual than ANN. Finally, an online platform is provided for any interested users. |
Tipo: | Artigo |
URI: | https://hdl.handle.net/1822/88942 |
DOI: | 10.1016/j.soildyn.2023.108008 |
ISSN: | 0267-7261 |
Versão da editora: | https://www.sciencedirect.com/science/article/pii/S0267726123002531 |
Arbitragem científica: | yes |
Acesso: | Acesso aberto |
Aparece nas coleções: | ISISE - Artigos em Revistas Internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
2023_SDEE_172_The potential of region-specific machine-learning-based ground motion models Application to Turkey.pdf | 16,69 MB | Adobe PDF | Ver/Abrir |
Este trabalho está licenciado sob uma Licença Creative Commons