Prediction of Peak Ground Velocity (PGV) and Cumulative Absolute Velocity (CAV) of Earthquakes Using Machine Learning Techniques

Basit Öğe Kaydı
dc.authorscopusid58531781200
dc.authorscopusid26535157900
dc.authorscopusid57194619312
dc.contributor.authorKuran, F.
dc.contributor.authorTanırcan, G.
dc.contributor.authorPashaei, E.
dc.date.accessioned2024-09-11T19:58:30Z
dc.date.available2024-09-11T19:58:30Z
dc.date.issued2024
dc.departmentİstanbul Gelişim Üniversitesien_US
dc.description7th International Conference on Earthquake Engineering and Seismology, ICEES 2023 -- 6 November 2023 through 10 November 2023 -- Antalya -- 313859en_US
dc.description.abstractThis study presents the prediction of cumulative absolute velocity (CAV) and peak ground velocity (PGV) using machine learning (ML) algorithms, which are relatively new compared to ground motion models with fixed functional forms. The performance of three ML algorithms, namely Linear Regression, Artificial Neural Network, and Gradient Boosting are evaluated and compared. The New Turkish Strong Motion Database (N-TSMD), containing over 23,000 recordings of 743 earthquakes that occurred in Turkiye between 1983 and 2020, is used to build ML models. In addition to N-TSMD, new recordings, including the recent Mw 7.7 and Mw 7.6 (Kahramanmaraş), Mw 6.6 (Gaziantep), and Mw 6.4 (Hatay) earthquakes, are added. In developing ML models, the moment magnitude (Mw), Joyner-Boore distance (RJB), shear-wave velocity averaged in the top 30 m of soil (Vs30), and style-of-faulting (SoF) are used as estimator parameters to characterize the source, path, site, and tectonic environment. Mean square error (MSE), root mean squared error (RMSE), and correlation coefficient (R) metrics are used to evaluate models. Results indicated that the Gradient Boosting algorithm demonstrates the best performance in predicting CAV and PGV according to all performance metrics. This is followed by Artificial Neural Network and Linear Regression, respectively. Residual analyses with predictions of the Gradient Boosting model indicated that there is almost no trend in the distribution of the total residuals of both PGV and CAV. The GB model’s prediction skill can be considered fair in all Mw, RJB, and Vs30 ranges. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.en_US
dc.identifier.doi10.1007/978-3-031-57357-6_3
dc.identifier.endpage42en_US
dc.identifier.isbn978-303157356-9en_US
dc.identifier.issn2366-2557en_US
dc.identifier.scopus2-s2.0-85197417014en_US
dc.identifier.scopusqualityQ4en_US
dc.identifier.startpage29en_US
dc.identifier.urihttps://doi.org/10.1007/978-3-031-57357-6_3
dc.identifier.urihttps://hdl.handle.net/11363/8501
dc.identifier.volume401 LNCEen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Science and Business Media Deutschland GmbHen_US
dc.relation.ispartofLecture Notes in Civil Engineeringen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240903_Gen_US
dc.subjectCumulative absolute velocity (CAV); Ground motion prediction; Machine learning; Peak ground velocity (PGV)en_US
dc.titlePrediction of Peak Ground Velocity (PGV) and Cumulative Absolute Velocity (CAV) of Earthquakes Using Machine Learning Techniquesen_US
dc.typeConference Objecten_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu