Developing machine learning‑based ground motion models to predict peak ground velocity in Turkiye

Basit Öğe Kaydı
dc.authoridhttps://orcid.org/0000-0002-2377-6085
dc.authoridhttps://orcid.org/0000-0002-0535-5658
dc.authoridhttps://orcid.org/0000-0001-7401-4964
dc.contributor.authorKuran, Fahrettin
dc.contributor.authorTanırcan, Gülüm
dc.contributor.authorPashaei, Elham
dc.date.accessioned2025-06-10T23:06:27Z
dc.date.available2025-06-10T23:06:27Z
dc.date.issued2024
dc.departmentMühendislik ve Mimarlık Fakültesi
dc.description.abstractThis paper introduces machine learningbased Turkiye-specifc ground motion models for the geometric mean horizontal component of peak ground velocity (PGV). PGV is a signifcant intensity metric to measure and diagnose potential earthquake damage in structures. Reliable prediction of PGV is of essential importance in precise calculations of seismic hazard. The efciencies, reliabilities, and capabilities of various machine learning algorithms, including Random Forest, Support Vector Machine, Linear Regression, Artifcial Neural Network, Gradient Boosting, and Bayesian Ridge Regression, are evaluated and compared. The most recently compiled Turkish strong motion database, which consists of over 950 earthquakes occurring from 1983 to 2023, is used for shaping the models’ ability to learn and make accurate predictions. Three feature selection methodsLeast Absolute Shrinkage and Selection Operator, Recursive Feature Elimination, and Pearson’s Correlation- representing embedded, wrapper, and flter approaches, respectively, are applied to determine the most suitable estimator parameters to predict PGV. Residual analyses and statistical evaluation metrics are employed to measure the performance and efectiveness of the machine learning models. Among the algorithms applied, Gradient Boosting demonstrates exceptional success in predicting PGV, particularly when utilizing all estimator parameters (features) collectively. The Gradient Boosting model exhibits superior predictive capabilities compared to existing ground motion models. It is applicable to shallow crustal strike-slip and normal faulting earthquakes with moment magnitude ranging from 3.5 to 7.8 and Joyner and Boore distance up to 200 km.
dc.identifier.doi10.1007/s10950-024-10239-y
dc.identifier.endpage1204
dc.identifier.issn1383-4649
dc.identifier.issn1573-157X
dc.identifier.issue5
dc.identifier.startpage1183
dc.identifier.urihttps://hdl.handle.net/11363/9899
dc.identifier.volume28
dc.identifier.wos001306222800001
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.institutionauthorPashaei, Elham
dc.institutionauthoridhttps://orcid.org/0000-0001-7401-4964
dc.language.isoen
dc.publisherSPRINGER, VAN GODEWIJCKSTRAAT 30, 3311 GZ DORDRECHT, NETHERLANDS
dc.relation.ispartofJOURNAL OF SEISMOLOGY
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectGround motion model
dc.subjectPeak ground velocity (PGV)
dc.subjectFeature selection
dc.subjectOutlier elimination
dc.subjectMachine learning
dc.subjectTurkiye
dc.titleDeveloping machine learning‑based ground motion models to predict peak ground velocity in Turkiye
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Makale / Article
Boyut:
4.49 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ N/A ]
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Web of Science ve Scopus Atıf Dizinlerindeki Yayınlar
WoS İndeksli Yayınlar Koleksiyonu