Shear Wave Velocity Prediction Using Machine Learning

AYDIN Y., NİGDELİ S. M., BEKDAŞ G.

Studies in Systems, Decision and Control, Springer International Publishing Ag, ss.329-338, 2026 identifier

  • Yayın Türü: Kitapta Bölüm / Araştırma Kitabı
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1007/978-3-032-07738-7_16
  • Yayınevi: Springer International Publishing Ag
  • Sayfa Sayıları: ss.329-338
  • Anahtar Kelimeler: Decision tree, Gradient boosting, Machine learning, Shear wave velocity, Support vector
  • İstanbul Üniversitesi-Cerrahpaşa Adresli: Evet

Özet

In solving applications of geotechnical engineering, an important problem is the calculation of the shear wave velocity, since the properties to be determined depending on this value are available. This study aims to predict shear wave velocity (Vs (m/s)) using parameters such as depth (m), cone resistance (qc) (MPa), friction resistance (fs) (kPa), pore water pressure (u2) (kPa), N and unit weight (kN/m3) using Boosting Regression (GBR), Support Vector Regression (SVR) and Decision Tree Regression (DTR). Coefficient of Determination (R2), Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) are used as performance metrics for regression. Among these models, GBR showed the highest prediction performance (R2: 89.03%, MAE: 15.1139, RMSE: 18.8585).