Sharif University of TechnologyScientia Iranica1026-309825420180801Predicting shear wave velocity of soil using multiple linear regression analysis and artificial neural networks19431955426310.24200/sci.2017.4263ENOMOLBANINATAEEDept. of geology, Ferdowsi University of
Mashhad, Mashhad, IranNASERHAFEZI MOGHADDASDept. of geology, Ferdowsi University of Mashhad, Mashhad, IranGHOLAM REZALASHKARI POURDept. of geology,
Ferdowsi University of Mashhad, Mashhad, IranMEHDI JABBARI NOOGHABIDept. of Statistics, Ferdowsi University of Mashhad, Mashhad, IranJournal Article20160516In this paper, the correlation between shear wave velocity and some of the index parameters of soils including standard penetration test blow counts (<em>SPT</em>), fine-content (<em>FC</em>), soil moisture (<em>W</em>), liquid limit (<em>LL</em>) and depth (<em>D</em>) is investigated. The study attempts to show the application of artificial neural networks and multiple regression analysis in the prediction of the shear wave velocity (<em>V<sub>S</sub></em>) value of soils.<br /> New predicting equations are suggested to correlate <em>V<sub>S</sub></em> and mentioned parameters based on a dataset collected from Mashhad city in the north east of Iran. The results suggest that better and more exact correlations in the estimation of <em>V<sub>S</sub></em> are acquired when <em>ANN</em> method is used. The predicted values using <em>ANN</em> method are checked against the real values of <em>V<sub>S</sub></em> to evaluate the performance of this method. The minimum correlation coefficient obtained in <em>ANN</em> method is higher than the maximum correlation coefficient obtained from the <em>MLR</em>. In addition, the value of estimation error in the <em>ANN</em> method is much less than the <em>MLR</em> method indicating the higher confidence coefficient of the <em>ANN</em> in estimating the <em>V<sub>S</sub></em> of soil.http://scientiairanica.sharif.edu/article_4263_57852cf72ee0384832b234269900f3bf.pdf