Shear wave velocity by support vector machine based on geotechnical soil properties

Abstract. Shear wave velocity (V_S) is a basic engineering property implemented in evaluating the soil shear modulus. In many instances it may be preferable to determine V_S indirectly by common in-situ tests, such as the Standard Penetration Test (SPT). In this paper, the relationship between V_S and geotechnical soil parameters such as standard penetration test blow counts (N₁₆₀), effective stress and fines content, as well as overburden stress ratio (σ_vo/σ^′_vo), is investigated. A new mode based on support vector machine (SVM) approach is proposed to correlate geotechnical parameters and V_S, predicated on a total of 620 data sets, including field investigation records for the Kocaeli (Turkey, 1999) and Chi-Chi (Taiwan, 1999) earthquakes. This study addresses the question of whether Support Vector Machine (SVM) approach should be used to estimate V_S based on the specified geotechnical variables, and assessing the influence of each variable on V_S. Results revealed that SVM, in comparison to previous statistical relations, provides an effective means of efficiently recognizing the patterns in data and accurately predicting the V_S.