Shear Wave Velocity Prediction with Hyperparameter Optimization
Shear wave velocity (V<sub>s</sub>) is an important soil parameter to be known for earthquake-resistant structural design and an important parameter for determining the dynamic properties of soils such as modulus of elasticity and shear modulus. Different V<sub>s</sub> measur...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/1/60 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Shear wave velocity (V<sub>s</sub>) is an important soil parameter to be known for earthquake-resistant structural design and an important parameter for determining the dynamic properties of soils such as modulus of elasticity and shear modulus. Different V<sub>s</sub> measurement methods are available. However, these methods, which are costly and labor intensive, have led to the search for new methods for determining the V<sub>s</sub>. This study aims to predict shear wave velocity (V<sub>s</sub> (m/s)) using depth (m), cone resistance (q<sub>c</sub>) (MPa), sleeve friction (f<sub>s</sub>) (kPa), pore water pressure (u<sub>2</sub>) (kPa), N, and unit weight (kN/m<sup>3</sup>). Since shear wave velocity varies with depth, regression studies were performed at depths up to 30 m in this study. The dataset used in this study is an open-source dataset, and the soil data are from the Taipei Basin. This dataset was extracted, and a 494-line dataset was created. In this study, using HyperNetExplorer 2024V1, V<sub>s</sub> prediction based on depth (m), cone resistance (q<sub>c</sub>) (MPa), shell friction (f<sub>s</sub>), pore water pressure (u<sub>2</sub>) (kPa), N, and unit weight (kN/m<sup>3</sup>) values could be performed with satisfactory results (R<sup>2</sup> = 0.78, MSE = 596.43). Satisfactory results were obtained in this study, in which Explainable Artificial Intelligence (XAI) models were also used. |
|---|---|
| ISSN: | 2078-2489 |