Full text loading...
-
[Invited] Estimating S-wave Velocity Profile from Horizontal-to-Vertical Spectral Ratio based on Supervised Machine Learning
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 6th Asia Pacific Meeting on Near Surface Geoscience and Engineering, May 2024, Volume 2024, p.1 - 5
Abstract
Summary
Average S-wave velocity (Vs) to 30 m depth (VS30) is indispensable information to estimate site amplification. We use a horizontal-to-vertical spectral ratio (H/V) to estimate the VS30. Measurement of H/V is easier compared with active surface wave methods (MASW) or microtremor array measurements (MAM). Inversion of the H/V is non-unique and it is impossible to obtain unique Vs profiles. We apply supervised machine learning to estimate VS30 from H/V together with other information. The pairs of H/V spectra (input layer) and Vs profiles (output layer) are used as training data. Input layer consists of an observed H/V spectrum site coordinate, and geomorphological information, and output layer is a velocity profile. We applied the method to the South Kanto Plain, Japan. We measured MASW, MAM and H/V at approximately 2000 sites. The pairs of H/V spectrum together with their coordinate, geomorphological classification and Vs profile obtained from the inversion of dispersion curve and H/V compose the training data. Trained neural network predicts Vs profiles from observed H/V spectra. The VS30 calculated from predicted Vs profiles are consistent with those calculated from true Vs profiles. The results implied that the machine learning could estimate VS30 from H/V together with other information.
© EAGE Publications BV