CaltechAUTHORS
  A Caltech Library Service

Geotechnical Site Characterization via Deep Neural Networks: Recovering the Shear Wave Velocity Profile of Layered Soils

Ayoubi, Peyman and Seylabi, Elnaz and Asimaki, Domniki (2020) Geotechnical Site Characterization via Deep Neural Networks: Recovering the Shear Wave Velocity Profile of Layered Soils. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20201002-151457704

[img] PDF (version 2) - Submitted Version
Creative Commons Public Domain Dedication.

1494Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20201002-151457704

Abstract

The mechanical property of soils is a vital part of seismic hazard analysis of a site. Such properties are obtained by either in-situ (destructive) experiments such as crosshole or downhole tests, or by non-destructive tests using surface wave inversion methods. While the latter is more favorable due to the cost-efficiency, there are challenges mostly due to computational need, non-uniqueness of inversion results, and fine-tuning parameters. In this article, we use a deep learning framework to circumvent the above-mentioned limitations to output soil mechanical properties, requiring dispersion data as input. Our trained model performs with high accuracy on the test dataset and shows satisfactory performance compared to the ensemble Kalman inversion technique. We finally propose a framework to extend the method to higher dimensions by numerically solving the wave equation in a two-dimensional medium.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
https://doi.org/10.31224/osf.io/jcw3tDOIDiscussion Paper
ORCID:
AuthorORCID
Ayoubi, Peyman0000-0001-6795-4923
Seylabi, Elnaz0000-0003-0718-372X
Asimaki, Domniki0000-0002-3008-8088
Additional Information:License CC0 1.0 Universal. Submitted: October 02, 2020; Last edited: October 05, 2020. Author asserted no Conflict of Interest.
Subject Keywords:Deep Learning; Dispersion; Geotechnical; Inversion; Shear wave velocity
Record Number:CaltechAUTHORS:20201002-151457704
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20201002-151457704
Official Citation:Ayoubi, P., Seylabi, E. E., & Asimaki, D. (2020, October 2). Geotechnical Site Characterization via Deep Neural Networks: Recovering the Shear Wave Velocity Profile of Layered Soils. https://doi.org/10.31224/osf.io/jcw3t
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:105764
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:05 Oct 2020 14:29
Last Modified:07 Oct 2020 21:51

Repository Staff Only: item control page