Open AccessSparse modeling for the geotechnical observation data
Author(s) -
Tetsushi Kurita
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/652/1/012023
Subject(s) - regularization (linguistics) , field (mathematics) , geotechnical engineering , computer science , algorithm , geology , artificial intelligence , mathematics , pure mathematics
In the geotechnical engineering, it is a significant issue to construct the numerical models for simulation analysis based on the observation data. In this study, sparse modeling used as an effective modeling method in the field of machine learning and image processing was applied to the geotechnical engineering and its effectiveness was examined. Aa a case study based on the field observation data, the fused lasso which is a typical method of the sparse modeling was applied to model the velocity structure of the subsurface ground using the PS logging data. As a result of examination, it was found that simplified models can be obtained by increasing the value of the regularization parameter.