%0 Journal Article
%T A regression-based approach to the prediction of crest settlement of embankment dams under earthquake shaking
%J Scientia Iranica
%I Sharif University of Technology
%Z 1026-3098
%A Javdanian, H.
%A Zarif Sanayei, H. R.
%A Shakarami, L.
%D 2020
%\ 04/01/2020
%V 27
%N 2
%P 671-681
%! A regression-based approach to the prediction of crest settlement of embankment dams under earthquake shaking
%K Embankment dam
%K earthquake
%K Crest settlement
%K Support vector regression
%K Predictive model
%R 10.24200/sci.2018.50483.1716
%X Settlement and deformation of the embankment dams are among the major damages caused by earthquakes, eventually leading to dam instability. Therefore, accurate assessment of the seismic settlement of embankment dams is of particular concern. This study aims to evaluate the settlement of embankment dams subjected to earthquake loads using regression-based methods. A wide-ranging real data on crest settlement of embankment dams caused by earthquakes was collected and analyzed. Yield acceleration of dam, maximum horizontal earthquake acceleration, fundamental period of dam body, predominant period of earthquake, and earthquake magnitude were considered as the most influential parameters affecting the seismic crest settlement of embankment dams. Using support vector regression method as well as multiple linear regression method, two models were developed to estimate earthquake induced crest settlement of embankment dams. Subsequently, sensitivity analysis was conducted in order to assess the behavior of the proposed models under different conditions. Finally, the accuracy of the proposed models was compared with the existing relationship for estimation of earthquake induced crest settlement of embankment dams. Although both MLR- and SVR-based models have an acceptable accuracy in estimation of the crest settlement of embankment dams under earthquake loading, the SVR-based model has a higher accuracy.
%U https://scientiairanica.sharif.edu/article_20440_5aef336d377fcc4d110ed1c115ce44c2.pdf