English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Random field Monte Carlo (MC) reliability analysis is a robust stochasticmethod to determine the probability of failure. This method, however, requiresa large number of numerical simulations demanding high computational costs.This paper explores the efficiency of different machine learning (ML)algorithms used as surrogate models trained on a limited number of random fieldslope stability simulations in predicting the results of large datasets. The MCdata in this paper require only the examination of failure or non-failure,circumventing the time-consuming calculation of factors of safety. An extensivedataset is generated, consisting of 120,000 finite difference MC slopestability simulations incorporating different levels of soil heterogeneity andanisotropy. The Bagging Ensemble, Random Forest and Support Vector classifiersare found to be the superior models for this problem amongst 9 different modelsand ensemble classifiers. Trained only on 0.47% of data (500 samples), the MLmodel can classify the entire 120,000 samples with an accuracy of %85 and AUCscore of %91. The performance of ML methods in classifying the random fieldslope stability results generally reduces with higher anisotropy andheterogeneity of soil. The ML assisted MC reliability analysis proves a robuststochastic method where errors in the predicted probability of failure using %5of MC data is only %0.46 in average. The approach reduced the computationaltime from 306 days to less than 6 hours.

Slope stability predictions on spatially variable random fields using machine learning surrogate models