Development of a Probabilistic Seismic Performance Assessment Model of Slope Using Machine Learning Methods

Abstract

The objective of this study is to propose a model that can predict the seismic performance of slope relatively accurately and efficiently by using machine learning methods. Probabilistic seismic fragility analyses of the slope had been carried out in other studies, and a closed-form equation for slope seismic performance was proposed through a multiple linear regression analysis. However, the traditional statistical linear regression analysis showed a limit that could not accurately represent such nonlinear slope seismic performances. To overcome this limit, in this study, we used three machine learning methods (i.e., support vector machine (SVM), artificial neural network (ANN), Gaussian process regression (GPR)) to generate prediction models of the slope seismic performance. The models obtained through the machine learning methods basically showed better performance compared to the models of the traditional statistical methods. The results of the SVM showed no significant performance difference compared with the results of the nonlinear regression analysis method, but the results based on the ANN and GPR showed a remarkable improvement in the prediction performance over the other models. Furthermore, this study confirmed that the GPR-based model predicted relatively accurate seismic performance values compared with the model through the ANN.

From slope seismic resilience to regional road network resilience: an integrated framework for evaluating the seismic resilience of mountainous road networks

“…Therefore, even at present, although it is widely believed that resilience-based seismic design is the most advanced concept of earthquake resistance, the seismic evaluation of slope engineering mainly focuses on seismic robustness or vulnerability. For example, many studies on the seismic performance or vulnerability (fragility) of slope engineering and its related reinforcement structures are based on statistical data obtained by on-site slope earthquake disaster investigation, analytical methods, and numerical simulation methods based on physical mechanisms [10][11][12][13][14][15][16] .…”

Research on the Investment Decision Model of Power Grid Enterprises Based on Neural Network Method

“…When determining the weight of each individual indicator, some important evaluation indicators are quantified and subjective factors are eliminated to objectively reflect the importance of each indicator [3]. The project benefit evaluation methods are currently mainly concentrated in the analytic hierarchy process [4], fuzzy comprehensive evaluation method [5], gray correlation analysis method [6] and the comprehensive application of a combination of multiple methods [7].…”

Fast Seismic Assessment of Built Urban Areas with the Accuracy of Mechanical Methods Using a Feedforward Neural Network

“…However, a recurrent approach would perhaps be better suited for the challenges described in the Future Work section (for instance, extending the proposed methodology to high-rise buildings). Additionally, a good number of recent studies have focused on several improvements of the ML algorithms and methodologies used to assess the impact of seismic actions on structures [30][31][32][33][34][35].…”