Efficient reliability analysis of earth dam slope stability using extreme gradient boosting method

Reliability analysis approach provides a rational means to quantitatively evaluate the safety of geotechnical structures from a probabilistic perspective. However, it suffers from a known criticism of extensive computational requirements and poor efficiency, which hinders its application in the reliability analysis of earth dam slope stability. Until now, the effects of spatially variable soil properties on the earth dam slope reliability remain unclear. This calls for a novel method to perform reliability analysis of earth dam slope stability accounting for the spatial variability of soil properties. This paper develops an efficient extreme gradient boosting (XGBoost)-based reliability analysis approach for evaluating the earth dam slope failure probability. With the aid of the proposed approach, the failure probability of earth dam slope can be evaluated rationally and efficiently. The proposed approach is illustrated using a practical case adapted from Ashigong earth dam. Results show that the XGBoost-based reliability analysis approach is able to predict the earth dam slope failure probability with reasonable accuracy and efficiency. The coefficient of variations and scale of fluctuations of soil properties affect the earth dam slope failure probability significantly. Moreover, the earth dam slope failure probability is highly dependent on the selection of auto-correlation function (ACF), and the widely used single exponential ACF tends to provide an unconservative estimate in this study.

[1]  Wenjun Liu,et al.  Empirical and semi-analytical models for predicting peak outflows caused by embankment dam failures , 2018, Journal of Hydrology.

[2]  Wengang Zhang,et al.  Bayesian Approach for Predicting Soil-Water Characteristic Curve from Particle-Size Distribution Data , 2019, Energies.

[3]  Siu-Kui Au,et al.  Determination of site-specific soil-water characteristic curve from a limited number of test data – A Bayesian perspective , 2017 .

[4]  Hongping Zhu,et al.  Assessing small failure probabilities by AK–SS: An active learning method combining Kriging and Subset Simulation , 2016 .

[5]  Harianto Rahardjo,et al.  PERMEABILITY FUNCTIONS FOR UNSATURATED SOILS , 1997 .

[6]  Yu Wang,et al.  Efficient Monte Carlo Simulation of parameter sensitivity in probabilistic slope stability analysis , 2010 .

[7]  Sung-Eun Cho.  Probabilistic analysis of seepage that considers the spatial variability of permeability for an embankment on soil foundation , 2012 .

[8]  Michael A. Hicks,et al.  Influence of length effect on embankment slope reliability in 3D , 2018 .

[9]  K. Phoon,et al.  Characterization of Geotechnical Variability , 1999 .

[10]  John P. Turner,et al.  Probabilistic Slope Stability Analysis with Stochastic Soil Hydraulic Conductivity , 2001 .

[11]  Kok-Kwang Phoon,et al.  Probabilistic Analysis of Soil-Water Characteristic Curves , 2010 .

[12]  Anthony T. C. Goh,et al.  Multivariate adaptive regression splines and neural network models for prediction of pile drivability , 2016 .

[13]  Anthony T. C. Goh,et al.  Multivariate adaptive regression splines for analysis of geotechnical engineering systems , 2013 .

[14]  Shuai Zhang,et al.  Efficient Bayesian networks for slope safety evaluation with large quantity monitoring information , 2017, Geoscience Frontiers.

[15]  Kok-Kwang Phoon,et al.  Effects of soil spatial variability on rainfall-induced landslides , 2011 .

[16]  Huabei Liu,et al.  Bayesian network models for probabilistic evaluation of earthquake-induced liquefaction based on CPT and Vs databases , 2019, Engineering Geology.

[17]  Harianto Rahardjo,et al.  Unsaturated Soil Mechanics in Engineering Practice: Fredlund/Unsaturated Soil Mechanics , 2012 .

[18]  Yu Wang,et al.  Direct simulation of random field samples from sparsely measured geotechnical data with consideration of uncertainty in interpretation , 2018, Canadian Geotechnical Journal.

[19]  Tzu-Tsung Wong,et al.  Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation , 2015, Pattern Recognit..

[20]  G. L. Sivakumar Babu,et al.  Reliability Analysis of Earth Dams , 2010 .

[21]  Erik H. Vanmarcke,et al.  Random Fields: Analysis and Synthesis. , 1985 .

[22]  Dian-Qing Li,et al.  A multiple response-surface method for slope reliability analysis considering spatial variability of soil properties , 2015 .

[23]  T. Le,et al.  Stability and failure mass of unsaturated heterogeneous slopes Thi Minh Hue Le, Domenico Gallipoli, Marcelo Sánchez, and Simon Wheeler , 2015 .

[24]  Amit Srivastava,et al.  Influence of spatial variability of permeability property on steady state seepage flow and slope stability analysis , 2010 .

[25]  Y. Mualem.  A New Model for Predicting the Hydraulic Conductivity , 1976 .

[26]  D. Montgomery,et al.  Comparing Computer Experiments for the Gaussian Process Model Using Integrated Prediction Variance , 2013 .

[27]  Yu Wang,et al.  Bayesian model comparison and selection of spatial correlation functions for soil parameters , 2014 .

[28]  K. Phoon,et al.  Simulation of Random Fields with Trend from Sparse Measurements without Detrending , 2019, Journal of Engineering Mechanics.

[29]  L. A. Richards.  Capillary conduction of liquids through porous mediums , 1931 .

[30]  Lei-Lei Liu,et al.  Efficient system reliability analysis of soil slopes using multivariate adaptive regression splines-based Monte Carlo simulation , 2016 .

[31]  Gordon A. Fenton,et al.  Statistics of free surface flow through stochastic earth dam , 1996 .

[32]  Liang Li,et al.  Reliability back analysis of shear strength parameters of landslide with three-dimensional upper bound limit analysis theory , 2016, Landslides.

[33]  Dian-Qing Li,et al.  Enhancement of random finite element method in reliability analysis and risk assessment of soil slopes using Subset Simulation , 2016, Landslides.

[34]  Yu Wang,et al.  Bayesian perspective on geotechnical variability and site characterization , 2016 .

[35]  Jie Zhang,et al.  Reliability analysis of slope stability under seismic condition during a given exposure time , 2018, Landslides.

[36]  Sung-Eun Cho.  Probabilistic Assessment of Slope Stability That Considers the Spatial Variability of Soil Properties , 2010 .

[37]  Delwyn G. Fredlund,et al.  Unsaturated Soil Mechanics in Engineering Practice , 2012 .

[38]  Dian-Qing Li,et al.  Response surface methods for slope reliability analysis: Review and comparison , 2016 .

[39]  Delwyn G. Fredlund,et al.  Statistical assessment of soil-water characteristic curve models for geotechnical engineering , 2001 .

[40]  Y. Cheng,et al.  Effects of spatial autocorrelation structure of permeability on seepage through an embankment on a soil foundation , 2017 .

[41]  Yufeng Gao,et al.  Effect of 2D spatial variability on slope reliability: A simplified FORM analysis , 2017, Geoscience Frontiers.

[42]  Kok-Kwang Phoon,et al.  Simulation of non-stationary non-Gaussian random fields from sparse measurements using Bayesian compressive sampling and Karhunen-Loève expansion , 2019, Structural Safety.

[43]  Yu WangY. Wang,et al.  Practical reliability analysis of slope stability by advanced Monte Carlo simulations in a spreadsheet , 2011 .

[44]  Dianqing Li,et al.  Reliability analysis of unsaturated slope stability considering SWCC model selection and parameter uncertainties , 2019, Engineering Geology.

[45]  Mary Ellen Hynes,et al.  Assessment of remedial measures to reduce exceedance probability of performance limit states in embankment dams , 2015 .

[46]  J. Beck,et al.  Estimation of Small Failure Probabilities in High Dimensions by Subset Simulation , 2001 .

[47]  Yung-ming Cheng,et al.  Advanced reliability analysis of slopes in spatially variable soils using multivariate adaptive regression splines , 2019, Geoscience Frontiers.

[48]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[49]  Van Genuchten,et al.  A closed-form equation for predicting the hydraulic conductivity of unsaturated soils , 1980 .

[50]  Siu-Kui Au,et al.  Engineering Risk Assessment with Subset Simulation , 2014 .

[51]  José Antonio Lozano,et al.  Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[52]  Simon J. Wheeler,et al.  Stochastic analysis of unsaturated seepage through randomly heterogeneous earth embankments , 2012 .

[53]  Andy Liaw,et al.  Extreme Gradient Boosting as a Method for Quantitative Structure-Activity Relationships , 2016, J. Chem. Inf. Model..

[54]  E. C. Childs,et al.  The permeability of porous materials , 1950, Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.

[55]  D. E. Pufahl,et al.  Model for the prediction of shear strength with respect to soil suction , 1996 .

[56]  Yang Zhao,et al.  Deep learning-based feature engineering methods for improved building energy prediction , 2019, Applied Energy.

[57]  Yu Wang,et al.  Direct simulation of two-dimensional isotropic or anisotropic random field from sparse measurement using Bayesian compressive sampling , 2019, Stochastic Environmental Research and Risk Assessment.

[58]  Ashraf A. Ahmed,et al.  Stochastic analysis of free surface flow through earth dams , 2009 .

[59]  Lei Zhang,et al.  Probabilistic stability analyses of undrained slopes by 3D random fields and finite element methods , 2017, Geoscience Frontiers.

[60]  D. V. Griffiths,et al.  EXTREME HYDRAULIC GRADIENT STATISTICS IN STOCHASTIC EARTH DAM , 1997 .