Slope reliability analysis in spatially variable soils using sliced inverse regression-based multivariate adaptive regression spline

Deng, Zhi-Ping; Pan, Min; Niu, Jingtai; Jiang, Shui‐Hua; Qian, Wuwen

doi:10.1007/s10064-021-02353-9

Cited by 34 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most studies focus on the dry or saturated soil slope stability analysis. [15][16][17][18][19][20][21] In the studies on the stability analysis of unsaturated soil slopes, some researchers only considered the spatial variability of saturated hydraulic conductivity k. [22][23][24][25][26] For example, Dou et al 27,28 proposed stationary and non-stationary random variable models to characterize the variability of saturated hydraulic conductivity and established a probabilistic framework of unsaturated soil slopes based on Monte Carlo Simulation method. Le et al 29,30 took into account the spatial variability of saturated hydraulic conductivity k, and studied its influence on the stability and sliding mass size of unsaturated soil slope under constant rainfall.…”

Section: Introductionmentioning

confidence: 99%

“…In terms of the stability analysis of slopes, researchers have considered the spatial variability of soil properties nowadays. Most studies focus on the dry or saturated soil slope stability analysis 15–21 . In the studies on the stability analysis of unsaturated soil slopes, some researchers only considered the spatial variability of saturated hydraulic conductivity k 22–26 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stability of unsaturated soil slope considering stratigraphic uncertainty and rotated anisotropy of soil properties

Cao,

Zhou,

Shen

2023

Num Anal Meth Geomechanics

View full text Add to dashboard Cite

The stratigraphic uncertainty and rotated anisotropy of soil properties exist widely in nature. Recent studies have shown that the slope stability was significantly influenced by these two uncertainties. However, there is no proper method for simulating these two uncertainties at the same time, and the influence of the two uncertainties has not been considered in previous unsaturated soil slope stability analysis. This paper aims to propose a coupled method for characterizing the stratigraphic uncertainty and rotated anisotropy of soil properties, and investigate the unsaturated soil slope stability considering the two uncertainties. Through a slope case, the proposed method for characterizing the two uncertainties is examined. The effect of rotational angle on the slope stability and groundwater table is studied. In addition, four different uncertainty considerations are chosen to compare their influence on the slope stability and groundwater table. The results show that the proposed method can well characterize the two uncertainties at the same time. The rotational anisotropy of soil properties has a substantial impact on the slope stability and groundwater table. The rotational angles corresponding to the maximum and minimum reliability index of slope depend on the uncertainty considerations in the slope stability analysis. The slope reliability index only considering stratigraphic uncertainty is the highest, and the slope reliability index considering stratigraphic uncertainty and rotated anisotropy of soil properties is the lowest.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Stability of unsaturated soil slope considering stratigraphic uncertainty and rotated anisotropy of soil properties

Cao,

Zhou,

Shen

2023

Num Anal Meth Geomechanics

View full text Add to dashboard Cite

show abstract

“…It also allows for the exploration of intricate nonlinear relationships between a response variable and various predictive variables-a crucial aspect in analyzing and designing soil compaction parameters. This technique has seen successful implementations in diverse fields of geotechnical engineering, including ultimate pile bearing capacity [36], the elastic modulus of rocks [37], Slope reliability analysis [38], the compressive strength of soil [39], liquefaction [40], settlement prediction [41], and penetration resistance in clay [42]. Yet, despite its proven effectiveness in these areas, its application in compaction-related studies remains surprisingly limited.…”

Section: Introductionmentioning

confidence: 99%

Utilizing Multivariate Adaptive Regression Splines (MARS) for Precise Estimation of Soil Compaction Parameters

Abed,

Kadhim,

Almusawi

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Traditional laboratory methods for estimating soil compaction parameters, such as the Proctor test, have been recognized as time-consuming and labor-intensive. Given the increasing need for the rapid and accurate estimation of soil compaction parameters for a range of geotechnical applications, the application of machine learning models offers a promising alternative. This study focuses on employing the multivariate adaptive regression splines (MARS) model algorithm, a machine learning method that presents a significant advantage over other models through generating human-understandable piecewise linear equations. The MARS model was trained and tested on a comprehensive dataset to predict essential soil compaction parameters, including optimum water content (wopt) and maximum dry density (ρdmax). The performance of the model was evaluated using coefficient of determination (R2) and root mean square error (RMSE) values. Remarkably, the MARS models showed excellent predictive ability with high R2 and low RMSE, MAE, and relative error values, indicating its robustness and reliability in predicting soil compaction parameters. Through rigorous five-fold cross-validation, the model’s predictions for wopt returned an RMSE of 1.948%, an R2 of 0.893, and an MAE of 1.498%. For ρdmax, the results showcased an RMSE of 0.064 Mg/m3, an R2 of 0.899, and an MAE of 0.050 Mg/m3. When evaluated on unseen data, the model’s performance for wopt prediction was marked with an MAE of 1.276%, RMSE of 1.577%, and R2 of 0.948. Similarly, for ρdmax, the predictions were characterized by an MAE of 0.047 Mg/m3, RMSE of 0.062 Mg/m3, and R2 of 0.919. The results also indicated that the MARS model outperformed previously developed machine learning models, suggesting its potential to replace conventional testing methods. The successful application of the MARS model could revolutionize the geotechnical field through providing quick and reliable predictions of soil compaction parameters, improving efficiency for construction projects. Lastly, a variable importance analysis was performed on the model to assess how input variables affect its outcomes. It was found that fine content (Cf) and plastic limit (PL) have the greatest impact on compaction parameters.

show abstract

“…Rotation-based linear mapping techniques (Constantine et al, 2014;Yang et al, 2016) required partial derivatives of input variables and output, which may be computationally expensive. Alternatively, the input variables are linearly combined and transformed into a new dimensionality-reduced space, such as principal component analysis (PCA) (Jolliffe, 2002) and sliced inverse regression (SIR) (Li, 2000;Pan and Dias, 2017;Li et al, 2019b;Deng et al, 2021). Specifically, PCA takes the principle of maximizing the variance to linearly combine the original space.…”

Section: Introductionmentioning

confidence: 99%

Adaptive slope reliability analysis method based on sliced inverse regression dimensionality reduction

Zhou,

Xiong,

et al. 2023

Front. Ecol. Evol.

View full text Add to dashboard Cite

The response surface model has been widely used in slope reliability analysis owing to its efficiency. However, this method still has certain limitations, especially the curse of high dimensionality when considering the spatial variability of geotechnical parameters. The slice inverse regression dimensionality reduction method is efficient to obtaining the dimensionality-reduction variables from the original soil parameters space, before constructing the response surface. However, the dimensionality reduction process may cause accuracy deficiency due to the loss of variable information. An adaptive slope reliability analysis method is proposed to quantify and correct information loss and errors. Additionally, the slope failure probability based on the response surface in the dimensionality reduction space is modified to an unbiased one based on the finite model in the original space. In this study, two soil slopes considering spatial variability are taken as examples. The results illustrate that this method can effectively reduce the loss of accuracy in the dimensionality reduction process, while obtaining unbiased finite-element-based failure probability effectually. The method addresses the limitation whereby the accuracy of the dimensionality reduction process depends on the sample size and the number of dimensionality-reduction variables. Simultaneously, the proposed method significantly improves the computational efficiency of the sliced inverse regression method and realizes a reasonable dimensionality reduction effect, thereby improving the application of the response surface in practical slope reliability high-dimensional issues.

show abstract

Slope reliability analysis in spatially variable soils using sliced inverse regression-based multivariate adaptive regression spline

Cited by 34 publications

References 35 publications

Stability of unsaturated soil slope considering stratigraphic uncertainty and rotated anisotropy of soil properties

Stability of unsaturated soil slope considering stratigraphic uncertainty and rotated anisotropy of soil properties

Utilizing Multivariate Adaptive Regression Splines (MARS) for Precise Estimation of Soil Compaction Parameters

Adaptive slope reliability analysis method based on sliced inverse regression dimensionality reduction

Contact Info

Product

Resources

About