A hybrid ensemble method for improved prediction of slope stability

Accurate prediction of slope stability is a significant issue in geomechanics with many artificial intelligence (AI) techniques being utilised. However, the application of AI has not reached its full potential because of the lack of more robust algorithms. In this paper, we proposed a hybrid ensemble method for the improved prediction of slope stability using classifier ensembles and genetic algorithm. Gaussian process classification, quadratic discriminant analysis, support vector machine, artificial neural networks, adaptive boosted decision trees, and k‐nearest neighbours were chosen to be individual AI techniques, and the weighted majority voting was used as the combination method. Validation method was chosen to be the 10‐fold cross‐validation, and performance measures were selected to be the accuracy, the receiver operating characteristic curve, and the area under the receiver operating characteristic curve (AUC). Grid search and genetic algorithm were used for the hyperparameter tuning and weight tuning respectively. The results show that the proposed hybrid ensemble method has great potential in improving the prediction of slope stability. Compared with individual classifiers, the optimum ensemble classifier achieved the highest AUC value (0.943) and the highest accuracy (0.902) on the testing set, denoting that the predictive performance has been improved. The optimum ensemble classifier with the Youden's cut‐off was recommended for slope stability prediction with respect to the AUC value, the accuracy, the true positive rate, and the true negative rate. This research indicates that the use of the classifier ensembles, rather than the search for the ideal individual classifiers, might help for the slope stability prediction.     

An extreme learning machine approach for slope stability evaluation and prediction

This paper presents slope stability evaluation and prediction with the approach of a fast robust neural network named the extreme learning machine (ELM). The circular failure mechanism of a slope is formulated based on its material, geometrical and environmental parameters such as the unit weight, the cohesion, the internal friction angle, the slope inclination, slope height and the pore water ratio. The ELM is proposed to evaluate the stability of slopes subjected to potential circular failures by means of prediction of the factor of safety (FS). Substantial slope cases collected worldwide are utilized to illustrate and assess the capability and predictability of the ELM on slope stability analysis. Based on the mean absolute percentage errors and the correlation coefficients between the original and predicted FS values, comparisons are demonstrated between the ELM and the generalized regression neural network (GRNN) as well as the prediction models generated from the genetic algorithms. Moreover, sensitivity analysis of the slope parameters and the ELM model parameters is carried out based on the two utilized evaluation functions. The time expense of the ELM on slope stability analysis is also investigated. The results prove that the ELM is advantageous to the GRNN and the genetic algorithm based models in the analysis of slope stability. Hence, the ELM can be a promising technique for approaching the problems in geotechnical engineering.     

A study of slope stability prediction using neural networks

The determination of the non-linear behaviour of multivariate dynamic systems often presents a challenging and demanding problem. Slope stability estimation is an engineering problem that involves several parameters. The impact of these parameters on the stability of slopes is investigated through the use of computational tools called neural networks. A number of networks of threshold logic unit were tested, with adjustable weights. The computational method for the training process was a back-propagation learning algorithm. In this paper, the input data for slope stability estimation consist of values of geotechnical and geometrical input parameters. As an output, the network estimates the factor of safety (FS) that can be modelled as a function approximation problem, or the stability status (S) that can be modelled either as a function approximation problem or as a classification model. The performance of the network is measured and the results are compared to those obtained by means of standard analytical methods. Furthermore, the relative importance of the parameters is studied using the method of the partitioning of weights and compared to the results obtained through the use of Index Information Theory.     

基于概率神经网络的岩土边坡稳定性预测方法

基于数据挖掘技术和智能系统,提出应用概率神经网络预测边坡稳定性的数值方法。根据大量边坡稳定或者失稳案例记录的数据库资料,采用数据挖掘方法能够从中提炼出有价值的分类模式。将岩土边坡的力学参数和几何形状作为神经网络的输入训练和测试神经网络。实际应用显示所建立的概率神经网络预测边坡稳定的实用性。与传统的极限平衡分析方法和极大似然估计方法相对比,所提出的概率神经网络具有更高的预测精度。     

LiDAR-supported prediction of slope failures using an integrated ensemble weights-of-evidence and analytical hierarchy process

The present study investigates a potential application of different resolution topographic data obtained from airborne LiDAR and an integrated ensemble weight-of-evidence and analytic hierarchy process (WoE–AHP) model to spatially predict slope failures. Previously failed slopes of the Pellizzano (Italy) were remotely mapped and divided into two subsets for training and testing purposes. 1, 2, 5, 10, 15, and 20 m topographic data were processed to extract nine terrain attributes identified as conditioning factors for landslides: slope degree, aspect, altitude, plan curvature, profile curvature, stream power index, topographic wetness index, sediment transport index, and topographic roughness index. Landslide (slope failure) susceptibility maps were produced using a single WoE (Model 1), an ensemble WoE–AHP model that used all conditioning factors (Model 2), and an ensemble WoE–AHP model that only used highly nominated conditioning factors (Model 3). The validation results proved the efficiency of high-resolution (≤ 5 m) topographic data and the ensemble model, particularly when all factors were used in the modeling process (Model 2). The average success rates and prediction rates for Model 2 that used ≤ 5 m resolution datasets were 84.26 and 82.78%, respectively. The finding presented in this paper can aid in planning more efficient LiDAR surveys and the handling of large datasets, and in gaining a better understanding of the nature of the predictive models.     

有限元强度折减法计算边坡稳定的对比分析

采用目前边坡稳定性分析比较流行的强度折减法,对比研究了MIDAS/GTS、FLAC、ANSYS配合Drucker-Prager（简称D-P）屈服准则和Mohr-Coulomb（简称M-C）屈服准则时软黏土、硬黏土、弱膨胀土3种工况下计算结果的偏差。软黏土工况下D-P准则和M-C准则计算结果的偏差相对较小,当边坡土体为硬黏土时,采用D-P准则与采用M-C准则计算结果的偏差明显增加。3种软件2种屈服准则下的计算结果都反映出,硬黏土的滑动面比弱膨胀土和软黏土的滑动面浅,而且同等情况下MIDAS计算得到的滑动面比ANSYS计算得到的滑动面浅;坡度较小时FLAC（M-C）计算的安全系数比MIDAS（M-C）计算得到的大,坡度较大时则相反;坡度较小时计算过程中先出现塑性区贯通,后出现计算不收敛;坡度较大时计算过程中先出现计算不收敛,后出现塑性区贯通。坡度较小时计算不收敛时的折减系数与出现塑性区贯通时的折减系数差别较大;坡度较大时这一差别较小,甚至计算到不收敛时塑性区仍未贯通,在用MIDAS计算时这一现象反映得更加明显。     

Prediction of safety factors for slope stability: comparison of machine learning techniques

Natural Hazards - Because of the disasters associated with slope failure, the analysis and forecasting of slope stability for geotechnical engineers are crucial. In this work, in order to forecast...     

Improving the coastal aquifers’ vulnerability assessment using SCMAI ensemble of three machine learning approaches

The main objective of this study is to integrate adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM) and artificial neural network (ANN) to design an integrated supervised committee machine artificial intelligence (SCMAI) model to spatially predict the groundwater vulnerability to seawater intrusion in Gharesoo-Gorgan Rood coastal aquifer placed in the northern part of Iran. Six hydrological GALDIT parameters (i.e., G groundwater occurrence, A aquifer hydraulic conductivity, L level of groundwater above sea level, D distance from the shore, I impact of the existing status of seawater intrusion in the region, and T thickness of the aquifer) were considered as inputs for each model. In the training step, the values of GALDIT’s vulnerability index were conditioned by using the values of TDS concentration in order to obtain the conditioned vulnerability index (CVI). The CVI was considered as the target for each model. After training the models, each model was tested using a separate TDS dataset. The results indicated that the ANN and ANFIS algorithms performed better than the SVM algorithm. The values of correlation were obtained as 88, 87, and 80% for ANN, ANFIS, and SVM models, respectively. In the testing step of the SCMAI model, the values of RMSE, R², and r were obtained as 6.4, 0.95, and 97%, respectively. Overall, SCMAI model outperformed other models to spatially predicting vulnerable zones. The result of the SCMAI model confirmed that the western zones along the shoreline had the highest vulnerability to seawater intrusion; therefore, it seems critical to consider emergency protection plans for study area.

Graphic abstract

     

高斯过程机器学习在边坡稳定性评价中的应用

针对边坡工程是复杂的非线性系统,采用常规的理论分析和数值计算方法难以满足对边坡稳定性评价的高精度与快速性的要求,为此,提出对处理非线性复杂问题具有很好的适应性一种有概率意义的核学习机--高斯过程机器学习方法来解决边坡稳定性的合理评价问题,建立了相应的边坡稳定性预测模型。工程应用研究结果表明,采用高斯过程机器学习方法进行边坡稳定性评价是科学可行的,该方法能很好地表达边坡稳定性与各影响因素之间的非线性映射关系,能方便快捷地给出合理可靠且具有概率意义的边坡稳定状态评价结果,为实现边坡快速设计的工程实践要求提供了一条新的途径。     

降雨条件下土质边坡稳定性预测预报方法

降雨往往足引起热带和亚热带膨胀土、残积土边坡失稳的主要促发因素,考虑降雨影响的土坡稳定性预测预报是一个亟待解决的复杂的工程问题.简要介绍了一套能考虑气候影响的非饱和土边坡稳定性分析的极限平衡分析方法和一套可考虑土体非线性和几何非线性的边坡稳定分析及变形计算的有限元方法.提出了一个降雨条件下土质边坡稳定性预测预报模型,其具体思路是:首先用数值方法计算渗流场,然后利用非饱和土的强度理论推求出整个场的强度分布,再利用极限平衡分析方法或有限元方法进行边坡稳定性分析,寻求斜坡稳定安全因数与降雨特征参数(雨强,降雨持时等)相关关系,如此,即可依据气象预报进行土坡稳定性预报.     

Comparative study of Sarma's method and the discontinuous deformation analysis for rock slope stability analysis

This paper presents a comparative study of two methods, Sarma's method and the discontinuous deformation analysis (DDA), for rock slope stability analysis. The comparison concerns the stability analysis of two classic rock slopes. The study shows that the DDA, which accounts for the block kinematics, provides a very different factor of safety as compared with Sarma's method. More realistic reaction forces around each rock block can be obtained by the DDA, including the thrust forces between rock blocks and the forces between the base and the blocks. The DDA's result shows two possible directions for the relative movement between two contiguous blocks at the initiation of slope failure. It also indicates that the limit equilibrium condition may not occur along the interfaces of rock blocks at the initiation of slope failure. The determination of realistic interaction forces around each block will be very important in rock slope stability analysis if nonlinear failure criteria are considered.     

Improved prediction of clay soil expansion using machine learning algorithms and meta-heuristic dichotomous ensemble classifiers

Soil swelling-related disaster is considered as one of the most devastating geo-hazards in modern history.Hence,proper determination of a soil’s ability to expand is very vital for achieving a secure and safe ground for infrastructures.Accordingly,this study has provided a novel and intelligent approach that enables an improved estimation of swelling by using kernelised machines(Bayesian linear regression(BLR)&bayes point machine(BPM)support vector machine(SVM)and deep-support vector machine(D-SVM));(multiple linear regressor(REG),logistic regressor(LR)and artificial neural network(ANN)),tree-based algorithms such as decision forest(RDF)&boosted trees(BDT).Also,and for the first time,meta-heuristic classifiers incorporating the techniques of voting(VE)and stacking(SE)were utilised.Different independent scenarios of explanatory features’combination that influence soil behaviour in swelling were investigated.Preliminary results indicated BLR as possessing the highest amount of deviation from the predictor variable(the actual swell-strain).REG and BLR performed slightly better than ANN while the meta-heuristic learners(VE and SE)produced the best overall performance(greatest R2 value of 0.94 and RMSE of 0.06%exhibited by VE).CEC,plasticity index and moisture content were the features considered to have the highest level of importance.Kernelized binary classifiers(SVM,D-SVM and BPM)gave better accuracy(average accuracy and recall rate of 0.93 and 0.60)compared to ANN,LR and RDF.Sensitivity-driven diagnostic test indicated that the meta-heuristic models’best performance occurred when ML training was conducted using k-fold validation technique.Finally,it is recommended that the concepts developed herein be deployed during the preliminary phases of a geotechnical or geological site characterisation by using the best performing meta-heuristic models via their background coding resource.     

基于MATLAB的边坡稳定性极限上限分析程序开发

基于系统能耗最小原理的极限分析上限定理,利用MATLAB强大的数据处理功能,对边坡稳定系数Ncr采用序列二次规划法（SQP）进行优化计算,并与枚举法相结合,从而解决SQP算法求解优化解容易陷入局部最优解的问题。同时开发了一款简单实用的边坡稳定性分析软件,实现了计算结果与临界滑裂破坏面图形的可视化输出。与经典算例对比分析,计算结果具有较好的一致性,表明了程序的可靠性。分析了内摩擦角?、边坡倾斜角?、? 3个参数对边坡稳定系数Ncr的影响。计算结果表明：边坡稳定性系数Ncr对?、? 较为敏感,而对? 的敏感次之。其次,当?、? 比较接近或在小范围内波动时,对稳定性系数Ncr的影响特别敏感;当?、?值较小时,滑动面通过坡趾下方,而当?值比较大时,滑动面通过坡趾。     

黄土坡体节理发育特征和空间分区与边坡稳定性

通过现场调查分析了黄土坡体节理发育特征,节理走向与边坡倾向呈大角度斜交,节理走向受边坡倾向的控制。根据对斜坡不同区域受力分析,台塬区土体主要受到湿陷拉张作用,在斜坡地带土体主要受水平卸荷所产生的推力作用,把斜坡区节理发育分为湿陷节理发育区、拉张节理发育区、挤压节理发育区和开挖卸荷节理发育区。最后,对有无节理边坡进行了稳定性计算,计算结果和理论分析一致。      

Analytical method for analysis of slope stability

An analytical method is presented for analysis of slope stability involving cohesive and non-cohesive soils. Earthquake effects are considered in an approximate manner in terms of seismic coefficient-dependent forces. Two kinds of failure surfaces are considered in this study: a planar failure surface, and a circular failure surface. The proposed method can be viewed as an extension of the method of slices, but it provides a more accurate treatment of the forces because they are represented in an integral form. The factor of safety is obtained by using the minimization technique rather than by a trial and error approach used commonly. The factors of safety obtained by the analytical method are found to be in good agreement with those determined by the local minimum factor-of-safety, Bishop's, and the method of slices. The proposed method is straightforward, easy to use, and less time-consuming in locating the most critical slip surface and calculating the minimum factor of safety for a given slope. Copyright © 1999 John Wiley & Sons, Ltd.     

水下岩质边坡稳定性计算模式的探讨

论文讨论了水下岩质边坡稳定性分析中平面型滑动及其边坡后缘出现拉张裂缝等两种计算模式,着重分析了水下岩质边坡的受力机理,推导了考虑动水的水流速度及不同的滑动面倾角等水下岩质边坡稳定性评价公式,得到了岩质边坡稳定系数与水流速度的关系曲线和岩质边坡稳定系数与滑动面夹角的关系曲线.通过实例计算,讨论了水下岩质边坡后缘出现拉张裂缝后稳定性评价的主要影响因素及其变化规律.当考虑水流速度对边坡的作用时,边坡的稳定性明显下降.     

Effectiveness of horizontal drains for slope stability

Horizontal drains have been commonly used in stabilising unsaturated residual soil slopes. This study examines the effectiveness of horizontal drains in stabilising residual soil slopes against rainfall-induced slope failures under a tropical climate. The study includes field instrumentation at two residual soil slopes complemented with a parametric study relating to drain position. Field monitoring results indicate that rainfall infiltration is limited to a certain depth below which infiltration becomes insignificant. This zone tends to be unsuitable for horizontal drains. Horizontal drains were found to be most effective when located at the base of a slope. The parametric study indicated conditions under which horizontal drains are effective or ineffective in improving the stability of a slope. It was also found that horizontal drains have little role in minimising infiltration in an unsaturated residual soil slope. Benefits of using horizontal drains can be obtained through the lowering of the water table.     

黄土高边坡的三维动力稳定性分析——以固原九龙山边坡为例

针对高烈度区九龙山黄土高边坡的动力稳定性问题,调查分析了该边坡的工程地质条件和场地所在区域构造活动与分布特征。在考察动荷载循环、往复作用下黄土反应敏感性及动强度参数,以及沿坡高确定地震惯性力反应地震作用大小的基础上,将强度参数折减与有限差分方法结合,从而形成了边坡的拟静力强度折减有限差分分析方法。通过九龙山土边坡拟静力强度折减三维有限差分法计算分析,得到了强度折减条件下边坡的位移场和应力场,边坡关键点位移与折减系数之间的关系,以及黄土高边坡的动力稳定性安全系数。其分析结果与传统的二维极限平衡分析方法确定的结果基本一致,验证了边坡拟静力强度折减有限差分方法的合理性。     

A comparative study of slip velocity models for the prediction of performance of floatex density separator

The separation features of the floatex density separator (FDS) are investigated through experimental and computational approaches. It has been shown that the performance of the FDS can be predicted reasonably well using a slip velocity model and steady-state mass balance equations. The approach for the formulation of the slip velocity model makes a difference in the prediction of FDS performance. The computed data from four different slip velocity models have been compared and contrasted with the experimental observations. It has been shown that a slip velocity model based on the modified Richardson and Zaki equation, in which the dissipative pressure gradient is considered to be the primary driving force for separation, predicts the performance more accurately than the other three. A deslimed feed is recommended for better performance of the FDS.     

An evaluation of various data pre-processing techniques with machine learning models for water level prediction

Natural Hazards - Floods are the most frequent type of natural disaster. It destroys wildlife habitat, damages bridges, railways, roads, properties, and puts millions of people at risk. As such,...