Support vector machines‐based modelling of seismic liquefaction potential

This paper investigates the potential of support vector machines (SVM)‐based classification approach to assess the liquefaction potential from actual standard penetration test (SPT) and cone penetration test (CPT) field data. SVMs are based on statistical learning theory and found to work well in comparison to neural networks in several other applications. Both CPT and SPT field data sets is used with SVMs for predicting the occurrence and non‐occurrence of liquefaction based on different input parameter combination. With SPT and CPT test data sets, highest accuracy of 96 and 97%, respectively, was achieved with SVMs. This suggests that SVMs can effectively be used to model the complex relationship between different soil parameter and the liquefaction potential. Several other combinations of input variable were used to assess the influence of different input parameters on liquefaction potential. Proposed approach suggest that neither normalized cone resistance value with CPT data nor the calculation of standardized SPT value is required with SPT data. Further, SVMs required few user‐defined parameters and provide better performance in comparison to neural network approach. Copyright © 2006 John Wiley & Sons, Ltd.     

Artificial neural network and liquefaction susceptibility assessment: a case study using the 2001 Bhuj earthquake data,Gujarat, India

This study pertains to prediction of liquefaction susceptibility of unconsolidated sediments using artificial neural network (ANN) as a prediction model. The backpropagation neural network was trained, tested, and validated with 23 datasets comprising parameters such as cyclic resistance ratio (CRR), cyclic stress ratio (CSR), liquefaction severity index (LSI), and liquefaction sensitivity index (LSeI). The network was also trained to predict the CRR values from LSI, LSeI, and CSR values. The predicted results were comparable with the field data on CRR and liquefaction severity. Thus, this study indicates the potentiality of the ANN technique in mapping the liquefaction susceptibility of the area.     

Assessment and Prediction of Liquefaction Potential Using Different Artificial Neural Network Models: A Case Study

Soil liquefaction as a transformation of granular material from solid to liquid state is a type of ground failure commonly associated with moderate to large earthquakes and refers to the loss of strength in saturated, cohesionless soils due to the build-up of pore water pressures and reduction of the effective stress during dynamic loading. In this paper, assessment and prediction of liquefaction potential of soils subjected to earthquake using two different artificial neural network models based on mechanical and geotechnical related parameters (model A) and earthquake related parameters (model B) have been proposed. In model A the depth, unit weight, SPT-N value, shear wave velocity, soil type and fine contents and in model B the depth, stress reduction factor, cyclic stress ratio, cyclic resistance ratio, pore pressure, total and effective vertical stress were considered as network inputs. Among the numerous tested models, the 6-4-4-2-1 structure correspond to model A and 7-5-4-6-1 for model B due to minimum network root mean square errors were selected as optimized network architecture models in this study. The performance of the network models were controlled approved and evaluated using several statistical criteria, regression analysis as well as detailed comparison with known accepted procedures. The results represented that the model A satisfied almost all the employed criteria and showed better performance than model B. The sensitivity analysis in this study showed that depth, shear wave velocity and SPT-N value for model A and cyclic resistance ratio, cyclic stress ratio and effective vertical stress for model B are the three most effective parameters on liquefaction potential analysis. Moreover, the calculated absolute error for model A represented better performance than model B. The reasonable agreement of network output in comparison with the results from previously accepted methods indicate satisfactory network performance for prediction of liquefaction potential analysis.     

Application of the adaptive neuro-fuzzy inference system for prediction of soil liquefaction

The determination of liquefaction potential of soils induced by earthquake is a major concern and an essential criterion in the design process of the civil engineering structures. A purely empirical interpretation of the filed case histories relating to liquefaction potential is often not well constrained due to the complication associated with this problem. In this study, an integrated fuzzy neural network model, called Adaptive Neuro-Fuzzy Inference System (ANFIS), is developed for the assessment of liquefaction potential. The model is trained with large databases of liquefaction case histories. Nine parameters such as earthquake magnitude, the water table, the total vertical stress, the effective vertical stress, the depth, the peak acceleration at the ground surface, the cyclic stress ratio, the mean grain size, and the measured cone penetration test tip resistance were used as input parameters. The results revealed that the ANFIS model is a fairly promising approach for the prediction of the soil liquefaction potential and capable of representing the complex relationship between seismic properties of soils and their liquefaction potential.     

Reliability assessment of serviceability performance of braced retaining walls using a neural network approach

In urban environments, one major concern with deep excavations in soft clay is the potentially large ground deformations in and around the excavation. Excessive movements can damage adjacent buildings and utilities. There are many uncertainties associated with the calculation of the ultimate or serviceability performance of a braced excavation system. These include the variabilities of the loadings, geotechnical soil properties, and engineering and geometrical properties of the wall. A risk‐based approach to serviceability performance failure is necessary to incorporate systematically the uncertainties associated with the various design parameters. This paper demonstrates the use of an integrated neural network–reliability method to assess the risk of serviceability failure through the calculation of the reliability index. By first performing a series of parametric studies using the finite element method and then approximating the non‐linear limit state surface (the boundary separating the safe and ‘failure’ domains) through a neural network model, the reliability index can be determined with the aid of a spreadsheet. Two illustrative examples are presented to show how the serviceability performance for braced excavation problems can be assessed using the reliability index. Copyright © 2005 John Wiley & Sons, Ltd.     

基于Logistic回归模型的砂土液化概率评价

以国内外23次地震中200组场地液化实测数据为基础,通过Logistic回归分析,建立关联修正标准贯入击数N160cs与循环应力比CSR的液化概率模型。以50 %液化概率水平为液化与非液化的临界点,建立了指数形式的抗液化应力比CRR计算式,新建概率模型预测饱和砂土液化与非液化的成功率分别为85.71 %和76.14 %,具有较高的可靠性。与已有模型比较,使用了新的数据和修正系数,消除了一些不合理的偏差,总体判别结果偏于安全。为了将确定性分析方法与概率分析方法联系起来,建立了抗液化安全系数FS与液化概率PL的关系式。算例结果表明,新建概率模型简单、实用、可靠。     

Liquefaction and cyclic mobility model for saturated granular media

A new constitutive law for the behaviour of undrained sand subjected to dynamic loading is presented. The proposed model works for small and large strain ranges and incorporates contractive and dilative properties of the sand into the unified numerical scheme. These features allow to correctly predict liquefaction and cyclic mobility phenomena for different initial relative densities of the soil. The model has been calibrated as an element test, by using cyclic simple shear data reported in the literature. For the contractive sand behaviour a well‐known endochronic densification model has been used, whereas a plastic model with a new non‐associative flow rule is applied when the sand tends to dilate. Both dilatancy and flow rule are based on a new state parameter, associated to the stiffness degradation of the material as the shaking goes on. Also, the function that represents the rearrangement memory of the soil takes a zero value when the material dilates, in order to easily model the change in the internal structure. Proceeding along this kind of approach, liquefaction and cyclic mobility are modelled with the same constitutive law, within the framework of a bi‐dimensional FEM coupled algorithm developed in the paper. For calibration purposes, the behaviour of the soil in a cyclic simple shear test has been simulated, in order to estimate the influence of permeability, frequency of loading, and homogeneity of the shear stress field on the laboratory data. Copyright © 2006 John Wiley & Sons, Ltd.     

Cyclic liquefaction screening of sand with non-plastic fines:Critical state approach

There have been significant advances in the application of critical state,CS,in liquefaction potential assessment.This was done by comparing state parameter,j with estimated characteristic cyclic stress ratio,CSR due to an earthquake.A cyclic resistance ratio,CRR curve,which can be determined from cyclic liquefaction tests,separates historical liquefied and non-liquefied data points(j,CSR).On the other hand,the concepts of equivalent granular state parameter,j*,which was developed for sands with fines,can be used in lieu j to provide a unifying framework for characterizing the undrained response of sands with non/low plasticity fines,irrespective of fines content(fc).The present work combines these two propositions,and by merely substituting j*for j into the aforementioned CS approach to capture the influence of fc.A series of static and cyclic triaxial tests were conducted,separately and independently of the concept of j*,for sand with up to fc of 30%.The clean sand was collected from Sabarmati river belt at Ahmedabad city in India which was severely affected during the Bhuj earthquake,2001.The experimental data gave a single relation for CRR and j*which was then used to assess liquefaction potential for a SPT based case study,where fc varies along the depth.The prediction matched with the field observation.     

Prediction of cyclic resistance ratio for silty sands and its applications in the simplified liquefaction analysis

Liquefaction resistance of granular soils is commonly characterized by the cyclic resistance ratio (CRR) in the simplified shear stress procedure of liquefaction potential assessment. This parameter is commonly estimated by cyclic tests on reconstituted samples or empirical correlations between liquefied/non-liquefied case histories. The current study employs results of cyclic triaxial tests on reconstituted soil specimens and presents a predictive equation for cyclic resistance ratio (CRR) of clean and silty sands. The CRR equation is a function of relative density, effective mean confining pressure, non-plastic fines content, number of harmonic cycles for liquefaction onset, and some other basic soil properties. It is demonstrated that the developed relationship obtains reasonable accuracy in the prediction of laboratory-based CRR. Based on the developed CRR model, new relationships are then presented for the coefficient of effective overburden pressure (K_σ) and magnitude scaling factor (MSF), two important modification factors in the simplified shear stress procedure. These new modification factors are then compared with those recommended by previous researchers. Finally, the possible application of the proposed CRR model in field condition is shown for a specific case. This study provides a preliminary insight into the liquefaction resistance of silty sands prior to the complementary laboratory studies.     

Assessment of Liquefaction Potential of Guwahati City: A Case Study

The liquefaction potential of saturated cohesionless deposits in Guwahati city, Assam, was evaluated. The critical cyclic stress ratio required to cause liquefaction and the cyclic stress ratio induced by an earthquake were obtained using the simplified empirical method developed by Seed and Idriss (J soil Mech Found Eng ASCE 97(SM9):1249–1273, 1971, Ground motions and soil liquefaction during earthquakes. Earthquake Engineering Research Institute, Berkeley, CA, 1982) and Seed et al. (J Geotech Eng ASCE 109(3):458–483, 1983, J Geotech Eng ASCE 111(12):1425–1445, 1985) and the Idriss and Boulanger (2004) method. Critical cyclic stress ratio was based on the empirical relationship between standard penetration resistance and cyclic stress ratio. The liquefaction potential was evaluated by determining factor of safety against liquefaction with depth for areas in the city. A soil database from 200 boreholes covering an area of 262 km² was used for the purpose. A design peak ground acceleration of 0.36 g was used since Guwahati falls in zone V according to the seismic zoning map of India. The results show that 48 sites in Guwahati are vulnerable to liquefaction according to the Seed and Idriss method and 49 sites are vulnerable to liquefaction according to the Idriss and Boulanger method. Results are presented as maps showing zones of levels of risk of liquefaction.     

Unidirectional cyclic resistance of Ticino and Toyoura sands from centrifuge cone penetration tests

The evaluation of the undrained cyclic resistance of sandy deposits is required to forecast the soil behaviour during an earthquake (liquefaction, cyclic mobility); due to the difficulties in obtaining undisturbed samples of most liquefiable soils, it is usually deduced from field test results such as cone penetration tests. This paper proposes a methodology to evaluate the undrained cyclic resistance from normalised cone resistance of two well-studied silica sands (Ticino and Toyoura), with different mineralogy, one mainly composed of feldspar, the other of quartz. The determination of the cyclic resistance of Ticino and Toyoura sands was achieved through undrained cyclic triaxial tests on reconstituted specimens. The tip resistance was deduced from CPTs performed in centrifuge with a miniaturised piezocone on homogeneous reconstituted models. Both the undrained cyclic and tip resistances were correlated with the state parameter ψ. Results of centrifuge and triaxial tests were combined through ψ to deduce the cyclic resistance ratio CRR directly from the normalised cone resistance. The shape of the curve relating CRR to the normalised cone resistance resulted unusual respect to all the recognised curves widespread in the geotechnical literature. The aim of the proposed correlations is to provide a useful instrument to improve the actual knowledge on liquefaction and to give a contribution based on the critical state soil mechanics framework to the development of refined correlations between the cyclic resistance of a sand and the results of cone penetration tests.     

CPT-based probabilistic evaluation of seismic soil liquefaction potential using multi-gene genetic programming

In this paper, liquefaction potential of soil is evaluated within a probabilistic framework based on the post-liquefaction cone penetration test (CPT) data using an evolutionary artificial intelligence technique, multi-gene genetic programming (MGGP). Based on the developed limit state function using MGGP, a relationship is given between probability of liquefaction (P_L) and factor of safety against liquefaction using Bayesian theory. This Bayesian mapping function is further used to develop a P_L-based design chart for evaluation of liquefaction potential of soil. Using an independent database of 200 cases, the efficacy of the present MGGP-based probabilistic method is compared with that of the available probabilistic methods based on artificial neural network (ANN) and statistical methods. The proposed method is found to be more efficient in terms of rate of successful prediction of liquefaction and non-liquefaction cases, in three different ranges of P_L values compared to ANN and statistical methods.     

Simple model for transient soil loading in earthquake analysis. I. Basic model and its application

Several models describing soil response under cyclic loading and the ‘liquefaction’ potential have been introduced in recent years with limited success. Most of these are over-complex for realistic parameter identification and have not been widely adopted for practical use. In this paper we introduce a relatively simple modification of the well-known critical state model which accounts reasonably well for the phenomena observed under cyclic tests and indeed improves the performance of critical state, models in monotonic loading. This model is compared with experimental results and with the ‘densification model’ introduced earlier by the authors and shows good predicitive capacity. The model is of a generalized plasticity-bounding surface type. In its simplest form, suitable for clay-like materials, it requires the identifications of a single parameter additional to those required for a standard, critical state model.     

A Novel Methodology to Classify Soil Liquefaction Using Deep Learning

In this research, deep learning (DL) model is proposed to classify the soil reliability for liquefaction. The applicability of the DL model is tested in comparison with emotional backpropagation neural network (EmBP). The database encompassing cone penetration test of Chi–Chi earthquake. This study uses cone resistance (q_c) and peck ground acceleration as inputs for prediction of liquefaction susceptibility of soil. The performance of developed models has been assessed by using various parameters (receiver operating characteristic, sensitivity, specificity, Phi correlation coefficient, Precision–Recall F measure). The performance of DL is excellent. Consistent results obtained from the proposed deep learning model, compared to the EmBP, indicate the robustness of the methodology used in this study. In addition, both the developed model was also tested on global earthquake data. During validation on global data, both the models shows good results based on fitness parameters. The developed classification models a simple, but also efficient decision-making tool in engineering design to quantitatively assess the liquefaction potential. The finding of this paper can be further used to capture the relationship between soil and earthquake parameters.

     

Simulation of liquefaction of unsaturated soil using critical state soil model

Several researchers have reported that the mean effective stress of unsaturated soils having a relatively high degree of saturation gradually decreases under fully undrained cyclic loading conditions, and such soils can be finally liquefied like saturated soils. This paper describes a series of simulations of fully undrained cyclic loading on unsaturated soils, conducted using an elastoplastic model for unsaturated soils. This model is a critical state soil model formulated using effective stress tensor for unsaturated soils, which incorporates the following concepts: (a) the volumetric movement of the state boundary surface containing the critical state line owing to the variation in the degree of saturation; (b) the soil water characteristic curve considering the effects of specific volume and hydraulic hysteresis; and (c) the subloading surface concept for considering the effect of density. Void air is assumed to be an ideal gas obeying Boyle's law. The proposed model is validated through comparisons with past results. The simulation results show that the proposed model properly describes the fully undrained cyclic behavior of unsaturated soils, such as liquefaction, compression, and an increase in the degree of saturation. Finally, the effects of the degree of saturation, void ratio, and confining pressure on the cyclic strength of unsaturated soils are described by the simulation results. The liquefaction resistance of unsaturated soils increases as the degree of saturation and the void ratio decrease, and as the confining pressure increases. Furthermore, the degree of saturation has a greater effect on the liquefaction resistance than the confining pressure and void ratio. Copyright © 2017 John Wiley & Sons, Ltd.     

Determination of liquefaction susceptibility of soil: a least square support vector machine approach

This article adopts least square support vector machine (LSSVM) for determination of liquefactions susceptibility of soil based on standard penetration test data. Two models (Models I and II) have been developed. For Model I, input variables are cyclic stress ratio and standard penetration test value (N). Model II employs peak ground acceleration and N as input variables. The developed LSSVM models (Models I and II) give equations for determination of liquefaction susceptibility of soil. The performances of Models I and II are the same. The developed LSSVM gives probabilistic output. The results of LSSVM have been compared with the artificial neural network model. This article shows that N and the peak ground acceleration are sufficient input parameters for determination of liquefaction susceptibility of soil. Copyright © 2012 John Wiley & Sons, Ltd.     

Evaluation of liquefaction potential based on CPT results using evolutionary polynomial regression

In this paper a new approach is presented, based on evolutionary polynomial regression (EPR), for determination of liquefaction potential of sands. EPR models are developed and validated using a database of 170 liquefaction and non-liquefaction field case histories for sandy soils based on CPT results. Three models are presented to relate liquefaction potential to soil geometric and geotechnical parameters as well as earthquake characteristics. It is shown that the EPR model is able to learn, with a very high accuracy, the complex relationship between liquefaction and its contributing factors in the form of a function. The attained function can then be used to generalize the learning to predict liquefaction potential for new cases not used in the construction of the model. The results of the developed EPR models are compared with a conventional model as well as a number of neural network-based models. It is shown that the proposed EPR model provides more accurate results than the conventional model and the accuracy of the EPR results is better than or at least comparable to that of the neural network-based models proposed in the literature. The advantages of the proposed EPR model over the conventional and neural network-based models are highlighted.     

以剪切波速与地表峰值加速度为依据的地震液化确定性及概率判别法

剪切波速作为土性的基本参数,为评价土体抵抗地震液化的能力提供了一种方法。回顾了以剪切波速和地表峰值加速度为依据的场地地震液化判别方法的演化历史,依据他人收集的现场液化资料,合计49次地震、618例液化/不液化场地数据,提出了确定液化临界曲线的基本原则,给出了基于修正剪切波速与地表峰值加速度的液化临界曲线,验证了液化临界曲线的位置对细粒含量、有效上覆压力、震级等因素取值变化的合理性,分析了估计土层循环应力比CSR的剪应力折减系数、震级标定系数、有效上覆压力修正系数等因素的不确定性对液化临界曲线的敏感性。结果表明：液化临界曲线对各种影响因素具有很好的适用性。利用Monte Carlo模拟、加权最大似然法和加权经验概率法,给出了建议的液化临界曲线的名义抗液化安全系数与液化概率的经验关系式及概率等值线,并对核电厂Ⅰ类、Ⅱ类和Ⅲ类抗震物项地基,分别建议了相应的液化临界曲线。该方法以丰富的现场液化数据为依据,具有广泛的应用前景。     

Laboratory Investigation into the Effects of Silty Fines on Liquefaction Susceptibility of Chlef (Algeria) Sandy Soils

In a number of recent case studies, the liquefaction of silty sands has been reported. To investigate the undrained shear and deformation behaviour of Chlef sand–silt mixtures, a series of monotonic and stress-controlled cyclic triaxial tests were conducted on sand encountered at the site. The aim of this laboratory investigation is to study the influence of silt contents, expressed by means of the equivalent void ratio on undrained residual shear strength of loose, medium dense and dense sand–silt mixtures under monotonic loading and liquefaction potential under cyclic loading. After an earthquake event, the prediction of the post-liquefaction strength is becoming a challenging task in order to ensure the stability of different types of earth structures. Thus, the choice of the appropriate undrained residual shear strength of silty sandy soils that are prone to liquefaction to be used in engineering practice design should be established. To achieve this, a series of undrained triaxial tests were conducted on reconstituted saturated silty sand samples with different fines contents ranging from 0 to 40 %. In all tests, the confining pressure was held constant at 100 kPa. From the experimental results obtained, it is clear that the global void ratio cannot be used as a state parameter and may not characterize the actual behaviour of the soil as well. The equivalent void ratio expressing the fine particles participation in soil strength is then introduced. A linear relationship between the undrained shear residual shear strength and the equivalent void ratio has been obtained for the studied range of the fines contents. Cyclic test results confirm that the increase in the equivalent void ratio and the fines content accelerates the liquefaction phenomenon for the studied stress ratio and the liquefaction resistance decreases with the increase in either the equivalent void ratio or the loading amplitude level. These cyclic tests results confirm the obtained monotonic tests results.