Liquefaction Potential Of Soil Deposits Research Articles

Liquefaction susceptibility using machine learning based on SPT data

Assessing the potential for liquefaction using traditional experimental or empirical analysis procedures is both time-consuming and arduous. Employing a machine learning model that can accurately predict liquefaction potential for a specific site can reduce the time, effort, and associated costs. This study proposes several empirical machine learning models, including deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM), and bi-directional long short-term memory (BILSTM), to assess the liquefaction potential of soil deposits based on SPT-based post liquefaction datasets. To train the proposed models, a dataset comprising 834 liquefied and non-liquefied cases was collected to perform the liquefaction analysis. A Pearson correlation matrix was also conducted to examine the correlation between soil and seismic parameters and the probability of liquefaction. Furthermore, a sensitivity analysis was adopted to assess the impact of soil and seismic parameters on the probability of liquefaction. The proposed model's prediction capability was assessed using several performance indices, including rank analysis, accuracy matrix, and AIC criteria. The comparative analysis of the proposed models' predictive ability to determine liquefaction probability revealed that the RNN model outperformed the others, displaying the highest accuracy and lowest error index values. Subsequently, the RNN model achieved the first rank with a total score value of 70, followed by the CNN (55), DNN (52), BILSTM (47), and LSTM (16) models. The parametric analysis, rank analysis, accuracy matrix, and AIC criteria collectively demonstrate the proposed models' ability to predict liquefaction probability. Furthermore, the robustness of these models was assessed through external validation and comparative analysis.

Evaluation of liquefaction potential of soil deposits using artificial neural networks

PurposeIn the literature, several empirical methods can be found to predict the occurrence of nonlinear soil liquefaction in soil layers. These methods are limited to the seismic conditions and the parameters used in developing the model. This paper seeks to present General Regression Neural Network (GRNN) model that addresses the collective knowledge built in simplified procedure.Design/methodology/approachThe GRNN model incorporates the soil and seismic parameters of the region. It was developed in four phases; identification, collection, implementation, and verification. The data used consisted of 3,895 case records, mostly from the cone penetration test (CPT) results produced from the two major earthquakes that took place in Turkey and Taiwan in 1999. The case records were divided randomly into training, testing and validation datasets. Soil liquefaction decision in terms of seismic demand and seismic capacity is determined by the stress‐based method and strain‐based method, and further tested with the well‐known Chinese criteria.FindingsThe results produced by the proposed GRNN model explore effectively the complex relationship between the soil and seismic input parameters and further forecast the liquefaction potential with an overall success ratio of 94 percent. Liquefaction decisions were further validated by the SPT, confirming the viability of the SPT‐to‐CPT data conversion, which is the main limitation of most of the simplified methods.Originality/valueThe proposed GRNN model provides a viable tool to geotechnical engineers to predict seismic condition in sites susceptible to liquefaction. The model can be constantly updated when new data are available, which will improve its predictability.

Evaluation of the liquefaction potential of soil deposits based on SPT and CPT test results

In the literature, predictions for the occurrence of nonlinear soil liquefaction in soil deposits have been investigated through numerous empirical methods. These methods which are also known as ‘conventional techniques’ were derived from several in-situ tests, laboratory tests and case records. An alternative general regression neural network (GRNN) model that addresses the collective knowledge built in a simplified procedure is proposed. To meet this objective, a total of 3895 case records including twelve soil and seismic parameters driven mostly from the cone penetration test (CPT) results are introduced into the model. The data includes the results of field tests from the two major earthquakes that took place in Turkey and Taiwan in 1999 and some of the desired input parameters are obtained from correlations existing in the literature. The soil liquefaction decision in terms of seismic demand and capacity is determined by recognized simplified approach, namely a stress-based method and a strain-based method. Furthermore, the liquefaction probability of soils with significant fines is tested with the so-called Chinese Criteria. The proposed GRNN model is developed in four phases, mainly: the identification phase, collection phase, implementation phase, and verification phase. An iterative procedure was followed to maximize the accuracy of the proposed model. The case records were divided randomly into testing, training, and validation datasets. The proposed GRNN model effectively explored the complex relationship between the introduced soil and seismic input parameters and validated the liquefaction decision.

The effective number of cycles of earthquake ground motion

The seismic response of any system that accumulates damage under cyclic loading is dependent not only on the maximum amplitude of the motion but also its duration. This is explicitly recognized in methods for estimating the liquefaction potential of soil deposits. Many researchers have proposed that the effective number of cycles of the ground motion is a more robust indicator of the destructive capacity of the shaking than the duration. However, as is the case with strong-motion duration, there is no universally accepted approach to determining the effective number of cycles of motion, and the different methods that have been proposed can give widely varying results for a particular accelerogram. Definitions of the effective number of cycles of motion are reviewed, classified and compared. Measurements are found to differ particularly for accelerograms with broad-banded frequency content, which contain a significant number of non-zero crossing peaks. The key seismological parameters influencing the number of cycles of motion and associated equations for predicting this quantity for future earthquakes are identified. Correlations between cycle counts and different duration measures are explored and found to be rather poor in the absence of additional parameters. Copyright © 2004 John Wiley & Sons, Ltd.

Assessment of Liquefaction Potential during Earthquakes by Arias Intensity

An Arias intensity approach to assess the liquefaction potential of soil deposits during earthquakes is proposed, using an energy-based measure of the severity of earthquake-shaking recorded on seismograms of the two horizontal components of ground motion. Values representing the severity of strong motion at depth in the soil column are associated with the liquefaction resistance of that layer, as measured by in situ penetration testing (SPT, CPT). This association results in a magnitude-independent boundary that envelopes initial liquefaction of soil in Arias intensity-normalized penetration resistance space. The Arias intensity approach is simple to apply and has proven to be highly reliable in assessing liquefaction potential. The advantages of using Arias intensity as a measure of earthquake-shaking severity in liquefaction assessment are: Arias intensity is derived from integration of the entire seismogram wave form, incorporating both the amplitude and duration elements of ground motion; all frequen...