Discriminant Model for Evaluating Soil Liquefaction Potential Using Cone Penetration Test Data

Lai, Sheng-Yao; Hsu, Sung‐Chi; Hsieh, Ming-Jyh

doi:10.1061/(asce)1090-0241(2004)130:12(1271)

Cited by 19 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of these simplified charts or equations rely on the analysis of liquefaction case histories. Statistical methods were commonly adopted to assign probabilities of liquefaction through various statistical classification and regression analyses [23][24][25][26].…”

Section: Evaluating Seismic Liquefaction Potentialmentioning

confidence: 99%

Multivariate adaptive regression splines for analysis of geotechnical engineering systems

Zhang

Goh

2013

Computers and Geotechnics

302

View full text Add to dashboard Cite

Section: Evaluating Seismic Liquefaction Potentialmentioning

confidence: 99%

Multivariate adaptive regression splines for analysis of geotechnical engineering systems

Zhang

Goh

2013

Computers and Geotechnics

302

View full text Add to dashboard Cite

“…Other in-situ test methods to evaluate liquefaction potential include the use of the dilatometer (Marchetti 1982) and the shear wave velocity test (Andrus and Stokoe 2000). Statistical methods were commonly adopted to assign probabilities of liquefaction through various statistical classification and regression analyses (Liao et al 1988, Juang et al 1999, Lai et al 2004, Tosun et al 2011.…”

Section: Introductionmentioning

confidence: 99%

Evaluating seismic liquefaction potential using multivariate adaptive regression splines and logistic regression

Zhang¹,

Goh²

2016

Geomech. Eng.

View full text Add to dashboard Cite

Simplified techniques based on in situ testing methods are commonly used to assess seismic liquefaction potential. Many of these simplified methods were developed by analyzing liquefaction case histories from which the liquefaction boundary (limit state) separating two categories (the occurrence or non-occurrence of liquefaction) is determined. As the liquefaction classification problem is highly nonlinear in nature, it is difficult to develop a comprehensive model using conventional modeling techniques that take into consideration all the independent variables, such as the seismic and soil properties. In this study, a modification of the Multivariate Adaptive Regression Splines (MARS) approach based on Logistic Regression (LR) LR_MARS is used to evaluate seismic liquefaction potential based on actual field records. Three different LR_MARS models were used to analyze three different field liquefaction databases and the results are compared with the neural network approaches. The developed spline functions and the limit state functions obtained reveal that the LR_MARS models can capture and describe the intrinsic, complex relationship between seismic parameters, soil parameters, and the liquefaction potential without having to make any assumptions about the underlying relationship between the various variables. Considering its computational efficiency, simplicity of interpretation, predictive accuracy, its data-driven and adaptive nature and its ability to map the interaction between variables, the use of LR_MARS model in assessing seismic liquefaction potential is promising.

show abstract

“…These in situ data are used to estimate the potential for "triggering" or initiation of seismically induced liquefaction. In the context of the analyses of in situ data, the estimate of liquefaction potential derived from ELMs can be broadly classified as ͑1͒ deterministic ͑Seed and Idriss 1971;Iwasaki et al 1978;Seed et al 1983;Robertson and Campanella 1985;Seed and De Alba 1986;Shibata and Teparaksa 1988;Goh 1994;Stark and Olson 1995;Robertson and Wride 1998;Juang et al 2000Juang et al , 2003Idriss and Boulanger 2006;Pal 2006;Hanna et al 2007;Goh 2007͒ and͑2͒ probabilistic ͑Liao et al 1988;Toprak et al 1999;Juang et al 2002;Goh 2002;Cetin et al 2002Cetin et al , 2004Lee et al 2003;Sonmez 2003;Lai et al 2004;Sonmez and Gokceoglu 2005;Papathanassiou et al 2005;Holzer et al 2006;Moss et al 2006;Juang and Li 2007͒. This paper attempts to improve liquefaction models by ͑1͒ quantitatively comparing the predictive performance of several ELMs; ͑2͒ identifying the threshold needed to apply the probabilistic ELMs; and ͑3͒ developing an alternative deterministic and probabilistic ELM based on the machine learning algorithm, known as support vector machine ͑SVM͒.…”

Section: Introductionmentioning

confidence: 99%

Validation and Application of Empirical Liquefaction Models

Oommen

Baise

Vogel

2010

J. Geotech. Geoenviron. Eng.

View full text Add to dashboard Cite

Empirical liquefaction models ͑ELMs͒ are the standard approach for predicting the occurrence of soil liquefaction. These models are typically based on in situ index tests, such as the standard penetration test ͑SPT͒ and cone penetration test ͑CPT͒, and are broadly classified as deterministic and probabilistic models. No objective and quantitative comparison of these models have been published. Similarly, no rigorous procedure has been published for choosing the threshold required for probabilistic models. This paper provides ͑1͒ a quantitative comparison of the predictive performance of ELMs; ͑2͒ a reproducible method for choosing the threshold that is needed to apply the probabilistic ELMs; and ͑3͒ an alternative deterministic and probabilistic ELM based on the machine learning algorithm, known as support vector machine ͑SVM͒. Deterministic and probabilistic ELMs have been developed for SPT and CPT data. For deterministic ELMs, we compare the "simplified procedure," the Bayesian updating method, and the SVM models for both SPT and CPT data. For probabilistic ELMs, we compare the Bayesian updating method with the SVM models. We compare these different approaches within a quantitative validation framework. This framework includes validation metrics developed within the statistics and artificial intelligence fields that are not common in the geotechnical literature. We incorporate estimated costs associated with risk as well as with risk mitigation. We conclude that ͑1͒ the best performing ELM depends on the associated costs; ͑2͒ the unique costs associated with an individual project directly determine the optimal threshold for the probabilistic ELMs; and ͑3͒ the more recent ELMs only marginally improve prediction accuracy; thus, efforts should focus on improving data collection.

show abstract

Discriminant Model for Evaluating Soil Liquefaction Potential Using Cone Penetration Test Data

Cited by 19 publications

References 10 publications

Multivariate adaptive regression splines for analysis of geotechnical engineering systems

Multivariate adaptive regression splines for analysis of geotechnical engineering systems

Evaluating seismic liquefaction potential using multivariate adaptive regression splines and logistic regression

Validation and Application of Empirical Liquefaction Models

Contact Info

Product

Resources

About