Standard Penetration Test Data Research Articles

Combination of Active and Passive Seismic Analyses for Embankment Characterization

Rayleigh wave dispersion is intensively used to determine near surface of shear wave velocity (Vs). The method has been known as non-invasive techniques which is costly effective and efficient to characterize subsurface. Acquisition of the Rayleigh wave can be approached in two ways, i.e. passive and active. Passive seismic is accurate to estimate dispersion curve in low frequency, although it is not accurate for high frequency. While active seismic is vice versa of passive seismic. The high frequency of Rayleigh wave dispersion reflects to near surface and vice versa. Therefore, we used the combination of both passive and active seismic method to overcome the limitations of each method. The Vs which is resulted by inversion of the combining data gives accurate model if compared to log and standard penetration test (N-SPT) data. Further, the approach has been used to characterize LUSI (Lumpur Sidoarjo) embankments. The result shows that embankment material (0-12 m) has higher Vs than that lower embankment material.

Correlations of SPT, CPT and DPL Data for Sandy Soil in Tanzania

In Tanzania, standard penetration test (SPT) is the most commonly used in situ test for foundation design site investigations. In an effort to increase the amount of geotechnical information at low ...

Site response assessment at the city of Al Khobar, eastern Saudi Arabia, from microtremor and borehole data

Al Khobar City is affected by distant earthquakes from the Zagros fold-fault belt, which is part of the subduction zone between the Arabian and Eurasian plates. These earthquakes have generated substantial site effects on the sedimentary layers, which in turn significantly influence earthquake ground motions in the area. Mapping of site response using microtremor measurements compared with geological and borehole data from Al Khobar City is the main objective of this work. The resonance frequency and the corresponding horizontal-to-vertical (H/V) ratio values have been calculated using the Nakamura technique on data from seismograph instruments deployed at 113 sites in Al Khobar City for different time periods. The recording length was about 1 h with a sampling frequency of 100 Hz. Most of the measured sites present three peaks of resonance frequency; the first peak ranges from 0.33 to 1.03 Hz, the second peak ranges from 1.03 to 1.23 Hz, while the third one ranges from 1.23 to 1.73 Hz. Tests have been conducted to ensure that these peaks are of natural origin The northern zones of Al Khobar City have lower resonance frequency values, indicating great sediment thickness. In contrast, the southern parts of the city have higher resonance frequency values, suggesting shallow bedrock depths. Furthermore, 29 geotechnical boreholes have been drilled to different depths in Al Khobar City. Standard penetration test (SPT) data has been corrected and used to calculate the resonance frequency at their locations. The borehole results showed that the resonance frequency values range from 0.27 to 1.95 Hz. These results are well correlated with those from the microtremor measurements. Accordingly, the first peak has been interpreted as being due to the impedance contrast between the limestone bedrock and the overlying sediments, while the third peak originates from a boundary between the uppermost surface layer and the underlying sediments.

Model uncertainty of SPT-based method for evaluation of seismic soil liquefaction potential using multi-gene genetic programming

In this paper, the model uncertainty of the developed standard penetration test (SPT)-based model for evaluation of liquefaction potential of soil is estimated within the framework of the first-order reliability method (FORM). First, an empirical model to determine the cyclic resistance ratio (CRR) of the soil is developed, based on the post-liquefaction SPT data using an evolutionary artificial intelligence technique, multi-gene genetic programming (MGGP). This developed resistance model along with an existing cyclic stress ratio (CSR) model forms a limit state function for reliability-based approach for liquefaction triggering analysis. The uncertainty of the developed limit state model is represented by a lognormal random variable, in terms of its mean and the coefficient of variation, estimated through an extensive reliability analysis following a trial and error approach using Bayesian mapping functions calibrated with a high quality post-liquefaction case history database. A deterministic model with a mapping function relating the probability of liquefaction (PL) and the factor of safety against liquefaction (Fs) is also developed for use in absence of parameter uncertainties. Two examples are presented to compare the present MGGP-based reliability method with the available regression-based reliability method.

Correlation of SPT-CPT Data from the Subsidence Area in Gölcük, Turkey

Previous correlative studies The relationship between SPT N values and cone tip resistance q c , n = (q c /N) was analyzed by many authors. De Alencar Velloso [3] indicated ratios of SPT N values and cone tip resistance for different soil types and introduced 0.35 MPa for clay and silty clay, 0.2 MPa for sandy clay and silty clay, 0.35 MPa for sandy silt, 0.6 MPa for fine grained sand, and 1.0 MPa for sand. Meigh and Nixon [6] indicated that this relation did not consider the effect of grain size and recommended n-values as 0.2 MPa for coarse grained sand and 0.3-0.4 MPa for gravelly sand. Schmertman [9] called attention to the conversion of SPT data to cone penetrometer values if only SPT data are available. He recommended 0.2 MPa for silt, sandy silt, and slightly cohesive silt-sand mixture, 0.3-0.4 MPa for clean, fine to medium sand and slightly silty sand, 0.5-0.6 MPa for sandy gravel and gravel. He also suggested that the correlation of sleeve friction (f s ) with N values is better than that of q c and N value, especially for cohesive A correlation of standard penetration test (SPT) and cone penetration test (CPT) data was carried out by this study. The SPT provides information on the resistance and properties of soils and weathered rocks. In addition to the SPT, the CPT is widely used for site investigation and geotechnical design especially in alluvial areas, based on soil types. In order to determine the CPT values of the investigation areas, where only reliable SPT values are available, the SPT blow counts (N values) can be converted into CPT cone resistances (q c values) by an SPT-CPT correlation. The correlation of SPT-CPT test results from the subsidence area was performed using statistical methods. The soils in this area are recent alluvial deposits, consisting mainly of silty clay, clayey silt, clay and sandy clay. The qc values are not increased when SPT values are increased as it is expected.

A Comparison between Two Field Methods of Evaluation of Liquefaction Potential in the Bandar Abbas City

The geotechnical characteristics of the soil layers are one of the main factors influencing liquefaction potential of the ground. In common usage, liquefaction refers to the loss of strength in saturated, cohesionless soils due to the build-up of pore water pressures during dynamic loading. The following five screening criteria, are recommended for completing a liquefaction evaluation: Geologic age and origin, Fines content and plasticity index, Saturation, Depth below ground surface and Soil penetration resistance. The liquefaction resistance of soils can be evaluated using laboratory tests such as cyclic simple shear, cyclic triaxial, cyclic torsional shear, and field methods such as Standard Penetration Test (SPT), Cone Penetration Test (CPT), and Shear Wave Velocity (Vs). The present study is aimed at comparing the results of two field methods used to evaluate liquefaction resistance of soil, i.e. SPT and CPT. It is concluded that the liquefaction evaluation methods based on the SPT data show more conservative results compared with those based on the CPT data.

Geotechnical characterization and seismic response of shallow geological formations in downtown Lisbon

<p> </p><p>The geological and geotechnical characterization of shallow formations is one of the main steps in performing a microzonation study. This paper presents an example of the usefulness of the information compiled in a geological and geotechnical database for the estimation of the seismic response of the shallower formations of the Lisbon downtown area of Baixa. The geotechnical characterization of this area was performed based on the analysis of Standard Penetration Test (SPT) data compiled in the geological and geotechnical database. This database, connected to a geoscientific information system (CGIS), allows, also, the definition of 2D geological profiles used for estimating the thickness of the shallower layers. The shear-wave velocities (V<span><sub>S </sub></span>) for each layer were estimated from empirical correlations using mean SPT values computed from the statistical evaluation of the compiled data. These V<span><sub>S</sub></span> values were further calibrated with ambient vibration recording analysis. The seismic response of Baixa’s superficial deposits was estimated by applying a 1D equivalent linear method to a set of soil profiles, regularly distributed across the area, and using synthetic accelerograms to simulate input motions associated with probable earthquake occurrences in Lisbon. The results are presented in terms of maps of predominant frequencies, with the corresponding amplification level, as well as spectral amplification factors for 1 Hz and 2.5 Hz. The results show that the fundamental frequency of the Baixa area is between 1.2 Hz and 2 Hz, for the whole central valley, reaching 3 Hz near the edges where anthroprogenic and alluvial deposits have less expression. Amplification factors up to 5 were obtained. These results were achieved regardless of the considered input motion. The similarity of the obtained fundamental frequency with the natural frequency of Baixa’s old building stock increases the probability of resonance effects in future earthquakes.</p><p><span style="font-size: medium;"><br /></span></p>

Evaluation of soil liquefaction potential index based on SPT data in the Erzincan, Eastern Turkey

This study includes determination of liquefaction potential in Erzincan Province. Erzincan Province, the study area, is located in a deep alluvial basin in a mountainous region of eastern Turkey that is a few kilometers from the highly active North Anatolian Fault Zone (NAFZ). North Anatolian Fault Zone is located approximately 7.7 km from Erzincan city center. In a probable earthquake, Erzincan Province is thought to be affected. On 13 March 1992, an earthquake having a surface wave magnitude of 6.8 struck Erzincan, giving rise to peak horizontal accelerations in the center of the city of 0.501g in the east–west direction and 0.398g in the north–south direction. Liquefaction potential for peak horizontal accelerations (0.501g and 0.398g) was determined. Liquefaction potential was investigated using Standard Penetration Test (SPT). Liquefaction potential analyses are determined in two steps: geotechnical investigations and calculations. In the first steps, boreholes were drilled to obtain disturbed and undisturbed soil samples and SPT values were obtained. Laboratory tests were made to identify physical properties of soil samples. In the second step, Liquefaction potential analyses were examined by a Seed and Idriss (1971) method (simplified method) based on Standard Penetration Test (SPT). In order to liquefaction analysis complete within a short time, MATLAB program were prepared. Following the analyses, liquefaction potential is investigated and by Sonmez and Gokceoglu (2005) method. At the final stage of this study, liquefaction potential maps and liquefaction potential index maps were prepared for different earthquake magnitudes and different depths.

Evaluation and use of clustering algorithms for standard penetration test data classification

AbstractThe standard penetration test (SPT) is the most common test conducted in the field, and it is used to determine in situ properties of different soils. Although it is a matter of debate, these tests are also used for the determination of the consistency of fine-grained soils, whereby the test results can also be utilized to establish numerous empirical correlations to predict the strength of soils in the field. In this study, unsupervised clustering algorithms were employed to classify the SPT standard penetration resistance value (SPT-N) in the field. In this scope, shear strength and liquidity index parameters were used to classify the SPT-N values by taking the classification system of Terzaghi and Peck (1967) into consideration. The results showed that the input parameters were successful for classifying the SPT-N value to an acceptable degree of strength attribute. Therefore, in cases where the SPT tests are unreliable or could not be performed, laboratory tests on undisturbed specimens can give valuable information regarding the consistency and SPT-N value of the soil specimen under investigation. Data in this study is based on several tests that were conducted in a region; nevertheless, it is advised that the results of this study should be evaluated using global data.

Assessment of liquefaction potential of Erzincan Province and its vicinity, Turkey

One of the most important causes of damages after the earthquakes is the soil liquefaction. Liquefaction can be defined as temporary loss in strength of saturated sandy and silty deposits under transient and cyclic loadings due to excess pore water pressure. This study includes determination of liquefaction potential in Erzincan city center and its vicinity. Due to the proximity of the North Anatolian Fault Zone, in a probable earthquake, Erzincan Province is thought to be affected. In this context, the earthquake scenarios were produced using the empirical expressions. Liquefaction potential for different earthquake magnitudes was determined. These earthquake magnitudes were selected as 6.0, 6.5, 7.0, 7.5, respectively. Liquefaction potential was investigated using standard penetration test (SPT) data. The first stage of the study, 63 boreholes in different locations was drilled and SPT was performed. Disturbed and undisturbed soil samples were taken from these boreholes. Laboratory testing was performed to determine physical properties of soil samples, and liquefaction potential analyses were examined using three methods, namely Seed and Idriss (J Soil Mech Found Div ASCE 97(9):1249–1273, 1971), Tokimatsu and Yoshimi (Soil Found 23(4):56–74, 1983), Iwasaki et al. (Soil liquefaction potential evaluation with use of the simplified procedure. International Conference on Recent Advances in Geotechnical Earthquake Engineering and Soil Dynamics, St. Louis, pp 209–214, 1981). In order to complete liquefaction analysis within a short time, MATLAB program was prepared. Liquefaction potential analyses were carried out with the MATLAB program. At the final stage of this study, liquefaction potential maps were prepared for different earthquake magnitudes. The expected results will be shared with the local authorities and important engineering remedial measurements will be proposed to prevent further life losses and to mitigate property losses.

Determination of Relationships Between Menard Pressuremeter Test and Standard Penetration Test Data by Using ANN model: a Case Study on the Clayey Soil in Sivas, Turkey

An extensive site characterization study, consisting of 70 Menard pressuremeter tests and 77 standard penetration tests was undertaken on the clayey soil deposit of high plasticity prior to the construction of 4 Eylul Dam’s water treatment plant which provides water supply to Sivas (Turkey). It is aimed to investigate the possible relationships between standard penetration and pressuremeter parameters for the clayey soil in Sivas. To obtain the accurate empirical equations, nonlinear regression analysis between standard penetration blow counts, pressuremeter modulus, and limit pressure were undertaken. An artificial neural network model was developed for accurate estimation of corresponding pressuremeter data based on the measured values. The measured data and calculated performance values were used at the design of Levenberg–Marquardt based multi-layer perceptron artificial neural network model. Calculated values were compared to the predicted values using the statistical error analysis. The relationship between limit pressure and undrained shear strength obtained from the conducted unconfined compression strength tests is also presented. The proposed equations are compared with those obtained from previous studies. The paper concludes that the presented equations based on the nonlinear regression analysis may be valuable for similar soils and beneficial to the practitioners for comparing, evaluating and reciprocal conversion of the parameters obtained from standard penetration and pressuremeter tests.

GIS-based examination of peats and soils in Surfers Paradise, Australia

Abstract The subsoil conditions of Surfers Paradise in Southeast Queensland of Australia have been examined in terms of soil stiffness by using geographic information system (GIS). Peat is a highly organic and compressible material. Surfers Paradise (as a study area) has problematic peat layer due to its high water content, high compressibility, and low shear strength. This layer has various thicknesses at different locations ranging between R.L. . 10 to R.L. -19.6 m. Buildings in Surfers Paradise are using piled foundations to avoid the high compressibility and low shear strength peat layer. Spatial Analyst extension in the GIS ArcMap10 has been utilised to develop zonation maps for different depths in the study area. Each depth has been interpolated as a surface to create Standard Penetration Test SPT-N value GIS-based zonation maps for each depth. In addition, 8 interpolation techniques have been examined to evaluate which technique gives better representation for the Standard Penetration Test (SPT) data. Inverse Distance weighing (IDW) method in Spatial Analyst extension gives better representation for the utilised data with certain parameters. Two different cross sections have been performed in the core of the study area to determine the extent and the depth of the peat layer underneath already erected buildings. Physical and engineering properties of the Surfers Paradise peat have been obtained and showed that this peat falls within the category of tropical peat.

Axial Load Capacity of Cast in Place Piles from SPT and CPTU Data

This paper aims to deal with the assessment of axial load capacity for cast in place pile foundations, which are made by the earth drill method, by using the data taken from Standard Penetration Tests (SPTs) and Piezocone Penetration Tests (CPTUs). These tests were carried out as part of the investigation program for P.N.G. Terminal-Power Plant, near Semani beach, in Hoxhara marsh, in the western part of Albania. The design of axial load capacity of piles is based on empirical formula using SPT and CPTU values. This study presents the results of axial load capacity analysis of cast in place piles by different analytical calculation methods, which are based on in situ tests results, and also referring to the Building Standard Law of Japan. In the end of our work, differences between calculations methods by using different in situ tests results are shown in tables and graphs.

Geostatistical interpolation for modelling SPT data in northern Izmir

In this study, it was aimed to map the corrected Standard Penetration Test (SPT) values in Karşıyaka city center by kriging approach. Six maps were prepared by this geostatistical approach at depths of 3, 6, 9, 13.5, 18 and 25.5 m. Borehole test results obtained from 388 boreholes in central Karşıyaka were used to model the spatial variation of (N1)60cs values in an area of 5.5 km2. Corrections were made for depth, hammer energy, rod length, sampler, borehole diameter and fines content, to the data in hand. At various depths, prepared variograms and the kriging method were used together to model the variation of corrected SPT data in the region, which enabled the estimation of missing data in the region. The results revealed that the estimation ability of the models were acceptable, which were validated by a number of parameters as well as the comparisons of the actual and estimated data. Outcomes of this study can be used in microzonation studies, site response analyses, calculation of bearing capacity of subsoils in the region and producing a number of parameters which are empirically related to corrected SPT number as well.

Seismic microzonation of a nuclear power plant site with detailed geotechnical, geophysical and site effect studies

This paper highlights the seismic microzonation carried out for a nuclear power plant site. Nuclear power plants are considered to be one of the most important and critical structures designed to withstand all natural disasters. Seismic microzonation is a process of demarcating a region into individual areas having different levels of various seismic hazards. This will help in identifying regions having high seismic hazard which is vital for engineering design and land-use planning. The main objective of this paper is to carry out the seismic microzonation of a nuclear power plant site situated in the east coast of South India, based on the spatial distribution of the hazard index value. The hazard index represents the consolidated effect of all major earthquake hazards and hazard influencing parameters. The present work will provide new directions for assessing the seismic hazards of new power plant sites in the country. Major seismic hazards considered for the evaluation of the hazard index are (1) intensity of ground shaking at bedrock, (2) site amplification, (3) liquefaction potential and (4) the predominant frequency of the earthquake motion at the surface. The intensity of ground shaking in terms of peak horizontal acceleration (PHA) was estimated for the study area using both deterministic and probabilistic approaches with logic tree methodology. The site characterization of the study area has been carried out using the multichannel analysis of surface waves test and available borehole data. One-dimensional ground response analysis was carried out at major locations within the study area for evaluating PHA and spectral accelerations at the ground surface. Based on the standard penetration test data, deterministic as well as probabilistic liquefaction hazard analysis has been carried out for the entire study area. Finally, all the major earthquake hazards estimated above, and other significant parameters representing local geology were integrated using the analytic hierarchy process and hazard index map for the study area was prepared. Maps showing the spatial variation of seismic hazards (intensity of ground shaking, liquefaction potential and predominant frequency) and hazard index are presented in this work.

모래지반에서 표준관입시험에 따른 관입거동

본 논문에서는 표준관입시험(SPT) 중에 발생하는 관입거동을 표현하기 위한 이론식을 유도하여 나타내었다. 이를 위하여 에너지보존법칙을 도입하고 SPT 항타거동을 소형강관말뚝이 관입되는 것과 같이 모형화 하였다. 이론식에는 쉽게 결정하기 어려운 쌍곡선 매개변수(m과 <TEX>${\lambda}$</TEX>)를 포함하여 3종류의 입력정수 항으로 구성되어 있다. 최적화된 m과 <TEX>${\lambda}$</TEX>값은 3점에서의 측정값을 사용하여 시행착오법으로 구하였다. 체계적으로 측정된 기존의 자료로부터 얻어진 관입곡선과 예측 관입곡선을 비교한 결과 좋은 일치를 보여 주어서 본 이론식의 적용성이 입증되었다. 본 이론식에 의하면, 주어진 깊이에서 m값이 증가할수록 <TEX>${\lambda}$</TEX>값은 감소하고 관입곡선의 곡률과 N값은 증가하였다. 일반적으로 예측 관입곡선은 예비타 부분을 넘어서면서 거의 직선적으로 변하였으며, 이러한 경향은 모래가 조밀할수록 현저하였다. 그러므로 제안방법은 불충분하게 측정된 관입곡선으로부터 30cm 관입에 해당하는 N값을 외삽법으로 구할 수 있다. 이와 유사한 결과는 역시 간단한 직선식을 이용하여 구할 수 있다. This paper presents an equation to depict the penetration behavior during the standard penetration test (SPT) in sandy deposits. An energy balance approach is considered and the driving mechanism of the SPT sampler is conceptually modeled as that of a miniature open-ended steel pipe pile into sands. The equation consists of three sets of input parameters including hyperbolic parameters (m and <TEX>${\lambda}$</TEX>) which are difficult to determine. An iterative technique is thus applied to determine the optimized values of m and <TEX>${\lambda}$</TEX> using three measured values from a routine SPT data. It is verified from a well-documented record that the simulated penetration curves are in good agreement with the measured ones. At a given depth, the increase in m results in the decrease in <TEX>${\lambda}$</TEX> and the increase in the curvature of the penetration curve as well as the simulated N-value. Generally, the predicted penetration curve becomes nearly straight for the portion of exceeding the seating drive zone, which is more pronounced as soil density increases. Thus, the simulation method can be applied to extrapolating a prematurely completed test data, i.e., to determining the N value equivalent to a 30 cm penetration. A simple linear equation is considered for obtaining similar results.

Influence of Assumed Groundwater Depth on Mapping Liquefaction Potential

Groundwater depth is a critical parameter in assessing regional liquefaction potential. Uncertainties associated with groundwater depth are usually pervasive because of natural variability and spatial separation between data points. These uncertainties often lead to erroneous or doubtful assessments of liquefaction potential. In an attempt to provide more credible estimates of liquefaction potential across a sizable urban area, this study sought to estimate the threshold groundwater depths that could be expected to trigger liquefaction in the St. Louis, MO, metro area, which was damaged by the 1811–1812 New Madrid earthquakes. We used liquefaction potential indexes (LPIs) > 5 and > 15 as the thresholds for moderate and severe liquefaction risks, respectively. The threshold groundwater depth for triggering liquefaction was evaluated using standard penetration test data and a scenario involving an M7.5 earthquake with a peak ground acceleration of 0.20 g. The threshold groundwater depths then were geostatistically contoured and compared with accepted groundwater level scenarios to map the corresponding liquefaction risk. This study revealed that Holocene alluvium in East St. Louis generally exhibits deeper threshold groundwater depths than do the mean groundwater levels and appears to be more prone to liquefaction.

Use of surface waves for geotechnical engineering applications in Western Sydney

Abstract. Current in situ methods used to geotechnically characterize the ground are predominantly based on invasive mechanical techniques (e.g. CPT, SPT, DMT). These techniques are localized to the tested area thus making it quite time consuming and costly to extensively cover large areas. Hence, a study has been initiated to investigate the use of the non-invasive Multichannel Analysis of Surface Waves (MASW) and Multichannel Simulation with One Receiver (MSOR) techniques to provide both an evaluation of compacted ground and a general geotechnical site characterization. The MASW technique relies on the measurement of active ambient vibrations generated by sledgehammer hits to the ground. Generated vibrations are gathered by interconnected electromagnetic geophones set up in the vertical direction and in a linear array at the ground surface with a constant spacing. The MSOR technique relies on one sensor, one single geophone used as the trigger, and multiple impacts are delivered on a steel plate at several distances in a linear array. The main attributes of these non-invasive techniques are the cost effectiveness and time efficiency when compared to current in situ mechanical invasive methods. They were applied to infer the stiffness of the ground layers by inversion of the phase velocity dispersion curves to derive the shear wave velocity (Vs) profile. The results produced by the MASW and the MSOR techniques were verified against independent mechanical Cone Penetration Test (CPT) and Standard Penetration Test (SPT) data. This paper identifies that the MASW and the MSOR techniques could be potentially useful and powerful tools in the evaluation of the ground compaction and general geotechnical site characterization.

Probabilistic characterization of Young's modulus of soil using equivalent samples

Several probability-based design codes (e.g., load and resistance factor design (LRFD) codes and Eurocode 7) have been developed and implemented around the world recently. A characteristic (or nominal) value of soil/rock properties is used in these design codes, and it is typically defined as a pre-specified quantile (e.g., mean or lower 5% quantile) of the statistical distribution of the soil properties. This poses a challenge in the implementation of the design codes, because the number of soil/rock property data obtained during site investigation is generally too sparse to generate meaningful statistics, rendering proper selection of the characteristic value a very difficult task. This paper aims to address this challenge by developing a Markov Chain Monte Carlo Simulation (MCMCS)-based approach for probabilistic characterization of undrained Young's modulus, Eu, of clay using standard penetration tests (SPT). Prior knowledge (e.g., previous engineering experience) and project-specific test data (e.g., SPT test data) are integrated probabilistically under a Bayesian framework and transformed into a large number, as many as needed, of equivalent samples of Eu. Subsequently, conventional statistical analysis is carried out to estimate statistics of Eu, and the characteristic value of the soil property is selected accordingly. Equations are derived for the proposed approach, and it is illustrated and validated using real SPT and pressuremeter test data at the clay site of the US National Geotechnical Experimentation Sites (NGES) at Texas A&M University.

SPT-based liquefaction potential assessment by relevance vector machine approach

This article adopts Relevance Vector Machine (RVM) for the determination of the liquefaction potential of soil based on Standard Penetration Test (SPT) data from Chi-Chi earthquake. RVM is a probabilistic sparse kernel model. This study uses RVM for solving binary classification problem. Two models (MODEL I and MODEL II) have been developed. Cyclic Stress Ratio and SPT blow count (N) have been used as input variables for MODEL I. MODEL II uses Peak Ground Acceleration (PGA) and N as input variables. The developed RVM model gives equations for the prediction of the liquefaction potential of soil. A comparative study has been presented between the developed RVM and the Artificial Neural Network (ANN). The results confirm that the developed RVM is a robust model for the prediction of the liquefaction potential of soil.