Site Characterization Model Using Artificial Neural Network and Kriging
01 Oct 2010-International Journal of Geomechanics (American Society of Civil Engineers)-Vol. 10, Iss: 5, pp 171-180
TL;DR: In this article, the problem of site characterization is treated as a task of function approximation of the large existing data from standard penetration tests (SPTs) in three-dimensional subsurface of Bangalore, India.
Abstract: In this paper, the problem of site characterization is treated as a task of function approximation of the large existing data from standard penetration tests (SPTs) in three-dimensional subsurface of Bangalore, India. More than 2,700 field SPT values (N) has been collected from 766 boreholes spread over an area of 220 -km2 area in Bangalore, India. To get N corrected value ( Nc ) , N values have been corrected for different parameters such as overburden stress, size of borehole, type of sampler, length of connected rod. In three-dimensional analysis, the function Nc = Nc ( X,Y,Z ) , where X , Y , and Z are the coordinates of a point corresponds to Nc value, is to be approximated with which Nc value at any half-space point in Bangalore, India can be determined. An attempt has been made to develop artificial neural network (ANN) model using multilayer perceptrons that are trained with Levenberg-Marquardt back-propagation algorithm. Also, a geostatistical model based on ordinary kriging technique has been ad...
Citations
More filters
TL;DR: The methods discussed here help the geotechnical practitioner to be familiar with the limitations and strengths of ANN compared with alternative conventional mathematical modeling methods.
Abstract: Artificial neural network (ANN) aimed to simulate the behavior of the nervous system as well as the human brain. Neural network models are mathematical computing systems inspired by the biological neural network in which try to constitute animal brains. ANNs recently extended, presented, and applied by many research scholars in the area of geotechnical engineering. After a comprehensive review of the published studies, there is a shortage of classification of study and research regarding systematic literature review about these approaches. A review of the literature reveals that artificial neural networks is well established in modeling retaining walls deflection, excavation, soil behavior, earth retaining structures, site characterization, pile bearing capacity (both skin friction and end-bearing) prediction, settlement of structures, liquefaction assessment, slope stability, landslide susceptibility mapping, and classification of soils. Therefore, the present study aimed to provide a systematic review of methodologies and applications with recent ANN developments in the subject of geotechnical engineering. Regarding this, a major database of the web of science has been selected. Furthermore, meta-analysis and systematic method which called PRISMA has been used. In this regard, the selected papers were classified according to the technique and method used, the year of publication, the authors, journals and conference names, research objectives, results and findings, and lastly solution and modeling. The outcome of the presented review will contribute to the knowledge of civil and/or geotechnical designers/practitioners in managing information in order to solve most types of geotechnical engineering problems. The methods discussed here help the geotechnical practitioner to be familiar with the limitations and strengths of ANN compared with alternative conventional mathematical modeling methods.
97 citations
TL;DR: In this article, a new framework for the probabilistic analysis of tunnel longitudinal performance is presented, where the conditional random field theory is adopted to simulate the spatial variation of soil properties along the tunnel longitudinal direction, in which the soil properties at borehole locations can be explicitly considered.
84 citations
TL;DR: In this article, the results of 90 Unconfined Compressive Strength (UCS) and California Bearing Ratio (CBR) tests on sulfate silty sand stabilized with different lime and microsilica percentages as the two main stabilizers.
62 citations
TL;DR: The main conclusions is that the number of researches in this field increases almost exponentially, the most used (AI) technique is the Artificial Neural Networks and its enhancements where it is presents about half the researches and finally correlating soil and rock properties is the most addressed subject with about 30% of the researched.
Abstract: It was 35 years ago since the first usage of Artificial Intelligence (AI) technique in geotechnical engineering, during those years many (AI) techniques were developed based in mathematical, statistical and logical concepts, but the breakthrough occurs by mimicking the natural searching and optimization algorithms. This huge development in (AI) techniques reflected on the geotechnical engineering problems. In this research, 626 paper and thesis published in the period from 1984 to 2019 concerned in applying (AI) techniques in geotechnical engineering were collected, filtered, arranged and classified with respect to subject, (AI) technique, publisher and publishing date and stored in a database. The extracted information from the database were tabulated, presented graphically and commented. The main conclusions is that the number of researches in this field increases almost exponentially, the most used (AI) technique is the Artificial Neural Networks and its enhancements where it is presents about half the researches and finally correlating soil and rock properties is the most addressed subject with about 30% of the researches.
56 citations
Additional excerpts
...…et al. (1997) 365 Cheng et al. (2014) 405 Ornek (2014) 445 Samui et al. (2009) 326 Kiefa (1998) 366 Miranda et al. (2004) 406 Ornek et al. (2012) 446 Samui and Sitharam (2010) 327 Amini et al. (2005) 367 Shahin (2015a) 407 Zaman et al. (2010) 447 Samui et al. (2015) 328 Prasad and…...
[...]
TL;DR: A new model is derived to predict the peak ground acceleration (PGA) utilizing a hybrid method coupling artificial neural network (ANN) and simulated annealing (SA), called SA-ANN, which is superior to the single ANN and other existing attenuation models.
Abstract: A new model is derived to predict the peak ground acceleration (PGA) utilizing a hybrid method coupling artificial neural network (ANN) and simulated annealing (SA), called SA-ANN. The proposed model relates PGA to earthquake source to site distance, earthquake magnitude, average shear-wave velocity, faulting mechanisms, and focal depth. A database of strong ground-motion recordings of 36 earthquakes, which happened in Iran’s tectonic regions, is used to establish the model. For more validity verification, the SA-ANN model is employed to predict the PGA of a part of the database beyond the training data domain. The proposed SA-ANN model is compared with the simple ANN in addition to 10 well-known models proposed in the literature. The proposed model performance is superior to the single ANN and other existing attenuation models. The SA-ANN model is highly correlated to the actual records (R ¼ 0.835 and r ¼ 0.0908) and it is subsequently converted into a tractable design equation.
41 citations
Cites methods from "Site Characterization Model Using A..."
...…widely utilized for geotechnical engineering modeling in the last two decades (e.g. Goh, 1994; Azmathullah et al., 2005; Das and Basudhar, 2008; Samui and Sitharam, 2010; Gandomi and Alavi, 2011; Guven et al., 2012; Fister et al., 2014) and have recently been used to predict groundmotion…...
[...]
...This soft computing technique, ANN, has been widely utilized for geotechnical engineering modeling in the last two decades (e.g. Goh, 1994; Azmathullah et al., 2005; Das and Basudhar, 2008; Samui and Sitharam, 2010; Gandomi and Alavi, 2011; Guven et al., 2012; Fister et al., 2014) and have recently been used to predict groundmotion characteristics (e....
[...]
References
More filters
TL;DR: In this paper, a simple yet accurate procedure for the description of the spatial variability of the undrained shear strength S u of soft clays is presented. But the results of the applied analysis verify previous findings on the vertical variability of S u and demonstrates the applicability of the present procedure in the commonly encountered situations with limited data.
Abstract: The objective of this study is to provide a simple yet accurate procedure for the description of the spatial variability of the undrained shear strength S u of soft clays. This is achieved on the basis of experimental findings and field observations of the depth-dependent nature of S u . The main features of the method are a linear with depth variation of the mean value and standard deviation of S u and a smooth exponential function that describes the correlation between values received by S u at different vertical locations. The developed procedure is illustrated in a case study involving actual strength data. Two sites are selected from the general area investigated in connection with the West Side Highway in New York City. Each site is characterized by the values of S u obtained along two boreholes using field vane shear tests. The results of the applied analysis verify previous findings on the vertical variability of S u and demonstrates the applicability of the present procedure in the commonly encountered situations with limited data.
83 citations
TL;DR: In this paper, a probabilistic model was proposed to predict the statistics of the penetration resistance and unbalanced moment for a given platform and site condition at any depth of skirt penetration.
Abstract: In the installation of an offshore gravity platform, proper anchoring of a skirt system into the seabed is important. The penetration of the skirt system is generally achieved by built-in ballasting system. Because of (1)inherent spatial randomness in soil resistance; (2)uncertainty in the exact location of the installed platform; (3)insufficient cone penetration test (CPT) values over platform base; and (4)calibration error in predicting skirt penetration resistance from CPT values, the average penetration resistance and the resultant unbalanced moment (in maintaining a horizontal platform position) at each depth of penetration cannot be predicted accurately. A probabilistic model is formulated which will predict the statistics of the penetration resistance and unbalanced moment for a given platform and site condition at any depth of skirt penetration. Such information will help in the design of the capacity of the ballast system. The probabilistic model is also extended to cover the case of sloping seabed.
79 citations
TL;DR: In this article, orthonormal residuals are kriging errors constructed so that, when the correct model is used, they are uncorrelated and have zero mean and unit variance.
Abstract: In linear geostatistics, models for the mean function (drift) and the variogram or generalized covariance function are selected on the basis of the modeler's understanding of the phenomenon studied as well as data One can seldom be assured that the most appropriate model has been selected; however, analysis of residuals is helpful in diagnosing whether some important characteristic of the data has been neglected and, ultimately, in providing a reasonable degree of assurance that the selected model is consistent with the available information The orthonormal residuals presented in this work are kriging errors constructed so that, when the correct model is used, they are uncorrelated and have zero mean and unit variance It is suggested that testing of orthonormal residuals is a practical way for evaluating the agreement of the model with the data and for diagnosing model deficiencies Their advantages over the usually employed standardized residuals are discussed A set of tests are presented Orthonormal residuals can also be useful in the estimation of the covariance (or variogram) parameters for a model that is considered correct
76 citations
TL;DR: The results show that the neural network approach has the potential to be a practical tool for site characterisation, and emphasis is placed on the application of generalised regression neural networks for siteCharacterisation.
Abstract: Site characterisation is an important task in geotechnical engineering practice. The ultimate goal in site characterisation is to be able to estimate in situ soil properties at any half-space point at a site based on limited tests. This estimate may be a point estimate or expressed in terms of some statistical parameters. Geostatistical and random field methods have been applied with limited success. This paper presents a new approach, based on artificial neural networks, for site characterisation. Emphasis is placed on the application of generalised regression neural networks for site characterisation. The results show that the neural network approach has the potential to be a practical tool for site characterisation.
69 citations