Compaction characteristics of granular soils in United Arab Emirates

Most of the topsoils encountered in United Arab Emirates and in the Arabian Peninsula are granular soils with small percentages of silt and clay. Determination of the compaction characteristics of such soils is an essential task in preparing for construction work. The accumulating experience over many years of soil testing in our laboratories suggested that there exists an underlying trend that governs the compaction characteristics of such soils. As such, a study was undertaken to assess the compaction characteristics of such soils and to develop the governing predictive equations. For the purposes of this study, 311 soil samples were collected from various locations in the United Arab Emirates, and tested for various including grain-size distribution, liquid limit, plasticity index, specific gravity of soil solids, maximum dry density of compaction, and optimum moisture content following ASTM D 1557-91 standard procedure C. Following the development of the predictive equations, a new set of 43 soil samples were collected and their compaction results were used to test the validity of predictive model. The range of variables for these soils were as follows: percent retained on US sieve #4 (R#4): 0–68; Percent passing US sieve #200 (P#200): 1–26; Liquid limit: 0–56; Plasticity index: 0–28; Specific gravity of soil solids: 2.55–2.8. Based on the compaction tests results, multiple regression analyses were conducted to develop mathematical models and nomographic solutions to predict the compaction properties of soils. The results indicated that the nomographs could predict well the maximum dry density within ±5% confidence interval and the optimum moisture content within ±3%. This revised version was published online in July 2006 with corrections to the Cover Date.     

Estimation of compaction parameters of fine‐grained soils in terms of compaction energy using artificial neural networks

The determination of the compaction parameters such as optimum water content (w_opt) and maximum dry unit weight (γ_dmax) requires great efforts by applying the compaction testing procedure which is also time consuming and needs significant amount of work. Therefore, it seems more reasonable to use the indirect methods for estimating the compaction parameters. In recent years, the artificial neural network (ANN) modelling has gained an increasing interest and is also acquiring more popularity in geotechnical engineering applications. This study deals with the estimation of the compaction parameters for fine‐grained soils based on compaction energy using ANN with the feed‐forward back‐propagation algorithm. In this study, the data including the results of the consistency tests, standard and modified Proctor tests, are collected from the literature and used in the analyses. The optimum structure of a network is determined for each ANN models. The analyses showed that the ANN models give quite reliable estimations in comparison with regression methods, thus they can be used as a reliable tool for the prediction of w_opt and γ_dmax. Copyright © 2010 John Wiley & Sons, Ltd.     

Application of Artificial Intelligence to Maximum Dry Density and Unconfined Compressive Strength of Cement Stabilized Soil

This paper describes two artificial intelligence techniques for prediction of maximum dry density (MDD) and unconfined compressive strength (UCS) of cement stabilized soil. The first technique uses various artificial neural network (ANN) models such as Bayesian regularization method (BRNN), Levenberg- Marquardt algorithm (LMNN) and differential evolution algorithm (DENN). The second technique uses the support vector machine (SVM) that is firmly based on the theory of statistical learning theory, uses regression technique by introducing ε-insensitive loss function has been adopted. The inputs of both models are liquid limit (LL), plasticity index (PI), clay fraction (CF)%, sand (S)%, gravel Gr (%), moisture content (MC) and cement content (Ce). The sensitivity analyses of the input parameters have been also done for both models. Based on different statistical criteria the SVM models are found to be better than ANN models for the prediction of MDD and UCS of cement stabilized soil.     

Models of compacted fine-grained soils used as mineral liner for solid waste

To prevent the leakage of pollutant liquids into groundwater and sublayers, the compacted fine-grained soils are commonly utilized as mineral liners or a sealing system constructed under municipal solid waste and other containment hazardous materials. This study presents the correlation equations of the compaction parameters required for construction of a mineral liner system. The determination of the characteristic compaction parameters, maximum dry unit weight (γ _dmax) and optimum water content (w _opt) requires considerable time and great effort. In this study, empirical models are described and examined to find which of the index properties correlate well with the compaction characteristics for estimating γ _dmax and w _opt of fine-grained soils at the standard compactive effort. The compaction data are correlated with different combinations of gravel content (G), sand content (S), fine-grained content (FC = clay + silt), plasticity index (I _p), liquid limit (w _L) and plastic limit (w _P) by performing multilinear regression (MLR) analyses. The obtained correlations with statistical parameters are presented and compared with the previous studies. It is found that the maximum dry unit weight and optimum water content have a considerably good correlation with plastic limit in comparison with liquid limit and plasticity index.     

Artificial Neural Network Prediction Models for Soil Compaction and Permeability

This paper presents Artificial Neural Network (ANN) prediction models which relate permeability, maximum dry density (MDD) and optimum moisture content with classification properties of the soils. The ANN prediction models were developed from the results of classification, compaction and permeability tests, and statistical analyses. The test soils were prepared from four soil components, namely, bentonite, limestone dust, sand and gravel. These four components were blended in different proportions to form 55 different mixes. The standard Proctor compaction tests were adopted, and both the falling and constant head test methods were used in the permeability tests. The permeability, MDD and optimum moisture content (OMC) data were trained with the soil’s classification properties by using an available ANN software package. Three sets of ANN prediction models are developed, one each for the MDD, OMC and permeability (PMC). A combined ANN model is also developed to predict the values of MDD, OMC, and PMC. A comparison with the test data indicates that predictions within 95% confidence interval can be obtained from the ANN models developed. Practical applications of these prediction models and the necessary precautions for using these models are discussed in detail in this paper.     

Artificial Neural Networks: A Solution to the Ambiguity in Prediction of Engineering Properties of Fine-Grained Soils

Determination of soaked california bearing ratio (CBR) and compaction characteristics of soils in the laboratory require considerable time and effort. To make a preliminary assessment of the suitability of soils required for a project, prediction models for these engineering properties on the basis of laboratory tests—which are quick to perform, less time consuming and cheap—such as the tests for index properties of soils, are preferable. Nevertheless researchers hold divergent views regarding the most influential parameters to be taken into account for prediction of soaked CBR and compaction characteristics of fine-grained soils. This could be due to the complex behaviour of soils—which, by their very nature, exhibit extreme variability. However this disagreement is a matter of concern as it affects the dependability of prediction models. This study therefore analyses the ability of artificial neural networks and multiple regression to handle different influential parameters simultaneously so as to make accurate predictions on soaked CBR and compaction characteristics of fine-grained soils. The results of simple regression analyses included in this study indicate that optimum moisture content (OMC) and maximum dry density (MDD) of fine-grained soils bear better correlation with soaked CBR of fine-grained soils than plastic limit and liquid limit. Simple regression analyses also indicate that plastic limit has stronger correlation with compaction characteristics of fine-grained soils than liquid limit. On the basis of these correlations obtained using simple regression analyses, neural network prediction models and multiple regression prediction models—with varying number of input parameters are developed. The results reveal that neural network models have more ability to utilize relatively less influential parameters than multiple regression models. The study establishes that in the case of neural network models, the relatively less powerful parameters—liquid limit and plastic limit can also be used effectively along with MDD and OMC for better prediction of soaked CBR of fine-grained soils. Also with the inclusion of less significant parameter—liquid limit along with plastic limit the predictions on compaction characteristics of fine-grained soils using neural network analysis improves considerably. Thus in the case of neural network analysis, the use of relatively less influential input parameters along with stronger parameters is definitely beneficial, unlike conventional statistical methods—for which, the consequence of this approach is unpredictable—giving sometimes not so favourable results. Very weak input parameters alone need to be avoided for neural network analysis. Consequently, when there is ambiguity regarding the most influential input parameters, neural network analysis is quite useful as all such influential parameters can be taken to consideration simultaneously, which will only improve the performance of neural network models. As soils by their very nature, exhibit extreme complexity, it is necessary to include maximum number of influential parameters—as can be determined easily using simple laboratory tests—in the prediction models for soil properties, so as to improve the reliability of these models—for which, use of neural networks is more desirable.     

Burden prediction in blasting operation using rock geomechanical properties

Burden prediction is a vital task in the production blasting. Both the excessive and insufficient burden can significantly affect the result of blasting operation. The burden which is determined by empirical models is often inaccurate and needs to be adjusted experimentally. In this paper, an attempt was made to develop an artificial neural network (ANN) in order to predict burden in the blasting operation of the Mouteh gold mine, using considering geomechanical properties of rocks as input parameters. As such here, network inputs consist of blastability index (BI), rock quality designation (RQD), unconfined compressive strength (UCS), density, and cohesive strength. To make a database (including 95 datasets), rock samples are used from Iran’s Mouteh goldmine. Trying various types of the networks, a neural network, with architecture 5-15-10-1, was found to be optimum. Superiority of ANN over regression model is proved by calculating. To compare the performance of the ANN modeling with that of multivariable regression analysis (MVRA), mean absolute error (E _a), mean relative error (E _r), and determination coefficient (R ²) between predicted and real values were calculated for both the models. It was observed that the ANN prediction capability is better than that of MVRA. The absolute and relative errors for the ANN model were calculated 0.05 m and 3.85%, respectively, whereas for the regression analysis, these errors were computed 0.11 m and 5.63%, respectively. Moreover, determination coefficient of the ANN model and MVRA were determined 0.987 and 0.924, respectively. Further, a sensitivity analysis shows that while BI and RQD were recognized as the most sensitive and effective parameters, cohesive strength is considered as the least sensitive input parameters on the ANN model output effective on the proposed (burden).     

Residual and Fully Softened Strength Evaluation of Soils using Artificial Neural Networks

A backpropagation artificial neural network (ANN) model is developed to predict the secant friction angle of residual and fully softened soils, using data reported by Stark et al. (J Geotech Geoenviron Eng ASCE 131:575–588, 2005). In the ANN model, index properties such as liquid limit, plastic limit, activity, clay fraction and effective normal stress are used as input variables while secant residual friction angle is used as output variable. The model is verified using data that were not used for model training and testing. The results also indicate that the secant residual friction angle of cohesive soils can be predicted quite accurately using liquid limit, clay fraction and effective normal stress as input variables with R ² = 0.93. The sensitivity analysis results indicate that plastic limit and activity have no appreciable effect on ANN predicted secant friction angles. The secant friction angle predictions of the ANN model were also compared with those of Stark’s et al. (2005) curves and the empirical formulas suggested for the same data sets by Wright (Evaluation of soil shear strengths for slope and retaining wall stability with emphasis on high plasticity clays, 2005). The comparison shows that the ANN model predictions are very close to those suggested by the Stark et al. (2005) curves but much better than the prediction of Wright’s (2005) empirical equations. The results also show that ANN is an alternative powerful tool to predict the secant friction angle of soils.     

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.     

Prediction of the unconfined compressive strength of compacted granular soils by using inference systems

Adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) models have been extensively used to predict different soil properties in geotechnical applications. In this study, it was aimed to develop ANFIS and ANN models to predict the unconfined compressive strength (UCS) of compacted soils. For this purpose, 84 soil samples with different grain-size distribution compacted at optimum water content were subjected to the unconfined compressive tests to determine their UCS values. Many of the test results (for 64 samples) were used to train the ANFIS and the ANN models, and the rest of the experimental results (for 20 samples) were used to predict the UCS of compacted samples. To train these models, the clay content, fine silt content, coarse silt content, fine sand content, middle sand content, coarse sand content, and gravel content of the total soil mass were used as input data for these models. The UCS values of compacted soils were output data in these models. The ANFIS model results were compared with those of the ANN model and it was seen that the ANFIS model results were very encouraging. Consequently, the results of this study have important findings indicating reliable and simple prediction tools for the UCS of compacted soils.     

Machine learning techniques applied to prediction of residual strength of clay

Stability with first time or reactivated landslides depends upon the residual shear strength of soil. This paper describes prediction of the residual strength of soil based on index properties using two machine learning techniques. Different Artificial Neural Network (ANN) models and Support Vector Machine (SVM) techniques have been used. SVM aims at minimizing a bound on the generalization error of a model rather than at minimizing the error on the training data only. The ANN models along with their generalizations capabilities are presented here for comparisons. This study also highlights the capability of SVM model over ANN models for the prediction of the residual strength of soil. Based on different statistical parameters, the SVM model is found to be better than the developed ANN models. A model equation has been developed for prediction of the residual strength based on the SVM for practicing geotechnical engineers. Sensitivity analyses have been also performed to investigate the effects of different index properties on the residual strength of soil.     

Property Correlations and Statistical Variations in the Geotechnical Properties of (CH) Clay Soils

This study was focused on the correlations between the physical and mechanical properties and geostatistical analysis of the clay of high plasticity (CH) soil based on the experimental data and the data collected from various research studies. Four types of CH soil with liquid limit (LL) of 50, 62, 76 and 88% were collected from the field, tested, compared with the data from literature and qualified using hyperbolic model. X-ray diffraction analyses showed the major constituents of the CH soil with LL of 50% were calcium silicate (Ca₂SiO₄), aluminum silicate (Al₂SiO₅) and quartz (SiO₂) and the major constituents of the CH soil with LL of 88% were montmorillonite (Na, Ca) _0.33(Al, Mg) ₂(Si₄O₁₀) (OH)₂·nH₂O, kaolinite (Al₂Si₂O₅(OH)₄) and quartz (SiO₂). The index properties, compacted properties, free swelling and compressive strength of the CH soils were investigated and quantified with over 1000 data collected from the literature. Using the mean (μ), standard deviation (σ), variation (σ²) and coefficient of variation parameters of CH soils properties such as density (γ), index properties (LL and PL), compaction properties (OMC and γ_dmax), swelling index (FS), initial void ratio (e_o), compression index (Cc) and undrained shear strength (S_u) properties were also studied. Liquid limit of CH soils varied between 50 and 110% and plasticity index varied between 26 and 72%. The wet unit weight (γ_wet) for the CH soils varied from 1.30 to 2.19 g/cm³. Undrained shear strength (S_u) of CH soils were varied from 10 to 184 kPa and quantified very well as a function of liquid limit, plasticity index, moisture content and dry density using the experimental data and data collected from the literature.     

Artificial neural networks and nonlinear regression techniques to assess the influence of slake durability cycles on the prediction of uniaxial compressive strength and modulus of elasticity for carbonate rocks

Understanding rock material characterizations and solving relevant problems are quite difficult tasks because of their complex behavior, which sometimes cannot be identified without intelligent, numerical, and analytical approaches. Because of that, some prediction techniques, like artificial neural networks (ANN) and nonlinear regression techniques, can be utilized to solve those problems. The purpose of this study is to examine the effects of the cycling integer of slake durability index test on intact rock behavior and estimate some rock properties, such as uniaxial compressive strength (UCS) and modulus of elasticity (E) from known rock index parameters using ANN and various regression techniques. Further, new performance index (PI) and degree of consistency (Cd) are introduced to examine the accuracy of generated models. For these purposes, intact rock dataset is established by performing rock tests including uniaxial compressive strength, modulus of elasticity, Schmidt hammer, effective porosity, dry unit weight, p‐wave velocity, and slake durability index tests on selected carbonate rocks. Afterward, the models are developed using ANN and nonlinear regression techniques. The concluding remark given is that four‐cycle slake durability index (I_d4) provides more accurate results to evaluate material characterization of carbonate rocks, and it is one of the reliable input variables to estimate UCS and E of carbonate rocks; introduced performance indices, both PI and Cd, may be accepted as good indicators to assess the accuracy of the complex models, and further, the ANN models have more prediction capability than the regression techniques to estimate relevant rock properties. Copyright © 2011 John Wiley & Sons, Ltd.     

Intelligent modelling of clay compressibility using hybrid meta-heuristic and machine learning algorithms

Compression index Ccis an essential parameter in geotechnical design for which the effectiveness of correlation is still a challenge.This paper suggests a novel modelling approach using machine learning(ML)technique.The performance of five commonly used machine learning(ML)algorithms,i.e.back-propagation neural network(BPNN),extreme learning machine(ELM),support vector machine(SVM),random forest(RF)and evolutionary polynomial regression(EPR)in predicting Cc is comprehensively investigated.A database with a total number of 311 datasets including three input variables,i.e.initial void ratio e0,liquid limit water content wL,plasticity index Ip,and one output variable Cc is first established.Genetic algorithm(GA)is used to optimize the hyper-parameters in five ML algorithms,and the average prediction error for the 10-fold cross-validation(CV)sets is set as thefitness function in the GA for enhancing the robustness of ML models.The results indicate that ML models outperform empirical prediction formulations with lower prediction error.RF yields the lowest error followed by BPNN,ELM,EPR and SVM.If the ranges of input variables in the database are large enough,BPNN and RF models are recommended to predict Cc.Furthermore,if the distribution of input variables is continuous,RF model is the best one.Otherwise,EPR model is recommended if the ranges of input variables are small.The predicted correlations between input and output variables using five ML models show great agreement with the physical explanation.     

Estimation of effective stress parameter of unsaturated soils by using artificial neural networks

Great efforts are required for determination of the effective stress parameter χ, applying the unsaturated testing procedure, since unsaturated soils that have the three‐phase system exhibit complex mechanical behavior. Therefore, it seems more reasonable to use the empirical methods for estimation of χ. The objective of this study is to investigate the practicability of using artificial neural networks (ANNs) to model the complex relationship between basic soil parameters, matric suction and the parameter χ. Five ANN models with different input parameters were developed. Feed‐forward back propagation was applied in the analyses as a learning algorithm. The data collected from the available literature were used for training and testing the ANN models. Furthermore, unsaturated triaxial tests were carried out under drained condition on compacted specimens. ANN models were validated by a part of data sets collected from the literature and data obtained from the current study, which were not included in the training phase. The analyses showed that the results obtained from ANN models are in satisfactory agreement with the experimental results and ANNs can be used as reliable tool for prediction of χ. Copyright © 2007 John Wiley & Sons, Ltd.     

Digital soil mapping in a Himalayan watershed using remote sensing and terrain parameters employing artificial neural network model

Digital soil mapping relies on field observations, laboratory measurements and remote sensing data, integrated with quantitative methods to map spatial patterns of soil properties. The study was undertaken in a hilly watershed in the Indian Himalayan region of Mandi district, Himachal Pradesh for mapping soil nutrients by employing artificial neural network (ANN), a potent data mining technique. Soil samples collected from the surface layer (0–15 cm) of 75 locations in the watershed, through grid sampling approach during the fallow period of November 2015, were preprocessed and analysed for various soil nutrients like soil organic carbon (SOC), nitrogen (N) and phosphorus (P). Spectral indices like Colouration Index, Brightness Index, Hue Index and Redness Index derived from Landsat 8 satellite data and terrain parameters such as Terrain Wetness Index, Stream Power Index and slope using CartoDEM (30 m) were used. Spectral and terrain indices sensitive to different nutrients were identified using correlation analysis and thereafter used for predictive modelling of nutrients using ANN technique by employing feed-forward neural network with backpropagation network architecture and Levenberg–Marquardt training algorithm. The prediction of SOC was obtained with an R² of 0.83 and mean squared error (MSE) of 0.05, whereas for available nitrogen, it was achieved with an R² value of 0.62 and MSE of 0.0006. The prediction accuracy for phosphorus was low, since the phosphorus content in the area was far below the normal P values of typical Indian soils and thus the R² value observed was only 0.511. The attempts to develop prediction models for available potassium (K) and clay (%) failed to give satisfactory results. The developed models were validated using independent data sets and used for mapping the spatial distribution of SOC and N in the watershed.     

Evaluation of the compression index of soils using an artificial neural network

The compression index is a one of the important soil parameters that is essential to geotechnical designs. As the determination of the compression index from consolidation tests is relatively time-consuming, empirical formulas based on soil parameters can be useful. Over the decades, a number of empirical formulas have been proposed to relate the compressibility to other soil parameters, such as the natural water content, liquid limit, plasticity index, specific gravity, and others. Each of the existing empirical formulas yields good results for a particular test set, but cannot accurately or reliably predict the compression index from various test sets. In this study, an alternative approach, an artificial neural network (ANN) model, is proposed to estimate the compression index with numerous consolidation test sets. The compression index was modeled as a function of seven variables including the natural water content, liquid limit, plastic index, specific gravity, and soil types. Nine hundred and forty-seven consolidation tests for soils sampled at 67 construction sites in the Republic of Korea were used for the training and testing of the ANN model. The predicted results showed that the neural network could provide a better performance than the empirical formulas.     

Predicting standard penetration test N-value from cone penetration test data using artificial neural networks

Standard Penetration Test(SPT) and Cone Penetration Test(CPT) are the most frequently used field tests to estimate soil parameters for geotechnical analysis and design.Numerous soil parameters are related to the SPT N-value.In contrast,CPT is becoming more popular for site investigation and geotechnical design.Correlation of CPT data with SPT N-value is very beneficial since most of the field parameters are related to SPT N-values.A back-propagation artificial neural network(ANN) model was developed to predict the N6o-value from CPT data.Data used in this study consisted of 109 CPT-SPT pairs for sand,sandy silt,and silty sand soils.The ANN model input variables are:CPT tip resistance(q_c),effective vertical stress(σ'_v),and CPT sleeve friction(f_s).A different set of SPT-CPT data was used to check the reliability of the developed ANN model.It was shown that ANN model either under-predicted the N_(60)-value by 7-16%or over-predicted it by 7-20%.It is concluded that back-propagation neural networks is a good tool to predict N_(60)-value from CPT data with acceptable accuracy.     

Effects of surfactants and electrolyte solutions on the properties of soil

Biosurfactants are frequently used in petroleum hydrocarbon and dense non-aqueous phase liquids (DNAPLs) remediation. The applicability of biosurfactant use in clayey soils requires an understanding and characterization of their interaction. Comprehensive effects of surfactants and electrolyte solutions on kaolinite clay soil were investigated for index properties, compaction, strength characteristics, hydraulic conductivities, and adsorption characteristics. Sodium dodecyl sulfate (SDS) and NaPO₃ decreased the liquid limit and plasticity index of the test soil. Maximum dry unit weights were increased and optimum moisture contents were decreased as SDS and biosurfactant were added for the compaction tests for mixtures of 30% kaolinite and 70% sand. The addition of non-ionic surfactant, biosurfactant, and CaCl₂ increased the initial elastic modulus and undrained shear strength of the kaolinite–sand mixture soils. Hydraulic conductivities were measured by fixed-wall double-ring permeameters. Results showed that the hydraulic conductivity was not significantly affected, but slightly decreased from 1×10⁻⁷ cm/s (water) to 0.3×10⁻⁷ cm/s for Triton X-100 and SDS. The adsorption characteristics of the chemicals onto kaolinite were also investigated by developing isotherm curves. SDS adsorbed onto soil particles with the strongest bonding strength of the fluids tested. Correlations among parameters were developed for surfactants, electrolyte solutions, and clayey soils.     

Prediction of Drillability of Rocks with Strength Properties Using a Hybrid GA-ANN Technique

The purpose of this paper is to provide a proper, practical and convenient drilling rate index (DRI) prediction model based on rock material properties. In order to obtain this purpose, 47 DRI tests were used. In addition, the relevant strength properties i.e. uniaxial compressive strength and Brazilian tensile strength were also used and selected as input parameters to predict DRI. Examined simple regression analysis showed that the relationships between the DRI and predictors are statistically meaningful but not good enough for DRI estimation in practice. Moreover, multiple regression, artificial neural network (ANN) and hybrid genetic algorithm (GA)-ANN models were constructed to estimate DRI. Several performance indices i.e. coefficient of determination (R²), root mean square error and variance account for were used for evaluation of performance prediction the proposed methods. Based on these results and the use of simple ranking procedure, the best models were chosen. It was found that the hybrid GA-ANN technique can performed better in predicting DRI compared to other developed models. This is because of the fact that the proposed hybrid model can update the biases and weights of the network connection to train by ANN.