Sustainable Stabilization of Puducherry Inland Clay using Lime and Quarry Dust: Geotechnical Properties and ANN-Based Predictive Modeling

Background/Objectives: The expansive clay soils of the Puducherry inland region exhibit high plasticity, excessive swelling, and low shear strength, making them unsuitable for direct use in construction without stabilization. Despite the proven effectiveness of lime and quarry dust as soil stabilizers, limited research exists on Puducherry inland clay, especially regarding long-term curing, durability, and the mechanistic interactions between these stabilizers and the clay. This study investigates the effect of lime and quarry dust as stabilizing agents on the geotechnical characteristics of Puducherry inland clay. Methods: Soil samples were treated separately with varying proportions of lime and quarry dust (7%, 14%, 21%, and 28% by dry weight) to assess improvements in geotechnical behaviour. Laboratory tests, including Atterberg limits, Free Swell Index (FSI), compaction characteristics, direct shear test, and Unconfined Compressive Strength (UCS) were conducted to evaluate changes in soil properties. Findings: The plasticity index of lime-stabilized clay decreased by approximately 25%, while quarry dust-stabilized clay showed a decrease of approximately 37%. The optimum moisture content of lime-stabilized clay and quarry dust-stabilized clay decreased by about 20% and 35%, respectively. The maximum dry density of lime- and quarry dust-stabilized clay increased by about 10% and 35%, respectively. Cohesion values for both lime- and quarry dust-stabilized clay were reduced by about 28%. The UCS of lime-stabilized clay showed a significant increase up to 21% additive content, beyond which the strength dropped drastically, whereas quarry dust-stabilized clay exhibited a continuous strength increase even beyond 21% addition. The FSI of lime- and quarry dust-stabilized clay decreased by about 35% and 28%, respectively. Novelty: Utilizing quarry dust for the stabilization of clay improves soil properties, making it suitable for construction. Compared to lime, quarry dust is abundantly available and is usually disposed of in landfills, contributing to environmental pollution. Stabilizing clay with quarry dust offers two key advantages: it enhances the engineering properties of clay and helps mitigate pollution by effectively utilizing a waste material. Keywords: Clay, Soil Stabilization, Cohesion, Lime, Quarry Dust, Geotechnical Properties

Prediction of the free swell index of the expansive soil using artificial neural network has been presented in this paper. Input parameters for the artificial neural network model were plasticity index and shrinkage index, while the output was the free swell index. Artificial neural network algorithm used a back propagation model. Training of the artificial neural network model was conducted on the data collected from literature, and the weights and biases were obtained which described the relation among the input variables and the output free swell index. Further, the sensitivity analysis was performed, and the parameters affecting the free swell index of the expansive soil were identified. The sensitivity analysis results indicated that the plasticity index (63.97 %) followed by shrinkage index (36.03 %) was affecting the free swell index in this order. The study shows that the prediction accuracy of the free swell index of the expansive soil using artificial neural network model was quite good.

The present investigation introduces a robust soft computing model by comparing twelve least square support vector machine (LSSVM), six long short-term memory (LSTM), and thirty-six artificial neural network (ANN) models to predict the unconfined compressive strength (UCS) of fine-grained soil. For that purpose, a database of fine content, dry unit weight, porosity, void ratio, degree of saturation, and specific gravity results of 85 soil specimens has been compiled from the literature. 75 and 10 soil specimens were trained and tested for each model. Six training databases have been prepared to analyze the effect of quality and quantity of training database by selecting 50%, 60%, 70%, 80%, 90%, and 100% of 75 soil specimens. The performance comparison demonstrated that the LSTM model (MD 113) requires fewer training datasets (50% of 75) than the LSSVM (MD 102 and MD 108) and ANN (MD 120, MD 127, MD 136, MD139, MD 148, and MD 150) models. Also, it was observed that the nonlinear LSSVM model (MD 108) is unaffected by multicollinearity in training datasets and predicted UCS better than the linear LSSVM model (MD 102). Furthermore, the Levenberg-Marquardt neural network model (MD 120) has outperformed the other ANN models with the root mean square error (RMSE) of 5.1214 N/cm2, the mean absolute error (MAE) of 4.1379 N/cm2, and correlation (R) of 0.9836. The overall performance comparison revealed that the LSTM model is more potent than the LSSVM and ANN models. The LSTM model predicted the UCS of fine-grained soil with the RMSE of 4.7539 N/cm2, the MAE of 4.2461 N/cm2, and R of 0.9880. Conversely, cosine amplitude sensitivity analysis demonstrated that the fine content and dry unit weight influence the prediction of virgin UCS of fine-grained soils.

The effect of Pond Ash (PA) activated with sodium chloride (NaCl) solution and reinforced with glass powder on the mechanical properties of soft clay soil, which comprise of the California bearing ratio (CBR) and the unconfined compressive strength (UCS) has been studied in this research work. The PA requires pozzolanic improvements to meet the ASTM C618 requirements for pozzolanas. In the present research paper, further emphasis has been on the machine learning prediction of CBR and UCS of the soft clay soil stabilized with a composite of PA. Generally, the studied soft clay soil properties, which were the microstructure, microspecter/micrograph, oxide composition, Atterberg limits, compaction behavior, free swell index (FSI), CBR and UCS significantly improved due to the enhanced cementitious ability of the activated and reinforced PA. The multiple data collected from this general stabilization result were used to predict the soil’s CBR and UCS by the artificial neural network (ANN) technique. The results showed high performance of the model in terms of the sum of squares error (SSE) of 1.5% and 2.0% and the coefficient of determination (R2) of 0.9979 and 0.9973 for the CBR and UCS models, respectively. The models also outclassed the performances of other models from the literature.

Stabilizing effect of combined woodash and lime on expansive soil from south-eastern Nigeria has been evaluated. The evaluation followed subjecting industrial woodash to X-ray fluorescence (XRF) to determine its chemical composition while an expansive soil underlain by the Coniacian Awgu Group was subjected to X-ray diffraction (XRD) to determine the mineralogy of the soil. The plasticity index (PI), linear shrinkage (LS), free swell index (FSI) and unconfined compressive strength (UCS) of the soil was determined to ascertain the geotechnical properties of the natural soil. The soil was then mixed with woodash in varying proportions viz: 0% woodash and 100% soil; 6% woodash and 94% soil; 12% woodash and 88% soil; 18% woodash and 82% soil; 24% woodash and 76% soil. The PI, LS, FSI and UCS of each woodash-soil admixture was determined to ascertain how these geotechnical properties varies amongst the admixtures and thus the soil improvement of the various woodash proportions. The woodash-soil admixture that gave the best improvement quality was further mixed with 2%, 4%, 6% and 8% lime and PI, LS, FSI and UCS of each woodash-soil-lime admixture also determined to ascertain the amount of lime that gives the best improvement to the woodash-soil admixture. The XRF result revealed that the woodash was dominated with CaO and some other oxides in minor quantities. The XRD result revealed that the soil contains clay minerals. The geotechnical properties of the woodash-soil admixtures indicate that 18% woodash and 82% soil showed the best improvement in PI, SL, FSI and UCS of the soil while the addition of 4% lime to this best improved woodash-soil admixture further improved only the FSI and UCS. Results show that the stabilizing effect of both the woodash and combined woodash and lime is controlled by the chemical composition of the woodash.

The volumetric change of expansive soil is considered as a challenge for civil engineers and many methods were produced in order to stabilize such soils. In this study the enhancement of 10, 20, and 30% of Quarry Dust (QD) as stabilization material for four types of silt and clays characterized as expansive soils was explored. The soil samples were collected from different locations in Northern Cyprus with swell percentages ranging from 4 to 20%. The properties of the collected samples were examined in a laboratory and the effect of quarry dust on physical properties, compaction characteristics, one dimensional swell and unconfined compressive strength were measured. Findings displayed that the addition of 10, 20, and 30% QD results in an overall decrease in the Atterberg limits. Addition of quarry dust improved the compaction properties of the obtained soil at all proportions, with the result showing a decrease in the optimum water content and a gradual increase in the maximum dry density. Also, the swell percentages decreased with the increases of the QD while the compressive strength improved. Moreover, the water absorption during the swell decreased with the increase of QD proportion. The results were then compared by multi-criteria decision analysis (MCDA) based on liquid limit, plasticity index, specific gravity, maximum dry density, optimum water content, clay type, unconfined compressive strength, the sample being naturally occurring and being environmentally friendly by using QD, a waste by-product. The best results were found in the highly plastic silt sample with no enhancement and originally having a low swell potential, followed by the same silt sample with 30% quarry dust enhancement. Among the clay samples the most desired swelling and mechanical behavior was observed in a highly plastic clay soil with original swell percentage of 13.5% in which with 30% QD enhancement it got reduced to 4.4%.KeywordsQuarry dustSoil stabilizationExpansive claysMCDACompressive strength

This research explores the use of Artificial Neural Network (ANN) modeling to predict the Unconfined Compression Strength (UCS) of stabilized medium expansive soil, aiming to optimize the parameters influencing soil stabilization. A database comprising 240 data points was compiled from laboratory tests involving seven input parameters: Stabilizers content (SCBA & WMD), Curing Period (CP), Liquid Limit (L.L), Plasticity Index (PI), Specific Gravity (Gs), and Free Swell (FS). ANN modeling, employing Levenberg-Marquardt algorithms, demonstrated successful UCS prediction. Increasing the number of neurons improved model accuracy, with optimum results achieved with 14 neurons. With 14 neurons for LMA, the R and R² value reaches 0.99, 0.98 Moreover, plots between experimental and predicted values shows strong correlation as majority of predicted UCS is closed to line of fit. Also error shows large count of data points closed to line of zero error. Sensitivity analysis highlighted SCBA, WMD, CP, L.L, and P.I as significant contributors to UCS prediction, emphasizing their importance in soil stabilization. The study underscores the effectiveness of ANN modeling in predicting soil strength and recommends 4% SCBA and 20% WMD for optimal stabilization. Overall, this research presents a comprehensive approach to predicting UCS in stabilized expansive soil, offering insights into parameter optimization and model enhancement for future geotechnical applications.

This article compares two modeling approaches for optimal operation of a turbo chiller installed in an office building: (1) a machine learning model developed with artificial neural network (ANN) and (2) a hybrid machine learning model developed with the ANN model and available physical knowledge of the chiller. Before developing the ANN model of the chiller, the authors used Gaussian mixture model in order to check the validity of measured data. Then, the hybrid model was developed by combining the ANN model and physics-based regression equations from the EnergyPlus engineering reference. It was found that both the ANN and hybrid ANN model are satisfactory to predict the chiller’s power consumption: mean bias error (MBE) = −2.63%, coefficient of variation of the root mean square error (CVRMSE) = 8.05% by the ANN model; MBE = −3.99%, CVRMSE = 11.98% by the hybrid ANN model. However, the hybrid model requires fewer inputs (four inputs) than the ANN model (eight inputs). The energy savings of both models are similar coefficient of performance (COP) = 4.32 by the optimal operation of the ANN model; COP = 4.44 by the optimal operation of the hybrid ANN model. In addition, the hybrid ANN model can be applied where the ANN model is unable to provide accurate predictions.

The resilient modulus (MR) is a crucial parameter, reflecting the dynamic stiffness and structural response of subgrade pavement materials. However, the repeated load triaxial tests to directly measure the MR are complicated, time-consuming, and expensive. Thus, an alternative manner of calculating such values needs to be constructed. In this paper, the backpropagation algorithm is used to construct an artificial neural network (ANN) model to predict the MR of unbound materials. The database used in the development phase of ANN consists of 9 input parameters, such as the percentage of particles passing through a 200 sieve, plasticity index, liquid limit, percentage of optimum moisture content, percent of moisture content, soil saturation degree, confining stress, deviator stress, and the unconfined compressive strength. The target of the proposed ANN model is MR values. The dataset is split into two subsets, namely the training dataset, which accounts for 70% of the total data, and the testing dataset, containing the remaining 30% of data. The results show that the proposed ANN algorithm could successfully predict the values of MR, based on several performance criteria such as the coefficient of determination (R2), root mean square error (RMSE). It could thus be concluded that the ANN model is a highly efficient alternative manner for quick estimation of MR and can be used as an advisory tool for engineers.

Stabilized aggregate bases are vital for the long-term service life of pavements. Their stiffness is comparatively higher; therefore, the inclusion of stabilized materials in the construction of bases prevents the cracking of the asphalt layer. The effect of wet–dry cycles (WDCs) on the resilient modulus (Mr) of subgrade materials stabilized with CaO and cementitious materials, modelled using artificial neural network (ANN) and gene expression programming (GEP) has been studied here. For this purpose, a number of wet–dry cycles (WDC), calcium oxide to SAF (silica, alumina, and ferric oxide compounds in the cementitious materials) ratio (CSAFRs), ratio of maximum dry density to the optimum moisture content (DMR), confining pressure (σ3), and deviator stress (σ4) were considered input variables, and Mr was treated as the target variable. Different ANN and GEP prediction models were developed, validated, and tested using 30% of the experimental data. Additionally, they were evaluated using statistical indices, such as the slope of the regression line between experimental and predicted results and the relative error analysis. The slope of the regression line for the ANN and GEP models was observed as (0.96, 0.99, and 0.94) and (0.72, 0.72, and 0.76) for the training, validation, and test data, respectively. The parametric analysis of the ANN and GEP models showed that Mr increased with the DMR, σ3, and σ4. An increase in the number of WDCs reduced the Mr value. The sensitivity analysis showed the sequences of importance as: DMR > CSAFR > WDC > σ4 > σ3, (ANN model) and DMR > WDC > CSAFR > σ4 > σ3 (GEP model). Both the ANN and GEP models reflected close agreement between experimental and predicted results; however, the ANN model depicted superior accuracy in predicting the Mr value.

Chapter 4 - Concepts, procedures, and applications of artificial neural network models in streamflow forecasting

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.

The present study was carried out using artificial neural network (ANN) model for predicting the sodium hazardness, i.e., sodium adsorption ratio (SAR), percent sodium (%Na) residual, Kelly’s ratio (KR), and residual sodium carbonate (RSC) in the groundwater of the Pratapgarh district of Southern Rajasthan, India. This study focuses on verifying the suitability of water for irrigational purpose, wherein more groundwater decline coupled with water quality problems compared to the other areas are observed. The southern part of the Rajasthan State is more populated as compared to the rest of the parts. The southern part of the Rajasthan is more populated as compared to the rest of the Rajasthan, which leads to the industrialization, urbanization, and evolutionary changes in the agricultural production in the southern region. Therefore, it is necessary to propose innovative methods for analyzing and predicting the water quality (WQ) for agricultural use. The study aims to develop an optimized artificial neural network (ANN) model to predict the sodium hazardness of groundwater for irrigation purposes. The ANN model was developed using ‘nntool’ in MATLAB software. The ANN model was trained and validated for ten years (2010–2020) of water quality data. An L-M 3-layer back propagation technique was adopted in ANN architecture to develop a reliable and accurate model for predicting the suitability of groundwater for irrigation. Furthermore, statistical performance indicators, such as RMSE, IA, R, and MBE, were used to check the consistency of ANN prediction results. The developed ANN model, i.e., ANN4 (3-12-1), ANN4 (4-15-1), ANN1 (4-5-1), and ANN4 (3-12-1), were found best suited for SAR, %Na, RSC, and KR water quality indicators for the Pratapgarh district. The performance analysis of the developed model (3-12-1) led to a correlation coefficient = 1, IA = 1, RMS = 0.14, and MBE = 0.0050. Hence, the proposed model provides a satisfactory match to the empirically generated datasets in the observed wells. This development of water quality modeling using an ANN model may help to useful for the planning of sustainable management and groundwater resources with crop suitability plans as per water quality.

A detailed understanding of rock geo-mechanical characteristics is necessary for enhancing well productivity, optimizing hydraulic fracturing, and maintaining wellbore stability. The expensive cost of measurements of these characteristics makes the log-based estimation a possible alternative. These days, in-situ rock characteristics are estimated utilizing wireline log data and machine learning algorithms. Even though there are many correlations had been proposed to estimate the Uniaxial (Unconfined) Compressive Strength (UCS), the majority of these correlations are built for specific rock types. UCS is affected by various rock properties such as porosity, texture, fluid content and grain size. In this study, an artificial neural network (ANN) model is proposed to estimate the UCS of sandstone formations from well log data (i.e., neutron porosity, bulk density, formation resistivity, and gamma ray) and the corresponding static Young's modulus and shale volume. The performance of the rock strength model is evaluated using statistical techniques to guarantee model dependability and accuracy. The findings demonstrate that the created ANN model is capable of predicting rock strength, which is supported by the excellent agreement between model predictions and Sonic-derived UCS. The Results demonstrate that the ANN model is competent in predicting the sandstone UCS with high accuracy (i.e. R coefficient of the 96% and average absolute error of 7.75%). The suggested approach is anticipated to improve wellbore performance by enhancing the ability of gas and oil professionals to estimate UCS as well as reducing the cost of estimating the geo-mechanical characteristics.

Groundwater level fluctuation modeling is a prime need for effective utilization and planning the conjunctive use in any basin.The application of Artificial Neural Network (ANN) and hybrid Wavelet ANN (WANN) models was investigated in predicting Groundwater level fluctuations. The RMSE of ANN model during calibration and validation were found to be 0.2868 and 0.3648 respectively, whereas for the WANN model the respective values were 0.1946 and 0.1695. Efficiencies during calibration and validation for ANN model were 0.8862 per cent and 0.8465 per cent respectively, whereas for WANN model were found to be much higher with the respective values of 0.9436 per cent and 0.9568 per cent indicating substantial improvement in the model performance. Hence hybrid ANN model is the promising tool to predict water table fluctuation as compared to ANN model.