Sufyan Ghani

Bio: Sufyan Ghani is an academic researcher from National Institute of Technology, Patna. The author has contributed to research in topics: Liquefaction & Soil liquefaction. The author has an hindex of 4, co-authored 10 publications receiving 29 citations.

A novel liquefaction study for fine-grained soil using PCA-based hybrid soft computing models

Abstract: Earthquake-induced liquefaction is an unpredicted phenomenon that causes catastrophic damages and devastation to the environment, structures, and human life. The assessment of soil liquefaction behavior is a decisive work for geotechnical engineers especially during the designing phase of any civil engineering projects. These decisions implicate tedious and costly experimental procedures and extensive evaluation. Considering these facts, the present study aims to simplify the process of evaluating soil’s liquefaction behavior in a broader domain involving the least experimental datasets. Three PCA (principal component analysis)-based advanced hybrid computational models, namely PCA-ANN, PCA-ANFIS, and PCA-ELM were developed to predict the liquefaction behavior of soils. The dimension reduction technique, i.e. PCA, was used to avoid the multicollinearity effect during the course of the development of the said models. Geotechnical parameters, namely plasticity index, SPT blow count, water content to liquid limit ratio, bulk density, total stress, effective stress, and fine content along with other seismic input variables, such as the ratio of peak ground acceleration and acceleration due to gravity, and magnitude of an earthquake were used to develop the predictive models. The predictive accuracy of the proposed models was evaluated via several fitness parameters. In the end, the best predictive model was determined using a novel tool called Rank Analysis. Based on the results, it has been established that the PCA-ELM hybrid computational model can be considered as a new alternative tool to assist geotechnical engineers in the task of assessing the liquefaction potential of soil during the preliminary design stage in any engineering project.

Experimental and computational response of strip footing resting on prestressed geotextile-reinforced industrial waste

Abstract: Geotechnical engineering practices involves the use of geosynthetic as one of the major construction materials for stabilizing terrains and these materials have been also proven to be technically efficient. In view of the above, a series of model load tests with variation in the depth of geotextile and prestressing force were carried out to study the strength and deformation characteristics of ferrochrome slag reinforced with single prestressed geotextile layer. The present study provides a sustainable replacements solution for industrial waste such as ferrochrome slag. It is also found that pretensioning of reinforcements is effective in comparison with simple reinforcement. The load settlement curves demonstrate that reinforcements and prestressing significantly reduce the settlement of a strip footing resting on geotextile-reinforced ferrochrome slag. Also, a pretensioning force of 9 kN/m is found to have the least settlement. Further, this study proposes the use of artificial neural network and extreme learning machine (ELM) to predict settlement using basic input parameters. Application of computational models provides an innovative solution for predicting the settlement of footing with ease and in a cost-efficient manner. The computational model concludes that the developed ELM models are efficient and effective in predicting the settlement of a footing and can be used as a robust tool for preliminary assessments.

Liquefaction study of fine-grained soil using computational model

Abstract: Liquefaction is one of the most disastrous phenomena that arises due to earthquakes and has always been a major concern for engineers due to the damages and devastation it causes to the environment, structures and the human life. Liquefaction evaluation has been studied vigorously by many researchers for past few decades and based on their observations various researchers gave different limits of PI and other geotechnical parameters which classified soil in liquefiable, potentially liquefiable and non-liquefiable zones, but the question of reliability still needs to be addressed. The present study provides a new set of range for plasticity index and wc/LL ratio for liquefaction classification of fine-grained soil. The present study develops a computational model based on in situ soil properties to evaluate liquefaction potential. Artificial neural network (ANN) model has been developed for predicting liquefaction susceptibility. The significance of plasticity index on liquefaction has been primarily considered while developing the ANN model. The results confirm that the use of artificial intelligence shows the best success rate amongst all the considered approaches for prediction of liquefaction. Due to its efficient cost and quick predictions, it can be used as a sustainable method for evaluating and predicting risk against seismic hazard and infrastructural development.

Insight into the Effect of Fine Content on Liquefaction Behavior of Soil

Abstract: The present paper presents different approaches which includes plasticity based criteria that helps in distinguish between liquefiable and non-liquefiable soils deposits having fine content. A brief review of the previous work has been mentioned to emphasise on the need of new parameters for liquefaction susceptibility of clayey soils. Clay content, liquid limit and water content are considered as key parameters that helps in liquefaction assessment. Several recommendations proposed by prominent researchers are described here to present wide range of plasticity index, liquid limit and other parameters that affects liquefaction behaviour of clayey soil significantly. But the differences in the range of plasticity index leads to confusion and misperception in determination of liquefaction susceptibility of fine grained soil. One of the high seismic zone site is analyzed using different approach which consider fine content of soil mass. It is found that for a better and proper segregation of the layers Bray and Sancio criteria may be adopted which uses plasticity as one of its input parameter and clearly differentiate site in between liquefiable, non-liquefiable and sites that may liquefy i.e. moderately liquefiable. This summarizes that plasticity is one of the significant criteria which draws a clear differentiating line between liquefiable and non-liquefiable soil deposits.

Probabilistic Study of Liquefaction Response of Fine-Grained Soil Using Multi-Linear Regression Model

Abstract: Liquefaction behavior of fine-grained soil is associated with numerous soil parameters; however, over the past few years, importance of plasticity in predicting liquefaction susceptibility of soil has been well established in the literature. Regardless of recent advancements, no evident correlation has been developed between plasticity of the soil and factors of safety against liquefaction. Henceforth, the present study evaluates the effect of plasticity on liquefaction behavior of fine-grained soil for seismically active regions of Bihar (India) by proposing an equation based on multi-linear regression (MLR) analysis for predicting factor of safety against liquefaction (FL). The results of the study are supported by reliability analysis (FOSM) which also establish a co-relation between FL, reliability index (β) and probability of liquefaction (PL). The validation of the results using real liquefaction data obtained from liquefied and non-liquefied sites of Chi-Chi earthquake in Taiwan as well as data from Indo-Gangetic plains has confirmed the consistency of the developed multi-linear regression equation. The study devices a substantial impact in the field of liquefaction prediction for fine-grained soil with moderate to high plasticity and aims to felicitate a significant contribution in the knowledge pool of liquefaction studies. The developed equation may also serve as a guideline for taking critical engineering decisions especially during preliminary design calculations of any civil engineering structures vulnerable to liquefaction.

Screening guide for rapid assessment of liquefaction hazard at highway bridge sites (excerpts)

Abstract: As an aid to seismic hazard assessment, this report provides a "screening guide" for systematic evaluation of liquefaction hazard at bridge sites and a guide for prioritizing sites for further investigation or mitigation. The guide presents a systematic application of standard criteria for assessing liquefaction, ground displacement potential, and vulnerability of bridges to damage. This CD-ROM version contains excerpts from the original report.

A novel improved Harris Hawks optimization algorithm coupled with ELM for predicting permeability of tight carbonates

Abstract: Tight carbonate reservoirs appear to be heterogeneous due to the patchy production of various digenetic properties. Consequently, the permeability calculation of tight rocks is costly, and only a finite number of core plugs in any single reservoir can be estimated. Hence, in the present study, a novel hybrid model constructed by combination of the improved version of the Harris Hawks optimisation (HHO), i.e., IHHO, and extreme learning machine (ELM) is proposed to predict the permeability of tight carbonates using limited number of input variables. The proposed IHHO employs a mutation mechanism to avoid trapping in local optima by increasing the search capabilities. Subsequently, ELM-IHHO, a novel metaheuristic ELM-based algorithm, was developed to predict the permeability of tight carbonates. Experimental results show that the proposed ELM-IHHO attained the most accurate prediction with R2 = 0.9254 and RMSE = 0.0619 in the testing phase. The result of the proposed model is significantly better than those obtained from other ELM-based hybrid models developed with particle swarm optimisation, genetic algorithm, and slime mould algorithm. The results also illustrate that the proposed ELM-IHHO model outperforms the other benchmark model, such as back-propagation neural nets, support vector regression, random forest, and group method of data handling in predicting the permeability of tight carbonates.