5 March 2024 in Arabian Journal for Science and Engineering
Industrialization and population growth have made surface areas more valuable, thereby the multi-story buildings have become an absolute necessity. At this point, numeric models became the fastest and simplest way to evaluate the response of soils and structures. The issued factor in the current paper is related to the way of transferring the multi-story building loads to an alluvial stratum and evaluate the accuracy of different cases, in order to save time and economy. For load transfer, the first case (case i) includes uniform distributed load, the second case (case ii) includes the transfer from the basement columns and walls, and the third case (case iii) includes modeling the real state of the building. Mainly, all three cases gave close results in terms of settlement magnitudes of 2.21, 1.96, and 1.81 cm, respectively. It was inspected that case (i) showed 12.8% more deformation than case (ii) and 22.1% more deformation than case (iii). However, the situation is not the same for the settlement pattern, and the under-column and corner effects are neglected in uniform load. Additionally, the bending moments, which is a critical parameter for the design of a reinforced concrete foundation, have developed different results. In case (ii) and (iii) a bending moment of 500 kNm/m is observed in the center column, while in case (i) the moments converge to 0. Therefore, this study highlights the importance of outstanding decision making when assessing the load-transferring mechanism in modeling with numerical methods. The necessity of the determination of the convenient load transfer way depending on the parameter that is crucial in the evaluation of the soil–structure interaction comes to the fore with current paper.
1 January 2026 in Open Geosciences
The accurate prediction of ultimate settlement is of critical importance for the longevity of structures, as it helps prevent structural damage and functional deterioration. Settlement, a function of the soil’s compression index ( C
c
), is typically determined through oedometer tests. This research seeks to enhance the prediction accuracy of C
c
within a sustainability framework by employing advanced machine learning techniques. A series of soil samples with varying clay contents were synthesized by incorporating bentonite into silt, resulting in nine distinct soil classes ranging from low plasticity silt (ML) to high plasticity clay (CH). Consolidation tests were performed on reconstituted samples subjected to 100 kPa pre-consolidation pressure, revealing significant correlations between the compression index and various physical properties. Leveraging these correlations, a comprehensive dataset was compiled, integrating current experimental data with relevant studies from the literature. The predictive capabilities of several machine learning models, including Support Vector Regression (SVR), Artificial Neural Networks (ANN), Random Forest (RF), and Multiple Regression Analysis (MRA), were evaluated. Among these, the RF model exhibited superior performance, achieving an R 2 of 0.83. The study introduces a novel prediction framework that extends beyond conventional settlement estimation by incorporating a comparative ML-based modeling approach supported by both experimental and literature-based data. Furthermore, the methodology demonstrates its practical value by offering a faster and less resource-dependent alternative to traditional consolidation testing, contributing to sustainability oriented and cost-efficient geotechnical design.