This paper presents a novel application of machine learning models to clarify the intricate behaviors of expansive soils, focusing on the impact of sand content, saturation level, and dry density. Departing from conventional methods, this research utilizes a data-centric approach, employing a suite of sophisticated machine learning models to predict soil properties with remarkable precision. The inclusion of a 30% sand mixture is identified as a critical threshold for optimizing soil strength and stiffness, a finding that underscores the transformative potential of sand amendment in soil engineering. In a significant advancement, the study benchmarks the predictive power of several models including extreme gradient boosting (XGBoost), gradient boosting regression (GBR), random forest regression (RFR), decision tree regression (DTR), support vector regression (SVR), symbolic regression (SR), and artificial neural networks (ANNs and proposed ANN-GMDH). Symbolic regression equations have been developed to predict the elasticity modulus and unconfined compressive strength of the investigated expansive soil. Despite the complex behaviors of expansive soil, the trained models allow for optimally predicting the values of unconfined compressive parameters. As a result, this paper provides for the first time a reliable and simply applicable approach for estimating the unconfined compressive parameters of expansive soils. The proposed ANN-GMDH model emerges as the pre-eminent model, demonstrating exceptional accuracy with the best metrics. These results not only highlight the ANN’s superior performance but also mark this study as a groundbreaking endeavor in the application of machine learning to soil behavior prediction, setting a new benchmark in the field.

Expansive soils pose significant challenges to structural integrity, primarily due to volumetric changes that can lead to detrimental consequences and substantial economic losses. This study delves into the intricate dynamics of expansive soils through loaded swelling pressure experiments conducted under diverse conditions, encompassing variations in the sand content, initial dry unit weight, and initial degree of saturation. The findings underscore the pronounced influence of these factors on soil swelling. To address these challenges, a novel method leveraging machine learning prediction models is introduced, offering an efficient and cost-effective framework to mitigate potential hazards associated with expansive soils. Employing advanced algorithms such as decision tree regression (DTR), random forest regression (RFR), gradient boosting regression (GBR), extreme gradient boosting (XGBoost), support vector regression (SVR), and artificial neural networks (ANN) in the Python software 3.11 environment, this study aims to predict the optimal applied stress and dry unit weight required for soil swelling mitigation. Results reveal that XGBoost and ANN stand out for their precision and superior metrics. While both performed well, ANN demonstrated exceptional consistency across training and testing phases, making it the preferred choice. In the tested dataset, ANN achieved the highest R-squared values (0.9917 and 0.9954), lowest RMSE (7.92 and 0.086), and lowest MAE (5.872 and 0.0488) for predicting optimal applied stress and dry unit weight, respectively.

Expansive soils exist in many countries worldwide, and their characteristics make them exceedingly difficult to engineer. Due to its significant swelling and shrinkage characteristics, expansive soil defies many of the stabilization solutions available to engineers. Differential heave or settlement occurs when expansive soil swells or shrinks, causing severe damage to foundations, buildings, roadways, and retaining structures. In such soils, it is necessary to construct a foundation that avoids the adverse effects of settlement. As a result, building the structure’s foundations on expansive soil necessitates special consideration. Helical piles provide resistance to uplift in light structures. However, they may not fully stabilize foundations in expansive soils. A granular anchor pile is another anchor technique that may provide the necessary resistance to uplift in expansive soils using simpler methods. This review and numerical study investigate the fundamental foundation treatments for expansive soils and the behavior of granular anchors and helical piles. Results indicate that granular anchor piles performed better than helical piles for uplift and settlement performance. For heave performance, the granular anchor and helical piles perform nearly identically. Both achieve heave reductions greater than 90% when L/H > 1.5 and D = 0.6 m.

The construction of tunnels in densely populated urban areas poses a significant challenge in terms of anticipating the settlement that may result from tunnel excavation. This paper presents a new and more realistic modeling method for tunnel excavation using a Tunnel Boring Machine (TBM). This method is compared with other reference modeling methods using a validated model of a subsurface tunnel excavated by a TBM with a slurry shield. A parametric study is conducted to investigate the impact of key parameters, including structure width, foundation depth, eccentricity, load on the structure, overburden depth, and tunnel diameter, on tunnel–soil–structure interaction and the resulting structure settlements. The results reveal that the tunnel diameter, eccentricity, and overburden depth have a significant impact on structure settlements, with values of 22.5%, 17%, and 7.1%, respectively. Finally, the paper proposes an equation for predicting the maximum settlement of a structure, considering the critical parameters. The validity of the equation is evaluated by comparing its results with the outputs from various case studies, including a newly validated model, two real-life case studies, and centrifuge tests. The results indicate a high level of consistency between the calculated and measured settlements.

Soil-water characteristic curve (SWCC) is an essential parameter in unsaturated soil mechanics, and it plays a significant role in geotechnical engineering to enhance theoretical analysis and numerical calculations. This study investigated the effects of key factors, such as the percentage of sand, initial degree of saturation, and initial dry unit weight, on the SWCC of expansive soil by measuring the matric suction using a pressure apparatus method. The empirical equation of SWCC was obtained using the Van Genuchten and Fredlung Xing models, and the processing of experimental data checks the fitting of the two empirical models. The findings revealed that the Fredlung Xing model fit the relationship between matric suction and volumetric water content of expansive soil better than the Van Genuchten model, indicating that the pressure apparatus approach’s experimental data are correct and acceptable. The study also found that the matric suction increased with decreasing percentage of added sand at the same volumetric moisture content, and the increase in initial dry unit weight increased the matric suction, with the water retention capacity decreasing significantly after adding 20% sand. Moreover, as the initial degree of saturation increased, the volumetric water content decreased, and the characteristic curves became identical when the initial saturation degree reached 90%. Finally, to minimize the water retention capacity of expansive soils, the study recommended adding a percentage of sand not less than 30% to the expansive clay sample.

Expansive clayey soils often pose challenges for construction projects due to their low bearing capacity, swelling, and shrinkage properties. While previous research has explored additives to enhance these soils’ properties, the potential of sand remains underexplored. This study investigates the impact of varying sand percentages on expansive clayey soils’ consistency, compaction, and permeability. This study examines how adding different percentages of sand influences the physical properties of expansive clayey soils. Laboratory tests involved systematic testing of texture, compaction, and permeability. Findings reveal a notable improvement in the physical properties of the soil with the addition of sand. Results from the laboratory tests provided data for empirical equations that facilitate the prediction of soil properties based on the sand content. The enhancement in soil properties underscores the potential of sand as an additive for expansive clayey soils. The empirical equations presented here provide practical benefits to geotechnical engineers and practitioners engaged in construction projects involving these soils, offering them valuable insights into the benefits of sand additives to improve physical characteristics. The insights gained from this research hold promising prospects for improving construction practices and addressing the challenges associated with these soils.