This study investigates the prediction of immediate settlement (Uz) in soft clay improved with Deep Soil Mixing (DSM) columns under heavy aircraft loading. Two key design parameters were considered: column spacing (2.25 m to 3.75 m) and column length (6 m to 20 m), with both rectangular and triangular arrangements analyzed. The datasets obtained from numerical simulations were modeled using Response Surface Methodology (RSM) and Artificial Neural Networks (ANN), with model calibration and validation performed through k-fold cross-validation. The statistical analysis revealed that both approaches achieved excellent predictive capability, with R² values exceeding 0.999. For the rectangular arrangement, RSM yielded slightly lower errors (RMSE = 0.0636 cm, MAE = 0.0553 cm) compared to ANN (RMSE = 0.0828 cm, MAE = 0.0682 cm), suggesting that a second-order polynomial approximation can effectively describe the settlement response in this configuration. Conversely, for the triangular arrangement, ANN clearly outperformed RSM, reducing RMSE from 0.0725 cm to 0.0265 cm and MAE from 0.0615 cm to 0.0111 cm, thereby capturing the nonlinear stress redistribution associated with isotropic column layouts more effectively. Observed–predicted plots confirmed the high predictive accuracy of both methods, with ANN showing superior generalization in triangular grids. Overall, the findings highlight that RSM remains a robust and computationally efficient tool for rectangular layouts with relatively linear responses. In contrast, ANN provides enhanced accuracy for triangular configurations where nonlinear interactions dominate, making it particularly suitable for DSM design optimization in airport pavement foundations.

Improving saline soils’ properties by incorporating limes is a practical technique, generally due to cation exchange, pozzolanic reaction, and carbonation. This study explores how soil salinity, measured by electrical conductivity, affects untreated and lime-treated saline soils. An Algerian sebkha soil (from Ain M’lila) with an original high salinity (ECe3 = 23.2 dS.m⁻¹) was used. The same soil was washed to create medium (ECe2 = 8.3 dS.m⁻¹) and low (ECe1 = 2.32 dS.m⁻¹) salinity soil samples. The results of this study indicate that salinity influenced the shape of the particle size distribution curve, particularly in the silt range. Salinity also had a significant effect on carbonate content (CaCO₃) and unconfined compressive strength (UCS). For the untreated soil, when salinity decreased, the UCS and CaCO₃ content increased. However, when salinity decreased for the treated soil, the UCS increased, while the CaCO₃ content decreased. X-ray diffraction (XRD) analysis of untreated soils showed halite (NaCl) disappearance and gypsum (CaSO₄ 2H₂O) reduction with decreasing salinity in ECe1. In treated soil at ECe3, these mineral phases remained constant. While XRD detected no new cementitious phases in treated ECe3 or ECe1 samples, thermogravimetric analysis confirmed the presence of portlandite in both. As Ain M’lila sebkha is a chloride–sulfate soil, the dissolution of the halite and gypsum phases released more Cl⁻ and SO₄²⁻ ions into the interstitial solution. In a low fraction of clay, these ions obstructed and slowed the pozzolanic reaction in the ECe3 soil. Identifying the season when this type of soil has lower salinity can be beneficial for treatment from a technical, economic, and environmental point of view.

This study investigates the effects of varying salinity levels on sebkha soils, focusing on their physical, mechanical, and chemical properties. Soil samples were collected from Tin silt sebkha in Ain M'lila across three different seasons, resulting in high salinity soil (HSS), medium salinity soil (MSS), and low salinity soil (LSS). The grain size distribution curves reveal that 70% of grains in both HSS and LSS have diameters less than 60 µm, with LSS containing 19% more particles smaller than 20 µm compared to HSS. Unconfined compressive strength (UCS) measurements show a significant decrease from 1100 kPa in LSS to 200 kPa in HSS, with corresponding peak strains increasing from 2.3% to 4.7%. Chemical analysis indicates that pH decreases from 8.17 in LSS to 6.79 in HSS, reflecting increased soil acidity with higher salinity. SEM images demonstrate that higher salinity results in a denser soil structure due to salt cementation, whereas lower salinity soils exhibit more micropores. The study highlights the need for comprehensive models integrating these properties to enhance predictive capabilities and inform effective soil management. Future research should explore remediation strategies using additives to improve soil strength and stability, addressing the challenges posed by salt dissolution and soil degradation.