Soft soils are commonly located in many regions near seas, oceans, and rivers all over the world. These regions are vital and attractive for population and governments development. Soft soil is classified as problematic soil owing to sustaining low shear strength and high settlement under structures. Constructing structures and/or infrastructures on soft soil is a considerable risk that needs great attention from structural engineers. The bearing capacity of structure foundations on soft soil depends mainly on their undrained shear strength. This soil feature strongly influences the selection of appropriate soil improvement methods. However, determining undrained shear strength is very difficult, costly, and time-consuming, especially for sensitive clay. Consequently, extracting undisturbed samples of sensitive clay faces several difficulties on construction sites. In this research, accurate field-tested data were fed to advanced machine learning models to predict the undrained shear strength of the sensitive clay to save hard effort, time, repeated laboratory testing, and costs. In this context, a dataset of 111 geotechnical testing points were collected based on laboratory and field examinations of the soil’s key features. These features included the water content, liquid limit, dry unit weight, plasticity index, consistency index, void ratio, specific gravity, and pocket penetration shear. Several machine learning algorithms were adopted to provide the soft clay modeling, including the linear, Gaussian process regression, ensemble and regression trees, and the support vector regression. The coefficient of determination was mainly used to assess the performance of each predictive model. The achieved results revealed that the support vector regression model attained the most accurate prediction for soil undrained shear strength. These outcomes lay the groundwork for evaluating soil shear strength characteristics in a practical, fast, and low-cost way.

Stabilisation of expansive soil using lime or sand is an effective improvement technique as it reduces the swelling ability of the soil. The aim of this paper is to study the influence of different lime fractions and lime–sand mixtures on the behaviour of highly expansive clay by performing swelling and strength tests on each mixture. Calcium (Ca)-bentonite is utilised as highly expansive clay. All samples were remoulded according to the results of the modified compaction Aashto test. Non-treated bentonite possesses high values of swelling and strength. Mixing lime and sand with clay causes significant reductions in swelling characteristics. The reductions increase effectively with the increase in lime and sand content. The swell potential and the swelling pressure of the clay almost vanish when stabilised by 10% lime and 50% sand. Generally, adding only lime into clay leads to an increase of its California bearing ratio (CBR) and unconfined compressive strength (UCS), whereas mixing clay with both lime and sand leads to an increase in the CBR values. The CBR values increase significantly with the increment of their content. For a >30% sand content, the UCS of the lime–clay mixtures decreases on increasing the sand fractions, whereas the UCS values increase with a longer curing time. The CBR and UCS-56 d curing time of the stabilised clay with 10% lime and 50% sand increase to twice the values for the non-treated clay.

The aim of the present research is to improve the mechanical characteristics of a continental collapsible Sabkha soil using eco-friendly lime content under structures. The experimental portion is performed on both treated and untreated saturated collapsible soil, focusing on compaction characteristics, collapse potential, shear strength, and California bearing ratio (CBR). Full-scale three-dimensional numerical models are built for a footing that rests on untreated and treated collapsible soil with different lime contents under immersion conditions. The results indicate that increasing lime in collapsible soil causes incremental improvements in the maximum dry density. Furthermore, lime stabilization effectively reduces the collapse potential of the studied soil, while increasing lime content in the soil leads to a greater reduction in the collapse potential, with a 20% lime content completely resolving the collapse problem. Increases in lime content also contribute to important increments in shear strength parameters and CBR values. Moreover, the shear strength of the stabilized soil with 20% lime increases to more than six times that of the untreated soil. The improvement in the mechanical properties of the stabilized soil is found to persist over time. Numerical analyses results also show that lime stabilization significantly increases the allowable bearing capacity of the soil. Consequently, the stabilized soil with 20% lime content increases the allowable bearing capacity to more than seven times that of the untreated soil, effectively reducing settlement of the footing.