This study investigates the application of machine learning (ML) algorithms for seismic damage classification of bridges supported by helical pile foundations in cohesive soils. While ML techniques have shown strong potential in seismic risk modeling, most prior research has focused on regression tasks or damage classification of overall bridge systems. The unique seismic behavior of foundation elements, particularly helical piles, remains unexplored. In this study, numerical data derived from finite element simulations are used to classify damage states for three key metrics: piers' drift, piles' ductility factor, and piles' settlement ratio. Several ML algorithms, including CatBoost, LightGBM, Random Forest, and traditional classifiers, are evaluated under original, oversampled, and undersampled datasets. Results show that CatBoost and LightGBM outperform other methods in accuracy and robustness, particularly under imbalanced data conditions. Oversampling improves classification for specific targets but introduces overfitting risks in others, while undersampling generally degrades model performance. This work addresses a significant gap in bridge risk assessment by combining advanced ML methods with a specialized foundation type, contributing to improved post-earthquake damage evaluation and infrastructure resilience.

This paper employed PFC3D and FLAC3D to conduct a three-dimensional discrete-continuous dual-scale coupled simulation and stability analysis of cohesive soil slope through discrete-continuous coupled algorithm and the gravity increase method. In the discrete element model zone, the progressive failure process of cohesive soil slope was studied by setting particles with different displacements to different colours, the evolutions of porosity and coordination number in the shear, sliding and stability zones of slope were analysed by arranging measurement spheres, and the variation law of particle position was obtained by the vertical layering of the soil. In the continuous model zone of coupled slope model, the horizontal and vertical stresses were verified with those of a pure FLAC3D model of slope. Furthermore, a comparative instability analysis of cohesive soil slope and gravelly soil slope was also performed. The safety factor for the cohesive soil slope in this work was determined to be 1.7 according to the mesoscopic fabric evolution of slope particles and the gravity increase method. The work in this paper broadens the application scope of the dual-scale coupled algorithm, highlights the differences in the mesoscopic instability mechanism between cohesive soil slop and gravelly soil slop, and provides new theoretical support for slope design and risk assessment in engineering practice.

The cone penetration tests have been employed extensively in both onshore and offshore site investigations to obtain the strength properties of soils. Interpretation of effective internal friction angle gyp' becomes complicated for cones in silty clays or clayey silts, since the soil around the advancing cone may be under partially drained conditions. Although there exist several robust methods to estimate gyp ' , the pore pressure at the cone shoulder has to be measured to represent the drainage conditions. Many cone penetrometers in practice are not equipped with a pore pressure transducer. Even for a piezocone, the pore pressure recorded in-situ may be unreliable due to the poorly saturated or clogged filter. These limitations prohibit the application of existing methods. Large deformation finite element analyses were carried out within the formula of effective stress to reproduce the cone penetrations under various drainage conditions. The numerical approach was validated against the existing model tests in centrifuge and chamber, with wide ranges of penetration rates and soil types. A backbone curve is proposed to estimate the normalized cone resistance varying with the normalized penetration rate. Based on the backbone curve, a procedure is developed to predict gyp' of cohesive soils under undrained or partially drained conditions, replacing the pore pressure with the normalized penetration rate. The procedure can be used for soils with an overconsolidation ratio no larger than 5.

Expansive soils pose significant challenges due to their tendency to swell when wet and shrink when dry, causing ground instability. These volumetric changes can lead to structural damage, including foundation cracks, uneven floors, and compromised infrastructure. Addressing these issues requires proper soil evaluation and the implementation of stabilization techniques to ensure long-term safety and durability. The high degree of expansive, problematic soil is stabilized by cement, bitumen, lime, etc. This investigation predicts the unconfined compressive strength (UCS) of lime-treated soil using decision tree (DT), ensemble tree (ET), gaussian process regression (GPR), support vector machine (SVM), and multilinear regression (MLR). This research investigates the impact of dimensionality on the computational approaches. The variance accounted for (VAF), correlation coefficient (R), mean absolute error (MAE), root mean square error (RMSE), and performance index (PI) metrics have computed the model's performance. The comparison reveals that model ET5 has predicted UCS with an excellent performance in testing (RMSE = 368.06 kPa, R = 0.9640, VAF = 91.60, PI = 1.8077) and validation (RMSE = 508.41 kPa, R = 0.9165, VAF = 83.89, PI = 1.6337) phase. Also, model ET5 has achieved better score (total = 90), area over the curve (testing = 8.98E-04, validation = 1.56E-03), computational cost (testing = 0.1772s, validation = 0.1551 s), uncertainty rank (= 1), and overfitting (testing = 2.32, validation = 2.80), presenting model ET5 as an optimal performance model. The dimensionality analysis reveals that simple models like MLR, SVM, GPR, and DT struggle with high-dimensional data (case 5). Still, the ET5 model achieves high performance and reliable prediction with consistency, compaction and soil physical parameters. Conversely, the effect of multicollinearity has been observed on the performance of the MLR, SVM, and DT models.

The erodibility of clay exhibits significant variability across different influencing factors. The existing research using compaction approach for specimen preparation neglected the non-uniformity in soil specimens and is unsuitable for high plasticity clay. In this study, the saturated preconsolidation approach was used to prepare uniform kaolinite specimens to simulate natural consolidating conditions. The prepared specimens were then analyzed using a hole erosion analyzer, and the surface morphology of the eroded hole was quantified using a 3D scanner. A total of 18 hole erosion tests were conducted under various preconsolidation pressures and erosion directions. The erosion resistances were found to increase with higher prestress, and the variation of critical shear stress across different erosion directions reached 29%. The SEM images reveal a stack-packing microstructure in the consolidated specimens, with a denser clay aggregate packing observed under higher pre-stress conditions. The anisotropic erosion property is properly described by the radial anisotropic coefficient kr and the roughness anisotropic coefficient k(pr), and the critical shear stress tau(c) is negatively correlated with k(r), while its correlation with k(pr) is not obvious.

In this paper, an investigation was conducted to characterize the behavior of weakly cohesive soil subjected to vibratory compaction. Thus, the authors developed a model for weakly cohesive soils, defined by inter-parametric laws that consider their initial state and predict the evolution of state parameters resulting from static and vibratory compaction processes, depending on the number of equipment passes. Four types of soil were proposed for testing, with different initial characteristics such as dry density, longitudinal modulus, and moisture content. Some correlations between main parameters involved in the compaction process were established, considering soil mechanical properties, compaction equipment, and in situ technology applied. The results obtained in the computational environment were implemented to predict the performance compaction process for an overall assessment. This research contributes to database development by offering valuable insights for specialists aiming to apply Industry 4.0 digitalization practices, which stipulate the use of predictability laws in pre-assessing the degree of soil compaction (or settlement) to estimate and maximize the efficiency of road construction or foundation works. These insights help optimize design processes, enhance functional performance, improve resource utilization, and ensure long-term sustainability in large infrastructure projects built on these soils.

Foundation elements with rough (textured) surfaces mobilize larger interface shear resistance than ones with conventional smooth or random rough surfaces when sheared against soils under monotonic loading. The overall performance of foundation elements such as piles supporting offshore wind turbines, suction caissons supporting tidal energy converters, soil nails, and soil anchors installed in cohesive soils could be enhanced through utilizing rough (textured) surfaces to resist applied static and/or cyclic loading. This paper describes the shear behavior of smooth and rough (textured) surfaces in kaolinite clay and kaolinite clay-sand mixture soils under static and cyclic axial loading. The experimental investigation presented herein consists of a series of interface shear tests performed on 3D printed rough (textured) surfaces and a 3D printed smooth reference surface utilizing the Cyclic Interface Shear Test system. The paper includes a description of the interface testing system components, cohesive soil specimens' preparation procedure, smooth and rough (textured) surfaces details, testing procedure, and results of static and cyclic tests. Test results indicate that kaolinite clay-sand mixture soil mobilized larger static and post-cyclic interface shear resistance and volume contraction relative to kaolinite clay soil when sheared against the smooth reference surface. When tested against rough (textured) surfaces with variable asperity height, larger shear resistance was mobilized and larger soil dilation greater than that mobilized by the reference untextured surface in both soils. The results also indicate rough (textured) surfaces exhibited a prevalent frictional anisotropy increases with asperity angle and height in cohesive soils, the surfaces mobilized larger shear resistance and volume change in one direction (i.e., against the asperity right-angled side) than the other direction (i.e., along the asperity inclined side).

The advent of biopolymers in the ground improvement industry has made significant contributions by reducing the carbon footprint and tremendous improvement in soil engineering properties at par with chemical stabilizers. The current study investigates the effect of two biopolymers, chitosan, and casein on the unconfined compressive strength (UCS) behavior of high-plasticity clay at varying dosages of 0.5%, 1%, 2%, and 4%. The study also evaluates the effect of curing periods up to 90 days on the untreated and biopolymer-treated clay. Chitosan and casein bring a 1428% increase and a 989% increase in UCS at the highest dosage of 4% and the highest curing period of 90 days. The nonlinear multivariate regression models establish a link between the experimental and best-fit data with the coefficient of multiple determination (R-2) > 0.98. Additionally, the reliability analysis assesses the efficacy of biopolymer-treated soils as an alternate embankment material. With an increase in curing period of up to 28 days, the chitosan-treated samples exhibit higher factors of safety compared to casein-treated samples. The modified embankment attains a target reliability index of more than 3.0 with minimum Chitosan content (Dch) of 2.25% and Casein content (D-ca) of 1.85% at Coefficient of Variation (COV) of UCSmin= 10% for 28-day cured samples. Thus, the reliability analysis presents a rational approach for using biopolymer-treated soils in embankment construction by considering the effect of dosage, curing period, and the variability associated with the UCS.

The rheological modeling of soil-drum interaction in the vibratory compaction process is a complex process. This paper aims to describe the behavior of soil-drum interaction through lumped parameter modeling. The amplitude of the vertical motion is evaluated for dynamic conditions using the rheological models (generalized and advanced Kelvin-Voigt-based models) and compared with the experimental results obtained from weakly cohesive soil compaction. Different modeling approaches are considered, and the results reveal that the properties of the soil as input play a vital role in the accuracy of the modeling.

The cyclic loading of foundation structures in sand leads to an accumulation of plastic deformations in the structures. For shallow foundations of high and slender structures such as wind energy converters (WECs), an accumulation of the plastic rotations is expected under cyclic eccentric loading that is imposed by wind loads, which could be crucial for the proof of serviceability. A practical approach to predict the behavior of shallow foundations under high-cycle eccentric loading is under research. In this paper, a numerical approach, the cyclic strain accumulation method (CSAM), which has been validated for cyclically loaded monopiles, is adopted for shallow foundations under eccentric cyclic loading. Modifications to the CSAM are described, which are necessary to apply it to shallow foundations. The results that are gained with the modified method are compared with a medium-scale model test, in which the deformations of a footing with a diameter of 2.0 m under eccentric one-way cyclic loading were investigated. It can be concluded that the CSAM can make realistic predictions and shows satisfying agreement with the measured cyclic behavior. Although more experiments are needed to finally validate the method, the CSAM could be a promising numerical approach to account for the cyclic behavior of shallow foundations under eccentric cyclic loading in sand.