Seismic actions are usually considered for their inertial effects on the built environment. However, additional effects may be caused by the volumetric-distortional coupling of soil behaviour: the fast cyclic shaking on saturated soils caused by earthquakes generates temporary undrained or quasi-undrained conditions and subsequent pore pressure variations that, if positive, reduce the effective stresses, eventually leading loose granular soils to liquefaction. Whatever the amount of seismically induced pore pressure build up, buildings on shallow foundations suffer settlements and tilts that may be extremely large when soils approach liquefaction, as demonstrated by several recent case histories. The paper proposes an equivalent elastic approach in effective stresses to predict the co-seismic (undrained) component of the seismically induced settlement of shallow foundations, which usually is the most relevant one, by considering the decrease of soil stiffness during the seismic event. The total settlement can be then estimated by adding the post-seismic (drained) component, also evaluated in this paper via a quite simple approach. Even though the equivalent elastic model is stretched into a highly non-linear soil behaviour range, especially when the soil is approaching liquefaction, the model considers the relevant capacity and demand factors and proved effective in simulating some centrifuge tests published in the literature. In the paper, the simplifying assumptions of the approach are clearly indicated, and their relevance discussed. It is argued that notwithstanding some limitations the model is physically based and therefore it allows for understanding and checking the relative relevance of all the parameters related to soil, foundation, and seismic action. Thus, it is a tool of possible interest in the design of shallow foundations in liquefaction-prone seismic areas.

Upon completing large-area layered filling, the foundation soil exhibits transverse isotropy and is predominantly. unsaturated, making post-construction settlement prediction challenging. Additionally, the creep model considering transverse isotropy and unsaturated characteristics has not been proposed. Therefore, the true triaxial apparatus for unsaturated soil was enhanced, and transversely isotropic unsaturated loess samples were prepared. The relationship between matrix suction and moisture content at various depths in transversely isotropic unsaturated loess was determined using soil-water characteristic curve tests. The creep characteristics of loess fill under varying moisture content, degree of compaction, deviatoric stress, and net confining pressure were examined using a consolidation drainage test system. According to the creep curve, the expressions for six parameters in the modified Burgers element model were determined, establishing a post-construction settlement prediction method for transversely isotropic unsaturated loess fill foundations. The results show that the transversely isotropic unsaturated loess exhibits distinet creep characteristics, primarily nonlinear attenuation creep. The degree of compaction, moisture content, deviatoric stress and net confining pressure significantly affect its creep characteristics. Creep stability strain is linearly related to the degree of compaction. Enhancing soil compaction can effectively reduce post-construction settlement of the fill foundation. A prediction algorithm based on the modified Burgers model, which reflects the influence of degree of compaction, moisture content, and stress level, and accurately describes the post-construction settlement behavior of transversely isotropic unsaturated loess fill foundations, is established. Actual engineering monitoring results demonstrate that the proposed settlement prediction algorithm is simple, practical, and effective. The research results can enrich and advance the creep model of unsaturated soil, and provide a scientific basis for solving the problem of deformation calculation of high fill foundation.

Physics-Informed Neural Networks (PINNs) have shown considerable potential in solving both forward and inverse problems governed by partial differential equations (PDEs) for a wide range of practical applications. This study leverages PINNs for modeling nonlinear large-strain consolidation of soft soil, including creep behavior. The inherent material and geometric nonlinearities associated with soft soil consolidation pose challenges for PINNs, including precision and computational efficiency. To address these issues, we introduce self-adaptive physics-informed neural networks (SA-PINNs), featuring an adaptive loss function weighting and a slope scaling method for the activation functions. Additionally, a sensitivity analysis exploring the influence of monitoring data on the parameter inversion accuracy is presented. Two engineering case studies are used to benchmark the settlement prediction capabilities of the present SA-PINN method with traditional techniques, demonstrating the superior prediction accuracy and consistency of the SA-PINN approach. The findings highlight the significant potential of SA-PINN in practical geotechnical engineering problems.

In uncoupled consolidation analysis, settlement and pore water pressure are solved independently, whereas in coupled analysis, they are solved simultaneously to ensure continuity (i.e., the volume change in soil due to compression must equal the water volume change caused by dissipation). This study investigates the coupling effects of soil deformation and pore water pressure dissipation in the back analysis of soft soil settlements. It further evaluates the suitability of both coupled and uncoupled constitutive models with different types of monitoring data, providing practical guidance for selecting consolidation models and achieving reliable long-term predictions. The one-dimensional governing equations for soft soil consolidation, incorporating prefabricated vertical drains and creep deformation, are first reviewed. A case study of a trial embankment in Ballina, New South Wales, Australia, is then used to demonstrate the impact of coupling effects and monitoring data on settlement predictions. The results show that considering coupling effects not only improves long-term settlement predictions but also reduces uncertainties in the updated soil parameters, especially when both settlement and pore water pressure data are used.

Accurate settlement forecasting is essential for preventing severe structural and infrastructure damage. This paper investigates predicting tunneling-induced ground settlements using machine learning models. Empirical methods for estimating settlements are often imprecise and site-specific. Developing novel, accurate prediction methods is critical to avoid catastrophic damage. The umbrella arch method constrains deformations for initial stability before installing primary support. This study develops machine learning models to forecast settlements solely from umbrella arch parameters, disregarding soil properties. Multilayer perceptron artificial neural networks (MLP-ANN) and support vector regression (SVR) are applied. Results demonstrate machine learning outperforms empirical methods. The MLPANN surpasses SVR, with R2 of 0.98 and 0.92, respectively. Strong correlation is observed between umbrella arch configuration and settlements. The suggested approach effectively estimates surface displacements lacking mechanical properties. Overall, this study supports machine learning, specifically MLP-ANN, as an efficient, reliable alternative to empirical methods for predicting tunneling-induced ground settlements from umbrella arch design.

Rolling dynamic compaction (RDC) has been found to be useful for compaction soils and is now widely used globally. Because RDC is not often used in soft soils with poor engineering properties, field monitoring was used to study the soft clay embankment responses under RDC conditions in this study. Analysis of the monitoring data revealed that the response of the soil occurred mainly in the first 20 passes. Field monitoring revealed a strong correlation between settlement, horizontal displacement, and pore water pressure. The depth of impact of RDC on the soft soil embankment was between 3 and 3.5 m. Although settlement prediction is an important issue for construction, there is a lack of prediction methods for RDC-induced soil settlement. In this study, we used three different machine learning algorithms: random forest regression (RFR), multilayer perceptron (MLP), and extreme gradient boosting (XGBoost) to predict the total settlement and uneven settlement induced by RDC on the soft soil embankment. The three prediction models were compared, and the predictive accuracy of these models was assessed. This study analyzes and summarizes the effect of RDC application on a soft clay embankment and explores the machine learning method used for settlement prediction based on monitoring data, which provides some methods and ideas for research on the application of RDC on soft soil foundations.

The prediction of time-dependent deformations of embankments constructed on soft soils is essential for preloading or surcharge design. The predictions can be obtained by Bayesian back analysis methods progressively based on measurements so that practical decisions can be made after each monitoring round. However, the effect of creep is typically ignored in previous settlement predictions based on Bayesian back analysis to avoid the heavy computational costs. This study aims to fill this gap by combining the Bayesian back analysis with a decoupled consolidation constitutive model, which accounts for creep to perform long-term settlement predictions of the trial embankment with prefabricated vertical drains (PVDs) constructed in Ballina, Australia. The effect of creep on settlement predictions is illustrated by the comparisons of the cases with and without considering creep. The results show that good settlement predictions could be obtained if creep is ignored and could be further improved if creep is incorporated when the monitoring settlement data is applied in the Bayesian back analysis. Ignoring creep could lead to an underestimation of the ultimate consolidation settlement. The swelling index kappa and the compression index lambda need to be adjusted to larger values to match the measurements if creep is ignored. Four updating schemes (using surface settlement data only, using settlement data at all monitoring depths, using pore water pressure data only, and using both settlement and pore water pressure data) are applied to study the effects of monitoring data on the accuracy of settlement prediction. The results show that the variability introduced by the noisy pore water pressure data result in fluctuating settlement predictions. Incorporating both settlement and pore water pressure observations into the Bayesian updating process reduces the variability in the updated soil parameters.