Buried pipelines are essential for the safe and efficient transportation of energy products such as oil, gas, and various chemical fluids. However, these pipelines are highly vulnerable to ground movements caused by geohazards such as seismic faults, landslide, liquefaction-induced lateral spreading, and soil creep, which can result in potential pipeline failures such as leaks or explosions. Response prediction of buried pipelines under such movements is critical for ensuring structural integrity, mitigating environmental risks, and avoiding costly disruptions. As such, this study adopts a Physics-Informed Neural Networks (PINNs) approach, integrated with a transfer learning technique, to predict structural response (e.g., strain) of both unreinforced and reinforced steel pipes subjected to Permanent Ground Displacement (PGD). The PINN method offers a meshless, simulation-free alternative to traditional numerical methods such as Finite Element Method (FEM) and Finite Difference Method (FDM), while eliminating the need for training data, unlike conventional machine learning approaches. The analyses can provide useful information for in-service pipe integrity assessment and reinforcement, if needed. The accuracy of the predicted results is verified against Finite Element (FE) and Finite Difference (FD) methods, showcasing the capability of PINNs in accurately predicting displacement and strain fields in pipelines under geohazard-induced ground movement.

This study conducted load-bearing capacity tests to quantitatively analyze the impact of permafrost degradation on the vertical load-bearing capacity of railway bridge pile foundations. Meanwhile, a prediction model vertical load-bearing capacity for pile foundations considering permafrost degradation was developed and validated through these tests. The findings indicate that the permafrost degradation significantly influences both the failure patterns of the pile foundation and the surrounding soil. With the aggravation of permafrost degradation, damage to the pile foundation and the surrounding soil becomes more pronounced. Furthermore, permafrost degradation aggravates, both the vertical ultimate bearing capacity and maximum side friction resistance of pile foundations exhibit a significant downward trend. Under unfrozen soil conditions, the vertical ultimate bearing capacity of pile foundations is reduced to 20.1 % compared to when the permafrost thickness 160 cm, while the maximum side friction resistance drops to 13.2 %. However, permafrost degradation has minimal impact on the maximum end bearing capacity of pile foundations. Nevertheless, as permafrost degradation aggravates, the proportion of the maximum end bearing capacity attributed to pile foundations increases. Moreover, the rebound rate of pile foundations decreases with decreasing permafrost thickness. Finally, the results confirm that the proposed prediction model can demonstrates a satisfactory level of accuracy in forecasting the impact of permafrost degradation on the vertical load-bearing capacity of pile foundations.

A series of finite element analyses, conducted on the basis of modified triaxial tests incorporating radial drainage, were carried out to investigate the lateral deformation and stress state characteristics of prefabricated vertical drain (PVD) unit cells under vacuum preloading. The analyses revealed that the inward horizontal strain of the unit cell increases approximately linearly with the vacuum pressure (Pv) but decreases non-linearly with an increase in the initial vertical effective stress (sigma ' v0). The variations in the effective stress ratio, corresponding to the median excess pore water pressure during vacuum preloading of the PVD unit cell, were elucidated in relation to the Pv and sigma ' v0 using the simulation data. Relationships were established between the normalized horizontal strain and normalized effective stress ratio, as well as between the normalized stress ratio and a composite index parameter that quantitatively captures the effects of vacuum pressure, initial effective stress, and subsoil consolidation characteristics. These relationships facilitate the prediction of lateral deformation in PVD-improved grounds subjected to vacuum preloading, utilizing fundamental preloading conditions and soil properties. Finally, the proposed methodology was applied to analyze two field case histories, and its validity was confirmed by the close correspondence between the predicted and measured lateral deformation.

Freeze-thaw (FT) cycles significantly affect soil permeability and could cause geological and environmental disasters. This study investigated the influence of FT cycles on the permeability of compacted clay through triaxial permeability tests, considering freezing temperature, cycle number, water content, and confining pressure. Scanning electron microscopy and nuclear magnetic resonance tests were performed to analyze the microstructure and pore characteristics of the clay during FT cycles. The results show that the hydraulic conductivity of the clay decreases significantly at high confining pressures due to soil consolidation. When the confining pressure exceeds 150 kPa, the impact of FT cycles on hydraulic conductivity becomes negligible. The increased number of FT cycles, exposure to lower freezing temperatures, and higher water content lead to more pronounced soil structure damage, resulting in a substantial increase in hydraulic conductivity. FT cycles cause macropores and microcracks to form and increase the average pore radius, creating preferential seepage pathways. Correlation analysis indicates that the increase in macropore content under various FT cycles is the primary reason for the increased hydraulic conductivity. Based on the modified Kozeny-Carman equation, a prediction model is developed to effectively estimate the hydraulic conductivity. These results provide valuable insight into the damage mechanism of clay permeability in seasonally frozen regions from a microscale perspective.

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.

Freeze-thaw cycles coupled with sulfate attack represent one of the most challenging service environments for concrete. This study aims to enhance the durability of concrete materials in environments characterized by sulfate attack and severe freeze-thaw conditions. Specifically, it investigates the deterioration laws and evolution models of mortar materials containing silica fume under both freeze-thaw and coupled freeze-thaw/sulfate attack conditions. Mortar specimens with varying silica fume contents (0%, 6%, 8%, and 10%) were prepared and subjected to single freeze-thaw and coupled freeze-thaw-sulfate attack tests to examine the impact of different silica fume dosages on the durability of mortar materials under these harsh conditions. Additionally, a quantitative assessment model for damage evolution was established using the entropy weight method and Wiener process model. The research findings indicate that silica fume significantly enhances the sulfate resistance and freeze-thaw durability of mortar materials, with an optimal dosage of 10%. Within the scope of this study, higher silica fume content results in a greater number of sulfate attack-freeze-thaw cycles the mortar can endure before damage and failure, thereby extending its service life. Based on the Wiener stochastic process damage model and field data, it is predicted that the service life of mortar containing 10% silica fume increases most notably to 36.6 years, representing a relative improvement of 45.8 % compared to mortar without silica fume. These results provide valuable references and guidance for the design and construction of concrete structures in regions characterized by high-cold temperatures and salt- corrosive soils.

Soil desiccation cracks and crack networks significantly influence the mechanical properties of soils. Accurate modeling and prediction of crack development are essential for both laboratory research and practical applications in geotechnical engineering and environmental science. In this study, a Desiccation Crack Simulation Program (DCSP) was developed on the MATLAB platform to simulate the evolution of soil desiccation cracks. Based on comprehensive statistical analyses of crack network images from previous studies and detailed observations of crack propagation, we propose a stochastic crack network generation model informed by geometric parameters and crack development processes. The model encompasses five key steps: (1) selection of crack initiation points, (2) crack propagation and intersection, (3) termination of crack growth, (4) secondary crack generation, and (5) final network formation. Key parameters include crack step size, randomized propagation direction, number of initial development points, and crack attraction distance. The DCSP enables both the rapid generation of random crack networks and the prediction of partially developed networks. The program was validated using two soil types, Xiashu soil and Pukou soil, demonstrating its effectiveness in simulating crack evolution. Prediction accuracy improves as crack network develops, highlighting the model's potential for predicting soil desiccation crack patterns.

Floods are devastating natural disasters causing significant damage worldwide, especially in southern Latin America, where recurrent river floods lead to severe impacts. This study proposes an innovative flood modelling approach using a naive Bayes classifier to simulate flood extents at a regional scale, incorporating spatial and temporal variability. Using 12 features, including topography, soil properties, precipitation and discharge, the model was trained with multiple flood events, avoiding sampling limitations and evaluating optimal pre-processing strategies for continuous data. The predictive capacity resulted in high performance metrics, with temporal validation accuracy (AC) up to 0.98 and a critical success index (CSI) of 0.58, and spatial validation achieved an AC up to 0.97 and CSI of 0.56, outperforming the hydrodynamic model by 65%. A reduced model with significant features improved computational efficiency and achieved a CSI exceeding 0.60. This practical tool supports flood risk management and enhances resilience in vulnerable regions.

Moisture accumulation within road pavements, particularly in unbound granular materials with or without thin sprayed seals, presents significant challenges in high-rainfall regions such as Queensland. This infiltration often leads to various forms of pavement distress, eventually causing irreversible damage to the pavement structure. The moisture content within pavements exhibits considerable dynamism and directly influenced by environmental factors such as precipitation, air temperature, and relative humidity. This variability underscores the importance of monitoring moisture changes using real-time climatic data to assess pavement conditions for operational management or incorporating these effects during pavement design based on historical climate data. Consequently, there is an increasing demand for advanced, technology-driven methodologies to predict moisture variations based on climatic inputs. Addressing this gap, the present study employs five traditional machine learning (ML) algorithms, K-nearest neighbors (KNN), regression trees, random forest, support vector machines (SVMs), and gaussian process regression (GPR), to forecast moisture levels within pavement layers over time, with varying algorithm complexities. Using data collected from an instrumented road in Brisbane, Australia, which includes pavement moisture and climatic factors, the study develops predictive models to forecast moisture content at future time steps. The approach incorporates current moisture content, rather than averaged values, along with seasonality (both daily and annual), and key climatic factors to predict next step moisture. Model performance is evaluated using R2, MSE, RMSE, and MAPE metrics. Results show that ML algorithms can reliably predict long-term moisture variations in pavements, provided optimal hyperparameters are selected for each algorithm. The best-performing algorithms include KNN (the number of neighbours equals to 15), medium regression tree, medium random forest, coarse SVM, and simple GPR, with medium random forest outperforming the others. The study also identifies the optimal hyperparameter combinations for each algorithm, offering significant advancements in moisture prediction tools for pavement technology.

Resourceful utilisation of tailings waste remains a hotspot in global research. While silica-aluminate-rich copper tailings can serve as raw materials for geopolymer preparation, their high Si/Al ratio significantly limits the geopolymerization degree. This study investigates the feasibility of developing copper tailings-based geopolymers for road base applications, using copper tailings as the primary raw material supplemented with 30 % soft soil, 15 % fly ash, and 5 % cement. The effect of NaOH content on the strength characteristics of copper tailings-based geopolymers was explored by the unconfined compressive strength test and triaxial test. The mineral composition and microstructure of copper tailings-based geopolymers specimens were characterised based on the microscopic technique. The results show that: (1) With the increase of NaOH content, the unconfined compressive strength of the copper tailings base polymer increases and then decreases, and reach the maximum value when the NaOH content is 1 %. Compared with the sample without NaOH, the addition of 1 % NaOH increased the unconfined compressive strength by 47 % at the early stage and 69 % at 28d curing age. (2) An optimal NaOH content significantly improves the shear performance of the copper tailings-based polymer, primarily by enhancing its cohesion. Triaxial test results demonstrate that 1 % NaOH addition increases cohesion by 73 % at 28d curing age. (3) The NaOH promotes the formation of geopolymer gel, refines the pore structure, and increases sample density, thereby enhancing strength. Overall, the research results can provide a reference for the application of copper tailings solid waste in roadbed materials.