Maximum Dry Density (MDD) and Optimum Moisture Content (OMC) are two important parameters of soil filling, which affect the soil stability and bearing capacity, and thus the reliability and durability of facilities such as highways and bridges. Therefore, it is important to make reasonable predictions of OMC and MDD. Four machine learning algorithms, namely, Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF), and Extreme Gradient Boosting Tree (XGBoost), are adopted in this paper to establish MDD and OMC prediction models. After training and testing, the best models of the four algorithms are compared. The results show that, as an ensemble learning algorithm, XGBoost is the best model for predicting MDD and OMC, with an R² of 0.9234 for OMC, and an R² of 0.9098 for MDD. Finally, the feature importance analysis concludes that the plastic limit (PL) and the liquid limit (LL) are the two features that affect OMC and MDD the most. The prediction of soil compaction parameters using machine learning models, especially ensemble learning, can significantly reduce the amount of laboratory work and improve the efficiency of optimizing design for soil resource utilization in engineering construction.

The shear characteristics of the interfaces between soil and concrete structures are essential for the safety of the structures. In this study, a large-scale direct shear test apparatus was developed to measure the mechanical parameters of soil–concrete interfaces under conditions with different soil types, soil moisture contents, and interfacial filling materials. The results showed that the shear stress of the soil–concrete interface increased initially and then became stable with the increase in the shear displacement. The shear displacement of the sandy soil when the shear stress became stable was smaller than that of the clayey soil. The silty sand–concrete interface had a smaller friction angle than the interface with the medium-coarse sand. Moreover, with the increase in the soil moisture content, the friction angle of the clayey soil–concrete interface decreased rapidly, whereas the cohesion first increased and then decreased, and the peak cohesion was near the plastic limit of the soil. Under the same moisture content, the friction angle and cohesion of the clay–concrete interface was reduced by filling the interface with a thin layer of sandy soil, while filling the silty sand–concrete interface with a thin layer of silt reduced the friction angle and increased the interfacial cohesion. Nonetheless, the filling had little impact on the overall shear strength of the interface.

The determination of the compression characteristics of cement-stabilized dredged soil is an important issue. However, conventional method of laboratory compression test is time-consuming. Considering its robustness, random forest (RF) regression algorithm was utilized in this research to predict the compressibility of cement-stabilized dredge soil. The input variables included fundamental physical parameters of uncemented soil, water/cement ratio, and cement content. The output variables were initial void ratio e₀ and compression index C_s at the pre-yield state, which can be used to describe the compression curve. Furthermore, a comparative analysis between the RF and support vector machine (SVM) algorithms was implemented, and variable importance was also evaluated according to the RF model. Results indicate that the RF model could quickly predict C_s and e₀ values of cement-stabilized dredged soil without one-dimensional oedometer tests. The RF algorithm was found to exhibit better performance than the SVM algorithm, and it has a strong ability to avoid over-fitting. The determination coefficient R² for C_s and e₀ on the validation set were found to respectively reach 0.83 and 0.97. Moreover, the importance values of the initial water content, water/cement ratio, and plastic limit were found to be 0.313, 0.249, and 0.117, respectively. The secant compression modulus E_s1−2 obtained from the compression curves could be applied to the calculation of settlement and stress in engineering design.

This study aims to optimize the sustainable utilization of excavated soil by incorporating it exclusively as a fine aggregate and cement in the formulation of soil-based controlled low-strength materials. The polycarboxylate superplasticizer was introduced to enhance flowability. Various factors, including the cement contents, initial water contents, and curing time, were systematically analyzed for their effects on the fresh properties, mechanical parameters, transverse relaxation time distribution, pore size distribution, porosity, and corrosivity of soil-based controlled low-strength materials. The results indicate that polycarboxylate superplasticizer effectively dispersed clay minerals and cement particles, enhancing the flowability. The unconfined compressive strength increased with the rising cement content and decreased with the increasing initial water content. Additionally, the transverse relaxation time distribution curves of the soil-based controlled low-strength materials exhibited two peaks. These curves shifted to smaller transverse relaxation time values with the increasing cement content, while gradually shifting to larger transverse relaxation time values with the increasing initial water content. An increase in the cement content resulted in higher volume percentages of small and mesopores, while extra-large pores and macropores decreased. The addition of the polycarboxylate superplasticizer had minimal impact on the pore volume percentage distribution. Furthermore, porosity experienced a decline with the rise in the cement content and curing time, in contrast to a notable increase with a higher initial water content. This investigation provides valuable insights into the engineering properties and microstructural characteristics of soil-based controlled low-strength materials, offering a foundation for sustainable waste management practices in geotechnical applications.

This study investigates the disposal of textile sludge via laboratory and field tests while protecting the eco‐environment. Solidification/stabilization (S/S) technology and skeleton construction method are introduced to investigate the application of S/S sludge for subgrade material. S/S is to enhance the sludge strength and stabilize the metal(loid)s and hazardous organics in the textile sludge. Skeleton construction method aims to decrease the liquid‐solid ratio in mixture to reduce the binder dosage and save binder cost. In the laboratory, binders and skeleton material are implemented to investigate the differences in unconfined compressive strength (UCS) to explore the optimal mixture. Results illustrate that UCS of binder‐sludge is below 100 kPa and enhanced more than 400 kPa after adding gypsum and skeleton material. Skeleton soil material with high plasticity index and low moisture content improves UCS significantly. Scanning electron microscopy test shows the physical microstructure of sludge is greatly improved for the particular space grid structure formed by the particles and cementitious products. The leaching test shows the metal(loid)s and organics in leachate are decreased after S/S treatment and below the standard value. Finally, the textile sludge was disposed for subgrade via the technology. The strength and leaching results of field tests are in good agreement with the laboratory results. The bearing capacity of the practical subgrade meets the design requirements.