Debris flow susceptibility mapping (DFSM), which has proven to be one of the most effective tools for risk management, faces a variety of problems. To realize the rational use of debris flow sample resources and improve the modeling efficiency, a unified model based on transfer learning was established for cross-regional DFSM. First, samples with 10 features collected from two debris flow-prone areas were separately used to perform factor prediction ability analysis (FPAA) based on the information gain ratio (IGR) method and then develop traditional machine learning models based on random forests (RF). Secondly, two feature matrices representing different areas were projected into a common latent feature space to obtain two new feature matrices. Then, the samples with new features were used together for FPAA and developing a unified machine learning model. Finally, the performance of the models was obtained and compared based on the area under curves (AUC) and some statistical results. All the conditioning factors played different roles in debris flow prediction in the two study areas, based on which two traditional models and a unified model were established. The unified model based on feature transferring realized efficient cross-regional modeling, solved the unconvincing problem of limited sample modeling, and enabled more accurate identification of some debris flow samples.

Volcanic soil is a special soil that is well-known for its distinctive texture, vesicular nature, and particle fragility. The fragility characteristic of volcanic soil is the main factor affecting the foundation stability in road engineering. This study focuses on the mechanical properties and particle crushing characteristics of volcanic soil retrieved from Northeast China. A series of triaxial consolidation and drainage shear tests are performed on volcanic coarse-grained soil (5 mm > d > 0.075 mm) under different initial relative densities and effective confining pressures. Results show the peak friction angle of volcanic soil significantly decreases with the increase of confining pressure. The particle crushing degree of volcanic soil increases with the increase of confining pressure, particle size, and relative density. The relative breakage rate of the same particle size group has a good linear relationship with a fractal dimension. Moreover, for the same particle size, the relationship between plastic work and relative breakage rate can be fitted by a power function, which is not significantly affected by relative density or effective confining pressure. From an engineering view, in addition to increasing the compaction degree of volcanic soil, volcanic soil with fine particles used as a roadbed filler can significantly reduce the deformation of the roadbed and improve the bearing capacity of the foundation.

The lack of reliable negative samples is an important factor limiting the quality of machine learning-based debris flow susceptibility mapping (DFSM). The purpose of this paper is to propose multiple negative-sample acquisition strategies for DFSM considering different sample representation forms. The sample representation forms mainly include a single grid, multi-grid, and watershed unit, and the negative-sample acquisition strategies are based on support vector machine (SVM), spy technique, and isolation forest (IF) methods, respectively. These three strategies can assign a value to all the samples based on different assumptions, and reliable, negative samples can be generated from samples with values below a predefined threshold. Combining different sample representation forms with negative sample acquisition strategies, nine datasets were then involved in random forest (RF) modeling. The receiver operating characteristic (ROC) curves and related statistical results were used to evaluate the models. The results show that the strategy based on the spy technique is suitable for multiple datasets, while the IF-based strategy is well-adapted to the watershed unit datasets. This study can provide more options for improving the quality of datasets in DFSM, which can further improve the performance of machine learning models.

The steel box girder bridge is a structure composed of mutually vertical stiffening ribs (longitudinal ribs and transverse ribs) that carry the loads of vehicles. Since the external loads are usually complex and variable, the rational design of the bridge components is a topic that deserves more attention. The purpose of this study is to explore the optimal range of some of the component design parameters, expecting to reduce costs while ensuring the stress-carrying capacity. A finite element model (FEM) based on ABAQUS was built and the results were verified by laboratory experiments. The varied thicknesses of the bridge deck, diaphragm, and U-rib were explored based on the validated FEM. The simulation results fit well with the experimental results, which proved that the FEM was quite reliable. The stress analysis results demonstrated an optimal range of 18–20 mm for bridge deck thickness, 14–16 mm for diaphragm thickness, and 8–10 mm for U-rib thickness. The present study holds significant reference value for the design and optimization of multiple steel box girder bridge components, which could further provide a theoretical foundation for related research in this field.

In numerical analysis, the pile equivalent calculation method plays a key role in foundation pit calculation results. However, the effect and mechanism of different pile equivalent calculation methods in the foundation pit has remained unclear. To solve this question, based on FLAC3D, four pile equivalent calculation methods were introduced into a typical pile–anchor pit. This research was carried out from the perspective of soil displacement and stress, special points’ stress paths, and the plastic zone. The results revealed that there was a remarkable influence on the calculation results for different pile equivalent calculation methods. Specifically, compared with structural pile elements, displacements near the pile were smaller in solid pile element mode. Moreover, with the increase in excavation depth, stress concentration appeared in the solid pile element mode. The solid support pile with the interface, compared to that without the interface, had less displacement but more stress concentration around the pile, which led the special points’ stress paths around the solid pile to become irregular. Regarding the structural pile elements, it is suggested that both modeling approaches had a similar effect. These findings could help to provide a deeper insight into pile–anchor foundation pit numerical analysis.

The presentation of a constitutive model could help researchers to predict the mechanical behavior of a material, which also contributes to the further generalization of the material. This paper is to explore the tensile constitutive model of engineered cementitious composites (ECCs) reinforced by high-strength steel wire mesh based on experiments and numerical simulations. DIANA was used to simulate the tensile process of the specimens, and experiments were carried out to validate the numerical model. The effect of the ECCs’ tensile strength, reinforcement ratio and specimen size were considered during the specimen design process. The results showed that most of the errors of the simulated values compared to the experimental results were within 5%, which proved that the numerical model was quite accurate. The proposed constitutive model revealed the different roles played by ECCs and high-strength steel wires at different stress stages, and the calculation results were in high agreement with the simulation results, indicating the effectiveness of the constitutive model. The study in this paper could provide an important reference for the popularization and application of ECCs reinforced by high-strength steel wire mesh.