Honggang Wu

In porous media grouting, highly viscous non-Newtonian fluids often trigger viscous fingering (Saffman–Taylor instability) due to adverse mobility ratios, creating fractal-like preferential channels that severely weaken the reinforcement volume. To overcome this, a novel swirl-driven grouting method is proposed. A 2.5D swirl seepage model is established to derive the analytical solution for tangential velocity spatial decay. Integrating the Capillary Bundle and Herschel–Bulkley models elucidates the nonlinear coupling mechanism of centrifugal force and shear-thinning. The swirl flow creates an in situ centrifugal pump, reshaping pressure gradients and triggering a sudden viscosity plunge via extremely high comprehensive shear rates. Furthermore, a modified Saffman–Taylor dispersion relation is constructed and validated via indoor sandbox experiments. Theoretical analysis yields a conditional critical Swirl Number threshold of approximately 0.6 under the tested parameters to suppress the fractal-like evolution of fingering. Experiments demonstrate that exceeding this threshold transitions the grout from preferential seepage to uniform isotropic diffusion. The measured isotropic index is closely enveloped within the 10% theoretical error band. Consequently, the effective projected area experiences a substantial leap of 83.3% due to synergistically enhanced driving forces and reduced medium resistance. This mechanism fundamentally overcomes viscous fingering and suppresses the fractal-like growth tendency of the displacement front, providing a solid theoretical basis for controlling grout diffusion morphology in underground engineering.

Sliding failure is a common form of instability for reverse rock slopes. The determination of the failure plane for such unstable slopes is currently a key and challenging issue in research. To pinpoint the position of the failure surface with higher accuracy, this paper proposes a key equilibrium model based on the symmetric bidirectional evolutionary structural optimization (BESO) method. This model is based on the basic parameters of the slope, the BESO method, and the limit equilibrium theory. It uses its own algorithm program to search and determine the key failure plane of the slope. At the same time, two rock slope model tests were conducted to verify the effectiveness of this method in slope stability analysis. The calculated results exhibit a good consistency with the experimental outcomes, which confirms the feasibility of using the key equilibrium-bidirectional evolutionary structural optimization (CE-BESO) method for stability evaluation of this type of slopes.

Round-ended bridge piers are specifically utilized for high-speed railways in mountainous areas. However, the protective measures for such piers under debris flow remain limited, especially regarding the various components in the debris flow. This study introduces a reinforced concrete (RC) composite structure to improve the debris flow impact resistance of round-ended piers and investigates the impact from three different components of debris flow, including the bulk impact of slurry, collisions of large boulders, and abrasion of rock fragments. The results indicate the following: (1) The RC composite structure effectively mitigated the macroscopic damage from all types of debris flows. This structure significantly decreased gravel accumulation in the front of the pier body and reduced the size of scouring pits. These effects are superior to those of steel casing protection. (2) The RC composite structure significantly reduced the pier top displacement and pier body bending moments and optimized the pressure distribution on the pier body. The peak pressure reduction reached 95.7%, 88.4%, and 97.7% under three different debris flows. These effects were more pronounced than those under steel casing protection, for which the corresponding reductions were 18.2%, 70.9%, and 69.7%. (3) The RC composite structure effectively absorbed impact-induced vibrations and weakened shock effects on the upstream face, exhibiting superior capabilities compared with those of steel casing. The RC composite structure showed particularly outstanding performance in gravel-dominated debris flows. Ultimately, the RC composite structure could be an effective technique for enhancing the resistance of round-ended bridge piers against debris flows.

To address the issues of the insufficient accuracy and weak generalization capabilities of single models in landslide displacement prediction, this paper proposes a machine learning model fusion prediction method for landslide displacement based on stacking. Taking the landslide displacement data (F) and rainfall (RAINFALL) of the Baishui River landslide in the Three Gorges Reservoir area as the research object, input sequences were constructed through data preprocessing and feature engineering. Prediction models including SVR, XGBoost, Bayesian optimization, and random forest were established. Based on the stacking framework, an integrated landslide displacement prediction model was developed by dynamically weighting the outputs of the base models using prediction accuracy and stability as fusion indicators. The Baishui River landslide, a typical colluvial landslide, was selected as a case study, with typical displacement data from monitoring points ZG118 and XD-01 from December 2006 to December 2012. The results show that the evaluation metrics (R², ERMSE, and EMAE) for ZG118 and XD-01 demonstrate satisfactory prediction performance. Compared with traditional single models such as a TCN and XGBoost, the proposed integrated model exhibits improved prediction accuracy, providing scientific support for the real-time monitoring and early warning of landslide hazards.

With the acceleration of urbanization, the demand for construction land has increased sharply. High and steep slope excavation has become an important way to provide construction sites, but its stability is directly related to engineering safety and the surrounding environment. Therefore, the difficulty of how to maintain slope stability during excavation is the focus of our current research. In this paper, based on the high and steep rock slope of a special building in a city in southern China, the PSO-BP (particle swarm optimization-back propagation neural network) algorithm is used to predict the support parameters of the slope, whose safety factor does not meet the requirements. The numerical simulation results show that the safety factor after optimized support is 21.1% higher than that before support, the slope dissipation energy is reduced by 53.1%, the displacement in the direction of zz and xx is reduced by 99.3% and 98. 7%, and the fitting degree between the support parameters predicted by the algorithm and the actual support parameters is good, which shows that the algorithm can provide a scientific and reliable basis for optimizing the slope reinforcement parameters, shortening the time of slope reinforcement design and improving the slope stability.

Accurate prediction of landslide susceptibility is a key component of disaster risk reduction and early warning systems. Traditional landslide susceptibility prediction methods often face challenges in capturing complex nonlinear and spatio-temporal relationships inherent in geospatial data. In this study, we propose a Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Spatial Attention Mechanism (SAM) hybrid deep learning model designed for spatial landslide susceptibility prediction. The model is trained on a comprehensive dataset comprising 19,898 samples, constructed from landslide records and 16 influencing factors in Kumamoto Prefecture, Japan. The input dataset is processed in tabular format using Microsoft Excel and includes variables such as topography, meteorology, soil characteristics, and human activity. The proposed model leverages Convolutional Neural Networks (CNN) to extract spatial features, Long Short-Term Memory networks (LSTM) to model temporal dependencies, and a Spatial Attention Mechanism (SAM) to enhance feature weighting dynamically. Experimental results demonstrate that the CNN–LSTM–SAM–Attention model significantly outperforms traditional machine learning approaches in terms of accuracy, precision, recall, F1 score, ROC–AUC, and PR–AUC. This substantial improvement is attributed to the model’s enhanced capability in capturing complex spatio-temporal patterns and dynamically weighting critical spatial features through the integrated Spatial Attention Mechanism (SAM). This study highlights the potential of deep learning-based approaches for improving the reliability of spatial landslide susceptibility prediction in complex terrain and dynamic climatic conditions.