Hao Yang
Research Subjects
Hao Yang has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Fang Wang
School of Civil Engineering and Hydraulic Engineering, Ningxia University, Yinchuan, Ningxia, People’s Republic of China
2 shared publications - Shixiao Liu
School of Civil Engineering and Hydraulic Engineering, Ningxia University, Yinchuan 750021, China
2 shared publications - Ju Cui
Ningxia Communications Investment Expressway Management Company Limited, Yinchuan 750000, China
1 shared publication - Xin Zhang
Ningxia Communications Investment Expressway Management Company Limited, Yinchuan 750000, China
1 shared publication
Latest Publications
- Open Access
- 24 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8407
Analysis of Anti-Skid Performance of Sand Accumulation Pavement Based on Multi-Scale Experiments
Desert highways have long been subjected to aeolian sand hazards, and sand accumulation on the pavement significantly weakens the surface texture and deteriorates skid resistance, which has become one of the core contributing factors to traffic accidents on desert road sections. Current research predominantly focuses on the attenuation law of the macroscopic friction coefficient of sand-covered pavements; however, the quantitative correlation mechanism between three-dimensional micro-texture characteristics and skid resistance has not been sufficiently revealed, and there is a lack of high-precision skid resistance prediction methods under multi-condition coupling scenarios. To address the above research deficiencies, this paper takes the asphalt pavement in the Tengger Desert region as the research object. A handheld three-dimensional texture scanning system was employed to acquire the three-dimensional pavement morphology parameters under different sand coverages, and the sideway force coefficient (SFC) was synchronously measured under the corresponding conditions. Through Pearson correlation analysis and dual multiple comparison correction using the FDR-BH and Bonferroni methods, the core influencing indicators were identified. Subsequently, a skid resistance prediction model based on a BP neural network optimized by the particle swarm optimization (PSO) algorithm was constructed and horizontally compared and validated with LSTM and PSO-SVM models. The research results show the following: ① under dry conditions, the root mean square height (), peak density (), arithmetic mean peak curvature (), valley void volume (), root mean square slope (), and developed interfacial area ratio () are significantly linearly correlated with the SFC, among which , , , and are the core controlling indicators, with the absolute values of their correlation coefficients all exceeding 0.73, and ② the constructed PSO-BP prediction model achieved a coefficient of determination of 0.86093 on the test set, and its prediction accuracy and generalization ability are both superior to those of the LSTM and PSO-SVM models, enabling it to effectively characterize the nonlinear mapping relationship between multiple texture parameters and skid resistance. This study can provide theoretical support and a technical basis for skid resistance evaluation, sand accumulation disaster warning, and scientific maintenance decision-making for desert highways.- 24 August 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8407
Open AccessAnalysis of Anti-Skid Performance of Sand Accumulation Pavement Based on Multi-Scale Experiments
Desert highways have long been subjected to aeolian sand hazards, and sand accumulation on the pavement significantly weakens the surface texture and deteriorates skid resistance, which has become one of the core contributing factors to traffic accidents on desert road sections. Current research predominantly focuses on the attenuation law of the macroscopic friction coefficient of sand-covered pavements; however, the quantitative correlation mechanism between three-dimensional micro-texture characteristics and skid resistance has not been sufficiently revealed, and there is a lack of high-precision skid resistance prediction methods under multi-condition coupling scenarios. To address the above research deficiencies, this paper takes the asphalt pavement in the Tengger Desert region as the research object. A handheld three-dimensional texture scanning system was employed to acquire the three-dimensional pavement morphology parameters under different sand coverages, and the sideway force coefficient (SFC) was synchronously measured under the corresponding conditions. Through Pearson correlation analysis and dual multiple comparison correction using the FDR-BH and Bonferroni methods, the core influencing indicators were identified. Subsequently, a skid resistance prediction model based on a BP neural network optimized by the particle swarm optimization (PSO) algorithm was constructed and horizontally compared and validated with LSTM and PSO-SVM models. The research results show the following: ① under dry conditions, the root mean square height (), peak density (), arithmetic mean peak curvature (), valley void volume (), root mean square slope (), and developed interfacial area ratio () are significantly linearly correlated with the SFC, among which , , , and are the core controlling indicators, with the absolute values of their correlation coefficients all exceeding 0.73, and ② the constructed PSO-BP prediction model achieved a coefficient of determination of 0.86093 on the test set, and its prediction accuracy and generalization ability are both superior to those of the LSTM and PSO-SVM models, enabling it to effectively characterize the nonlinear mapping relationship between multiple texture parameters and skid resistance. This study can provide theoretical support and a technical basis for skid resistance evaluation, sand accumulation disaster warning, and scientific maintenance decision-making for desert highways. - Open Access
- 13 June 2026
- Published by MDPI AG in Geohazards
- Vol. 7 (2) , 75
Prediction of Rainfall-Induced Slope Stability Spatiotemporal Evolution Based on a Hybrid Transformer–LSTM Deep Learning Framework
Rainfall is a critical factor inducing slope instability, and accurate prediction of the factor of safety (FOS) of slopes under rainfall conditions is of paramount importance for disaster prevention and mitigation. Conventional numerical simulation methods incur high computational costs, while individual machine learning models are often insufficient to adequately capture the nonlinear spatiotemporal evolution characteristics of multiple factors under coupled multi-physics fields. To address these limitations, this paper proposes a Transformer–LSTM prediction framework. First, a fluid–structure coupling model for rainfall-affected slopes is constructed using COMSOL, and multi-factor orthogonal experiments are performed to generate multi-dimensional time-series data. Subsequently, a Transformer–LSTM fusion deep learning model is built, in which LSTM is employed to extract the temporal dynamic characteristics of rainfall infiltration, and the self-attention mechanism of the Transformer is leveraged to enhance feature extraction and global dependency modeling of key disaster-causing factors. Experimental results demonstrate that the Transformer–LSTM model significantly outperforms traditional PSO-LSTM, PSO-SVM, and standalone Transformer or LSTM models in terms of both prediction accuracy and generalization capability. Its coefficient of determination (R2) remains above 0.94, and key evaluation metrics—including mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE)—attain the lowest values among the compared models. Furthermore, the SHAP (SHapley Additive exPlanations) interpretability framework is introduced to quantitatively elucidate the model’s predictive decision-making and to establish a physically grounded causal mapping with geotechnical mechanisms. It is confirmed that effective cohesion and slope angle exert a dominant interactive effect on the degradation of slope stability, providing data-driven support for wide-area monitoring of rainfall-induced landslides.
- 13 June 2026
- Published by MDPI AG in Geohazards
- Vol. 7 (2) , 75
Open AccessPrediction of Rainfall-Induced Slope Stability Spatiotemporal Evolution Based on a Hybrid Transformer–LSTM Deep Learning Framework
Rainfall is a critical factor inducing slope instability, and accurate prediction of the factor of safety (FOS) of slopes under rainfall conditions is of paramount importance for disaster prevention and mitigation. Conventional numerical simulation methods incur high computational costs, while individual machine learning models are often insufficient to adequately capture the nonlinear spatiotemporal evolution characteristics of multiple factors under coupled multi-physics fields. To address these limitations, this paper proposes a Transformer–LSTM prediction framework. First, a fluid–structure coupling model for rainfall-affected slopes is constructed using COMSOL, and multi-factor orthogonal experiments are performed to generate multi-dimensional time-series data. Subsequently, a Transformer–LSTM fusion deep learning model is built, in which LSTM is employed to extract the temporal dynamic characteristics of rainfall infiltration, and the self-attention mechanism of the Transformer is leveraged to enhance feature extraction and global dependency modeling of key disaster-causing factors. Experimental results demonstrate that the Transformer–LSTM model significantly outperforms traditional PSO-LSTM, PSO-SVM, and standalone Transformer or LSTM models in terms of both prediction accuracy and generalization capability. Its coefficient of determination (R2) remains above 0.94, and key evaluation metrics—including mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE)—attain the lowest values among the compared models. Furthermore, the SHAP (SHapley Additive exPlanations) interpretability framework is introduced to quantitatively elucidate the model’s predictive decision-making and to establish a physically grounded causal mapping with geotechnical mechanisms. It is confirmed that effective cohesion and slope angle exert a dominant interactive effect on the degradation of slope stability, providing data-driven support for wide-area monitoring of rainfall-induced landslides.