The complex topography of China’s Tibetan Plateau mountainous roads, characterized by diverse curve types and frequent traffic accidents, significantly impacts the safety and sustainability of the transportation system. To enhance driving safety on these mountain roads and promote low-carbon, resilient transportation development, this study investigates the mechanisms through which different curve types affect driving safety and proposes optimization strategies based on interpretable machine learning methods. Focusing on three typical curve types in plateau regions, drone high-altitude photography was employed to capture footage of three specific curves along China’s National Highway G318. Oblique photography was utilized to acquire road environment information, from which 11 data indicators were extracted. Subsequently, 8 indicators, including cornering preference and vehicle type, were designated as explanatory variables, the curve type indicator was set as the dependent variable, and the remaining indicators were established as safety assessment indicators. Linear models (logistic regression, ridge regression) and non-linear models (Random Forest, LightGBM, XGBoost) were used to conduct model comparison and factor analysis. Ultimately, three non-linear models were selected, employing an explainability-oriented dynamic ensemble learning strategy (X-DEL) to evaluate the three curve types. The results indicate that non-linear models outperform linear models in terms of accuracy and scene adaptability. The explainability-oriented dynamic ensemble learning strategy (X-DEL) is beneficial for the construction of driving safety models and factor analysis on Tibetan Plateau mountainous roads. Furthermore, the contribution of indicators to driving safety varies across different curve types. This research not only deepens the scientific understanding of safety issues on plateau mountainous roads but, more importantly, its proposed solutions directly contribute to building safer, more efficient, and environmentally friendly transportation systems, thereby providing crucial impetus for sustainable transportation and high-quality regional development in the Tibetan Plateau.

This study proposes a novel vehicle speed prediction model for plateau transportation—CLS-DW Stacking (Constrained Least Squares Dynamic Weighting Model Stacking)—which holds significant implications for the sustainable development of transportation systems in high-altitude regions. Research on sharp-curved roads on mountainous plateaus remains scarce. Compared with plain areas, data acquisition in such regions is constrained by government confidentiality policies, while complex environmental and topographical conditions lead to substantial variations in road alignment and elevation. To address these challenges, this study presents a sustainable data acquisition and construction method: unmanned aerial vehicle (UAV) video data are processed through road image segmentation, trajectory tracking, and three-dimensional modeling to generate multi-source heterogeneous datasets for both single-curve and continuous-curve scenarios. Building upon these datasets, the proposed framework integrates constrained least squares with multiple deep learning methods to achieve accurate traffic flow prediction. Bi-LSTM (Bidirectional Long Short-Term Memory), Informer, and GRU (Gated Recurrent Unit) are employed as base learners, and the loss function is redefined with non-negativity and normalization constraints on the weights. This ensures optimal weight coefficients for each base learner, with the final prediction obtained via weighted summation. The experimental results show that, compared with single deep learning models such as Informer, the proposed model reduces the mean squared error (MSE) by 1.9% on the single curve dataset and by 7.7% on the continuous curve dataset. Furthermore, by combining vehicle speed predictions across different altitude gradients with decision tree-based interpretable analysis, this research provides scientific support for developing altitude-specific and precision-oriented speed limit policies. The outcomes contribute to accident risk reduction, traffic congestion mitigation, and carbon emission reduction, thereby improving road resource utilization efficiency. This work not only fills the research gap in traffic prediction for sharp-curved plateau roads but also supports the construction of green transportation systems and the broader objectives of sustainable development in high-altitude regions.

Mechanical impact during transportation and construction can locally damage protective coatings on steel bridge components and affect their subsequent barrier response. In this study, conventional baseline and modified multilayer coating systems were prepared on Q235B carbon steel and Q355NH weathering steel and subjected to drop-weight impacts of 0.98–2.94 J. Three-dimensional surface characterization, scanning electron microscopy (SEM), and electrochemical impedance spectroscopy (EIS) were combined to evaluate impact-induced geometric damage, surface fracture morphology, and short-term post-impact electrochemical response. The projected damage area generally increased with impact energy, whereas indentation volume and maximum indentation depth exhibited different evolution trends. At 2.94 J, the modified systems exhibited projected damage areas of 22.24 and 22.63 mm², approximately half those of the corresponding baseline systems, while retaining comparatively high indentation volumes. Three-dimensional morphology and SEM observations showed that the baseline systems developed broader lateral deformation and more extensive peripheral surface damage, whereas the modified systems exhibited a smaller lateral extent of the overall impact-affected region. This damage localization therefore reflects reduced lateral spreading rather than a uniformly smaller central indentation. Short-term EIS responses were strongly system-dependent and showed no universal monotonic relationship with impact energy. These results indicate that reduced lateral damage extent does not necessarily imply reduced local deformation or improved electrochemical response, highlighting the need for multidimensional assessment of impact-damaged protective coatings.

Xizang is characterized by high altitude, low air pressure, strong atmospheric transparency, and complex terrain, while sparse ground stations coexist with continuously available remotely sensed data, and systematic studies on SSR bias correction and meteorological influences under plateau conditions remain limited. This study focuses on a short-term spring case at one urban observation site in Lhasa, using observations collected from 4 to 30 April 2025 to investigate the bias correction of remotely sensed surface solar radiation (SSR) and the influence of meteorological factors. Ground observations and Himawari-8 remotely sensed data were first spatially and temporally matched and preprocessed. Spearman correlation analysis was then used to select key input variables. Support vector regression, random forest, XGBoost, and multiple linear regression models were subsequently developed, followed by a Stacking ensemble model for bias correction. Finally, local sensitivity analysis was conducted to examine the local response of the correction model to selected meteorological variables at a representative baseline point. The results showed that the correlation coefficient between remotely sensed SSR and ground-observed SSR was 0.88 ($p<0.001$). The Stacking ensemble model achieved the best performance, with a test set $R^2$ of 0.8796, an MAE of 118.54 W/m², and an RMSE of 152.41 W/m². Local sensitivity analysis showed that a +10 hPa perturbation in air pressure increased the model output by 173.45 W/m², while a +10 °C perturbation in air temperature increased the output by 23.76 W/m². This study provides a reference for improving the accuracy of remotely sensed SSR and for solar resource assessment in plateau regions.