Sustainable Road Infrastructure: Technologies and Assessments

Highways consume a significant amount of electrical energy annually, especially in remote desert regions where the cost of electricity is high. This research explores the utilization of natural resources along desert highways to establish hybrid energy generation systems for service areas. Three service areas along the desert highway in northern Xinjiang, China, serve as case studies. To assess the feasibility of hybrid energy generation systems in these service areas, meteorological data for the three locations were obtained from the NASA platform. The HOMER Pro software was employed for technical, economic, and environmental analyses of the systems. The results indicate the feasibility of Photovoltaic (PV)/Wind/Battery hybrid energy systems in the Huanghuagou, Kelameili, and Wujiaqu service areas. The application of these hybrid energy generation systems across the three service areas could provide 3,349,557 kWh of electrical energy annually for the desert highway. Sensitivity analysis reveals that the Net Present Cost (NPC) and Cost of Energy (COE) values decrease with increasing radiation levels, while NPC shows an increasing trend with growing load demand, and COE exhibits a decreasing trend. Among the three regions, Wujiaqu demonstrates the highest economic viability, with a COE of $0.34/kWh and an NPC of $3,141,641/kWh. Furthermore, Wujiaqu exhibits the lowest environmental impact, with CO₂ emissions of 198,387 kg/yr, SO₂ emissions of 493 kg/yr, and NO_x emissions of 1,711 kg/yr.

With the deepening of the concept of green, low-carbon, and sustainable development, the continuous growth of the ownership of new energy vehicles has led to increasing public concerns about the traffic safety issues of these vehicles. In order to conduct research on the traffic safety of new energy vehicles, three sampling methods, namely, Synthetic Minority Over-sampling Technique (SMOTE), Edited Nearest Neighbours (ENN), and SMOTE-ENN hybrid sampling, were employed, along with cost-sensitive learning, to address the problem of imbalanced data in the UK road traffic accident dataset. Three algorithms, eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost), were selected for modeling work. Lastly, the evaluation criteria used for model selection were primarily based on G-mean, with AUC and accuracy as secondary measures. The TreeSHAP method was applied to explain the interaction mechanism between accident severity and its influencing factors in the constructed models. The results showed that LightGBM had a more stable overall performance and higher computational efficiency. XGBoost demonstrated a balanced combination of computational efficiency and model performance. CatBoost, however, was more time-consuming and showed less stability with different datasets. Studies have found that people using fewer protective means of transportation (bicycles, motorcycles) and vulnerable groups such as pedestrians are susceptible to serious injury and death.