Sustainable transportation emission reduction through intelligent transportation systems: Mitigation drivers, and temporal trends
Environmental Impact Assessment Review, 2024年12月07日
本研究基于融合机器学习排放模型与真实轨迹数据，采用K-Means聚类分析驾驶行为。结果表明，ITSGS可减少CO2 6.09%-9.24%、NOx 11.39%-18.17%，且在市中心和非高峰时段效果更优。
Abstract
Intelligent Transportation Speed Guidance Systems (ITSGS) represent a burgeoning solution for sustainable emissions reduction. However, the absence of comprehensive environmental benefits assessment has impeded its advancement. This study analyzes how ITSGS achieves based on spatio-temporal data analysis. A fusion machine learning-based emission models and extensive real-world trajectory is utilized to quantify emissions. The K-Means clustering algorithm employed identify driving behavior. results show that by improving behavior, can achieve reductions 6.09 % 9.24 CO 2 , 11.39 18.17 NOx 11.48 18.04 co, 3.84 8.09 THC. At same time, Furthermore, consistently delivers significant across all time periods, with most notable improvements occurring during off-peak hours. It also significantly reduces pollutant in urban centers high travel demand. Projections suggest from 2025 2035, will help China cumulatively avoid approximately 0.30 million tons 3.31 0.31 THC light-duty passenger gasoline vehicles. instills confidence transportation stakeholders continue contribute green, low-carbon transportation.