Abstract
With the rise in vehicle ownership, traffic congestion has emerged as a major barrier to urban progress, making the study and optimization of urban road capacity exceedingly crucial. The research on the medium and long-term free-flowing capacity and queue emission rate of roads takes an in-depth exploration of this issue from a cutting-edge perspective, aiming to find solutions adaptable to the progression of the times. The purpose of this study is to understand and predict the road capacity and queue emission rate more accurately, thus improving the urban traffic condition. Existing literature primarily focuses on short-term forecasts of road capacity, leaving a notable void in the research of medium and long-term road capacity and queue emission rate. This gap often results in a lack of sufficient foresight when urban traffic planning faces practical issues. To fill this void, this study undertook an in-depth examination of the road capacity and queue emission rate over the medium and long term (10 years) based on big data analysis and artificial intelligence theories. This paper employs a Radial Basis Function (RBF) neural network, combined with twelve other parameters that could potentially impact road capacity, such as traffic volume, road width, number of lanes, traffic signal control methods, etc., to analyze the relationship between each parameter and free-flow traffic and queue emission rate. These analyses are grounded in extensive road data, encompassing not only the city's main roads but also secondary roads and community roads. The study results show a continuous downward trend in the free-flowing capacity of roads and a slight upward trend in the queue emission rate over the past decade. Further analysis reveals the extent of impact each factor has on the free-flow traffic and queue emission rate, providing a scientific basis for future urban traffic planning.