Ronghan Yao

The primary pollutants emitted from mobile sources have become one of the main sources of urban air pollution. In this study, the primary pollutants CO, HC, NOx and PM from mobile sources in Zibo city, China are studied. Firstly, the localized mobile-source pollutant emission factors are corrected using vehicle emission experiments; secondly, multi-source data fusion is performed using road network data, road traffic data, air quality and meteorological data; then, the corrected pollutant emission factors and multi-source data are used to construct a localized emission measurement model and dispersion simulation model, visualize the emission distribution and propose residual concentration correction to accurately obtain the pollutant sharing rate. The results show that the pollutant emission trends are highly coupled with the distribution of urban residents’ working hours. Based on the localized dispersion model used to analyze the pollutant traceability at air monitoring stations, the emission sharing rate of NOx is the largest, and according to the analysis of the changing trend of mobile-source emission sharing rate, the mobile source pollutants in Zibo are mainly influenced by pollutant emissions from road motor vehicles. This study provides data support and a theoretical basis for the management of the transportation industry to carry out exhaust gas control of motor vehicles and non-road mobile machinery and to make decisions related to improving the air environment (delineating the scope of low emission zones).

With the development of the connected autonomous bus, the interactions between the bus and social vehicle during the mandatory lane changing for bus exiting become more diverse and complex. This research investigates the evolutionary dynamics of behavioral decision-making for the bus and social vehicle in different scenarios. The evolutionary game model for the connected autonomous bus and social vehicle is built, as do the human-driven bus and social vehicle, and the connected autonomous bus under different penetration rates and social vehicle. The results of numerical experiments reveal that the connected autonomous bus chooses to change lanes in most instances, and the strategies of the human-driven bus show conservative tendencies. Such tendencies are weakened when the connected autonomous bus and human-driven bus are mixed. As for the social vehicle in different scenarios, the strategies that balance overall traffic safety and efficiency are promoted. This research provides some references for intelligent decision-making of lane changing in urban public transportation.

To predict traffic flow under adverse weather, a hybrid deep learning model concerning adverse weather (DLW-Net) is formulated. The DLW-Net model consists of the target and global analysis parts. For the target analysis part, the spatio-temporal characteristics of traffic flow data are analyzed using the convolutional neural network (CNN), the long short-term memory (LSTM) and gated recurrent unit (GRU) neural networks. For the global analysis part, the variation rules of traffic flow and weather data are extracted using the LSTM model. Additionally, the characteristics of traffic flow under normal and adverse weather are also discussed. The developed model is verified using three cases. The results show that traffic volume and speed would reduce under heavy rain compared to normal weather, however, drizzle has little impact on traffic flow patterns; the rules of traffic speed data are disturbed by strong wind; and the DLW-Net model performs best under all the conditions.

Three hybrid deep spatio-temporal models are proposed to accurately predict traffic flow under normal conditions, on holidays and under adverse weather. Each of the proposed models consists of the global and target parts, and fuses the weather and traffic flow data obtained from the target and upstream sections. The convolutional neural network (CNN), and the gated recurrent unit (GRU) and convolutional long short-term memory (ConvLSTM) neural networks are selected to analyze the spatio-temporal characteristics of traffic flow data. Then, the three proposed models are verified using three actual cases, including traffic flow prediction under normal conditions, on holidays and under adverse weather. Moreover, the characteristics of traffic flow data on the Independence Day and Thanksgiving Day are discussed, as do the patterns of traffic flow data under heavy rain and strong wind. The experimental results show that: the three new models usually perform better than the existing models under all the situations; different holidays and different types of adverse weather have various impacts on the characteristics of traffic volume and speed data.

To improve public transportation operations, this research investigates the lane-changing behaviors for buses exiting at bus bay stops. Game theory is utilized to analyze the interactions between bus and social vehicle drivers. A two-player noncooperative, non-zero-sum mixed-strategy game model is formulated to consider the time saving and collision avoidance payoffs for both players in the game. The characteristic of mass passengers carried by buses is also taken into account in the payoffs. The maximum likelihood estimation is used to calibrate the formulated model using the vehicle trajectory data collected from Lvboqiao bus bay stop, Dalian, China. The validation results reveal that the formulated model can effectively predict the lane-changing decisions with a high level of accuracy. Besides mixed strategies, the players in the game may have dominant strategies, which are the best choices that have nothing to do with the strategies that other players may adopt. In both mixed and dominant strategies, bus drivers are more inclined to choose the strategy of not changing a lane, and social vehicle drivers tend to choose the strategy of not giving way to the bus. The tendencies to choose strategies by both players are consistent with the actual decisions made by drivers. It is proven that the formulated game model is highly reliable to describe bus drivers’ exiting behaviors at bus bay stops and can offer the decent theoretical support for both players to make better decisions.

Housing price is one of the most popular topics in urban studies. Among all the determinants of housing price, transportation accessibility is an essential factor that people often consider when purchasing a house. Using a semilogarithmic hedonic price model, this paper discusses the effects of structural attributes and accessibility of neighboring destinations on housing prices. The study area targets the core urban area of Dalian city, China. The data used in this study consist of sales prices of commercial apartments and houses and the geographic coordinates of corresponding residential areas. Estimation results of the hedonic price model show that structural attributes and accessibility to neighboring destinations significantly affect housing prices. The most influential factors to housing prices are the location of apartment or house, the nearby quality of higher education resources, and proximity to public transit service. These findings are significant for real estate developers, urban planners, and transportation planners to better understand the real estate market and to promote transit-oriented development.

Short-term traffic flow prediction is very important and provides the basic data for traffic management and route guidance. The rules of traffic flow data during different periods in a day are different. Thus, this paper proposes a membership degree-based Markov (MM) model and two period division-based Markov (PM and PW) models. The MM model introduces the membership degree to determine the state of traffic flow. The PM and PW models introduce the Fisher optimal division method to divide one day into several periods based on traffic flow data. Then, the period division-based Markov models integrate the Markov (CM) or weighted Markov (WM) model with the MM model to predict traffic volumes during different periods. The impacts of vehicle type on traffic flow prediction are also discussed. The proposed models are verified using the field data. The results show that: (1) the PM and PW models both perform better than the CM, WM, state membership degree-based Markov and weighted state membership degree-based Markov models; (2) the PW model sometimes performs better than the backward propagation (BP) neural network; (3) when traffic flow data are distinguished by vehicle type, the performance of the PM and PW models can be improved. It is suggested to adopt the proposed period division-based Markov models to predict traffic flow with the concern of vehicle type, so that more accurate traffic flow information can be provided for traffic management and route guidance.