Accurate traffic speed forecasting not only can help traffic management departments make better judgments and improve the efficacy of road monitoring but also can help drivers plan their driving routes and arrive safely and smoothly at their destination. This paper focuses on the lack of traffic speed data and proposes a method for traffic speed forecasting based on the multitemporal traffic flow volume of the previous and later moment states. First, according to traffic flow volume data, the different traffic patterns of previous and later moment states were extracted. Second, the performance of five forecasting models, namely, long short-term memory (LSTM), backpropagation (BP), classification and regression trees, k-nearest neighbor, and support vector regression, were compared. Finally, the model with the best prediction results was used to conduct sensitivity analysis experiments for different traffic patterns. Through a real-data case study, we found that the LSTM model has the highest prediction accuracy compared to other models in both time and space. This traffic pattern “previous = 3 and later = 3” can forecast traffic speed more accurately, and its forecasting ability is robust across a range of scenarios.

Intersections are the bottlenecks of the road network. The capacity of signalized intersections restricts the operation of the road network. Dynamic estimation of capacity is necessary for signalized intersections refined management. With the development of technology, more and more detectors were installed near the intersection. It had been the information-rich environment, which provided support for dynamic estimation of capacity. A dynamic estimation method for a saturation flow rate based on a neural network was developed. It would grasp the dynamic change of saturation flow rates and influencing factors. The measure data at three scenarios (through lanes, shared right-turn and through lanes, shared left-turn and through lanes) of signalized intersections in Beijing were taken as examples to validate the proposed method. Firstly, the traffic flow characteristics of the three scenarios and factors affecting the saturation flow rate were analyzed. Secondly, neural network models of the three scenarios were established. Then the hyperparameters of neural network models were determined. After training, the neural network structure and parameters were saved. Lastly, the test set data was validated by the training model. At the same time, the proposed method was compared with the Highway Capacity Manual (HCM) method and the statistical regression method. The results show that both regression models and neural network models have better accuracy than HCM models. In a simple scenario, the neural network models are not much different from the regression models. With the increase of complexity of scenarios, the advantages of neural network models are highlighted. In through-left lane and through-right lane scenarios, the estimated saturation flow rates used by the proposed method were 7.02%, 4.70%, respectively. In the complexity of traffic scenarios, the proposed method can estimate the saturation flow rate accurately and timely. The results could be used for signal control schemes optimizing and operation managing at signalized intersections subtly.

Understanding how land use affects urban rail transit (URT) ridership is essential for facilitating URT usage. While previous studies have explored the way that land use impacts URT ridership, few have figured out how this impact evolves over time. Utilizing URT turnstile and land use data in Beijing, we employed panel data analysis methods to verify the existence of the temporal heterogeneity of the impact and capture this temporal heterogeneity. The results identified time-varying impacts of land use on the URT boarding and alighting trips on weekdays and non-weekdays and also demonstrated the rationality of the mixed effects time-varying coefficient panel data (TVC-P) model in capturing this temporal heterogeneity accurately. The TVC-P model revealed how land use density appealed to URT commuting during weekday morning peak times, and how it triggered the generation of URT commutes during the weekday evening rush hours. The land use diversity promoted URT trips over an extended period on non-weekdays. Additionally, the study identified the time-varying impacts of specific land use on URT ridership. These insights provide both theoretical and empirical support for developing policies and actions that improve the efficiency of transportation systems and foster alignment between land use and transport.

Lane imbalance does not provide sufficient space for merging vehicles to adjust their speed and change lanes smoothly. This leads to improper driving behavior that disrupts mainline traffic flow stability, resulting in capacity drops and increased vehicle emissions. However, quantitative analyses, specifically the effects of lane imbalance on capacity and emissions, remain limited. Existing traffic simulation platforms struggle to capture the effects of geometric design changes on capacity. To address these gaps, we developed a simulation method incorporating interactions between geometric design and traffic flow demand into an XGBoost model, enhancing the predictive accuracy for driving behavior parameters. Implemented within the TESS NG platform, this model enables real-time adjustments in driving behavior parameters as traffic demand varies under different lane balance conditions. The simulation results indicated a 42.4% capacity drop and a 34.9% increase in CO₂ emissions when the balanced merging area was shifted to lane imbalance. Conversely, shifting to lane balance increases capacity by 8.2% and reduces CO₂ emissions by 39.8% under severe congestion conditions. Under lane imbalance, vehicle speeds are lower across all traffic demand levels. When the demand exceeds 1300 pcu/h/ln, lane changes occur closer to the end of the acceleration lane, with higher speed differentials. These insights underscore the potential of lane balance optimization to mitigate capacity drops and emissions, providing a valuable simulation approach for the design and evaluation of merging areas.