Analysis of the Superposition Effect of Passenger Flow at New Rail Transit Stations Based on Causal Inference

This paper explores the relationship of walk access distance to rapid rail transit (RRT) stations with personal characteristics and station context, specifically in regard to an operated RRT system in the city of Nanjing, China. Both descriptive analysis and regression analysis on the commuter survey are conducted to reveal the association. Descriptive analysis indicates that the walk access distance in the morning peak is longer than that in the afternoon peak. Young commuters walk farther to access to RRT stations than children and older people. The walk access distance decreases with increasing household income. Regression analysis, in particular, on the association between walk access distance and station context suggests that commuters walk farther to reach a terminal station but walk a shorter distance to arrive at a transfer station than to a typical station. The walk access distance to an elevated station is longer than that to an underground station, and an approximately 100-m distance premium does seem to exist. In addition, the radius of the pedestrian catchment area (PCA) of an underground RRT station is about 200–300 m longer than the PCA of bus rapid transit station. Implications of the present study include defining flexible rail transit station's PCAs in estimating urban rail transit (URT) ridership at the station level, optimizing the house location and price premium analysis around URT stations, and identifying the opportunities for transit-oriented development in the PCA of rail stations.

Towards a collective opinion generation approach with multiple objectives for evaluating rail transit station accessibility in urban areas

Urban rail transit and land use development mutually influence each other, and their coordinated development helps alleviate urban issues such as traffic congestion, which is one of the key aspects of sustainable urban development. Utilizing data in Shenzhen, including the building census data, land use data and rail transit station swipe data in 1999 and 2015, we perform a detailed analysis of the intrinsic relationship between rail transit station capacity and surrounding land use. This analysis covers various indicators such as development intensity, land use information entropy, station type and peak passenger flow during morning and evening. By introducing the "node-place" model, we construct an index system to evaluate the degree of coordination between rail transit stations and land use. The <italic>k</italic>-means clustering method is employed to classify the coordination status as subordinate, balanced and imbalanced states. The results indicate that with the development and construction of rail transit stations, the level of intensive land use around Shenzhen's rail transit stations has increased. There is a significant correlation between the passenger flow of stations and the surrounding land use indicators. All-day passenger flow is significantly positively correlated with the floor area ratio and commercial and office building area; morning peak passenger flow is significantly and positively correlated with residential building area and building density, and negatively correlated with the floor area ratio; while evening peak passenger flow is highly correlated with commercial building area and road network density. Overall, the coordinated development level between rail transit stations and their surrounding land use is relatively low. Station types predominantly fall into a subordinate state with low and balanced development of node and place values, while coordinated types are rare and mainly concentrated in the central area. Future efforts should focus on adopting targeted development strategies for imbalanced node areas to enhance their agglomeration effects and service levels.

The spatial and temporal rules governing passenger flow in urban rail transit (URT) stations are complex, and simulation modeling and analysis of passenger flow distribution in stations are very important in regard to scientifically organizing and controlling passenger flow and improving passenger travel efficiency. With a focus on the multilevel three‐dimensional spatial structure of URT stations and the composition of multiclass passenger flow lines, the travel process and microbehavior of passengers are analyzed here. The goal‐driven behavior of passenger flow groups in the free area and the interaction between them are considered, and a static–dynamic field hybrid model describing the differences in speed between passengers, their walking, and avoidance behavior and a queue field model of queuing behavior are constructed. A selection behavior model for facility nodes such as gates, interlayer facilities, and waiting areas is constructed to represent heterogeneous passenger flow to multiservice channels. A passenger flow simulation method framework for URT stations that takes into account heterogeneous passenger flow, the 3D spatial structure, and multipotential energy field is also established. The effectiveness of the proposed model and method is verified via simulation of Changsha Metro Shumuling Station, and it is found that the proportion of escalators selected as interlayer facilities is significantly higher than that for stairs. After a train leaves the station, the passenger flow density on both sides of the platform reaches more than 1.5 person/m2, significantly higher than that in the central area of the platform. The average passing times for passengers at the exit gate and the ascending escalator are 16–18 and 13–14 s, respectively. The average queue length and passing times for passengers are higher than those at the entrance gate and the descending escalator. These results can provide support for decisions on the actual operation of URT stations.

Urban rail transit is an essential part of the urban public transportation system. The reasonable spatial data visualization of urban rail transit stations can provide a more intuitive way for the majority of travelers to arrange travel plans and find destinations. The map service of rail transit stations generated by data visualization has gradually become indispensable information guidance in the rail transit system. The existing map service icons block each other when the scale changes, and new stations cannot be displayed dynamically when users drag the map. This paper uses filtering and sorting methods to dynamically query and visualize the relatively more important transportation stations within the users’ visible range, so as to solve the above problems and provide people with better transportation services. Our method introduces three constraints: spatial diversity, time-sharing passenger flow analysis and whether it is a transit station, and calculates the scores of constraint relationships of feature objects to evaluate stations. On the basis of the skyline query, the scores of feature objects are combined and sorted to obtain an ordered object set of the most interesting k points(top-k POIs), and the rail transit stations are dynamically retrieved and visualized. Before sorting POIs, we filter out POIs that need to be fitted, so that only the k most representative POIs in the currently visible range are displayed. When the map scale changes, the displayed POIs are updated. Finally, through the statistics of efficiency calculation of this method under different scales and centers, combined with users’ evaluations, it was proved that our method could better display critical information and improve user experience.

The study of exploring the internal connection between rail transit and land use is of great significance for the coordinated development of urban space and rail transit construction, and it is also important for the intensive use of land affected by rail transit stations. The land use structure and population density surrounding the stations of Line 1.2.3 of Xi’an Rail Transit were clustered by SPSS for identifying the rail transit stations with high population density. Subsequently, We have established an indicator system of urban land use and rail transit operation capabilities based on multivariate data, and explored the coordinated relationship between rail transit and land use through data envelopment analysis (DEA) evaluation methods at high population density stations. Besides, the coupling degree of land use in rail transit stations with high population density was evaluated, and the key indicators affecting the coupling degree were further analyzed in Xi’an. In conclusion, this study finds that the relationship between rail transit capacity and land use of high population density rail transit stations is unbalanced. Hence, to promote the sustainable development of rail transit capacity and surrounding land, it is suggested that we should confine the development of land use intensity around the station, improve the service functions of small-scale living areas, and optimize the travel environment intended for short-distance travel. For residents, they are encouraged to choose the mode of rail transit for their long-distance travel. At the same time, the peak passenger flow at the stations should be evacuated accordingly.

The study of short-term passenger flow of rail transit is based on the passenger flow data, usually taking the station as the smallest unit and can only grasp the passenger flow law between stations macroscopically. In order to study the microscopic passenger flow law in different scenes within the station, it is necessary to obtain the passenger flow sequence of the corresponding scene. Therefore, we propose an end-to-end refined short-term passenger flow identification model based on computer vision named PAX-Detect. The structure of the model are as follows: 1). Take pictures of the scene in the station and manually mark the passenger's head; 2). Using annotated datasets to train the YOLOv5 algorithm and pruning optimization;3). YOLOv5 and Deep SORT algorithm are used to detect and track passengers in the video, and the statistical results of the number of passengers are output in real-time. The experiment is carried out on the video data of the escalator entrance of a subway station in Beijing. The experimental results show that the accuracy of the real-time statistical algorithm for passenger numbers reaches 99.4% in the test scenario. The proposed model can identify the microscopic passenger flow in the scene of the rail transit station in real-time and has a certain application prospect.

Mountainous urban rail transit stations exhibit distinct characteristics. To investigate how these features affect passenger flow variations at rail stations, we analyze geographic-environmental data surrounding the stations and integrate road network topology, automatic fare collection data, and point-of-interest (POI) data. We propose a method to classify rail transit stations by considering the mountainous features and establish a multiscale geographically weighted regression (MGWR) model to assess the classification results. This study focuses on 189 rail stations in Chongqing, identifying six station categories: comprehensive mountainous, comprehensive non-mountainous, employment mountainous, employment non-mountainous, residential mountainous, and residential non-mountainous. The MGWR results show that road growth coefficients, average longitudinal slopes, and road lengths significantly influence station performance. For instance, the average longitudinal slope substantially affects employment in mountainous stations, particularly during the morning peak. The analysis reveals that the average longitudinal slope exerts a stronger negative effect on morning peak inbound passenger flow at employment mountainous stations (-0.949), indicating that commuters are more sensitive to travel time during the morning peak. In contrast, the evening peak inbound passenger flow is less impacted (-0.409), suggesting that evening commuters face fewer time constraints. These findings offer strategic insights for zoning transit stations to support transit-oriented development(TOD).

There is a causal interaction between urban rail passenger flow and the station-built environment. Analyzing the implicit relationship can help clarify rail transit operations or improve the land use planning of the station. However, to characterize the built environment around the station area, existing literature generally adopts classification factors in broad categories with strong subjectivity, and the research results are often shown to have case-specific applicability. Taking 154 stations on 8 rail transit lines in Xi’an, China, as an example, this paper uses the data sources of multiple open platforms, such as web map spatial data, mobile phone data, and price data on house purchasing and renting, then combines urban land classification in the China Urban Land Classification and Planning and Construction La1d Standard to classify the land use in the station area using structural hierarchy. On the basis of extracting fine-grained factors of the built environment, a semi-parametric Geographically Weighted Poisson Regression (sGWPR) model is used to analyze the correlation and influence between the variation of passenger flow and environmental factors. The results show that the area of Class II residential land (called R2) is the basis for generating passenger flow demand during morning and evening peak periods; The connection intensity between rail transit station area and bus services has a significant impact on commuters’ utilization level of urban rail transit. Furthermore, two scenarios in practical applications will be provided as guidance according to the research results. This study provides a general analytical framework using urban multi-source data to study the internal relationship and impact between the built environment of urban rail transit stations and passenger flow demand.

Park-and-ride (P&R) and transit-oriented development (TOD) are two major strategies to leverage the high capacity of rail transit systems in urban areas. Both rooted in the station-area land, the two strategies must be reconciled in an integrated planning framework. To this end, a bilevel programming model is proposed to tackle the competitive location issue of P&R and TOD near rail transit stations: the upper level is a 0–1 programming model, simulating governmental land-use decision-making behavior with the objective of maximizing metro patronage and minimizing vehicle kilometers traveled, or minimizing vehicle hours of delay; and the lower level is the multimodal network equilibrium model, simulating travelers’ responses and assigning traffic and passenger flows in the network. The traffic analysis zones containing rail stations are divided into transit station areas and auto-oriented zones. The household residential relocation model, accessibility quantitative model, and generation-distribution joint model are used to describe the complex interactions between transit system and land-use development near rail stations. A hypothetical scenario is designed to quantitatively analyze the impacts of different station-based land-use decisions and parameters of population and employment densities. A real case study is presented to illustrate the implementation of the proposed model.

Accurate and timely passenger flow prediction is important for the successful deployment of rail transit intelligent operation. The Sparrow Search Algorithm (SSA) has been applied to the parameter optimization of a Long-Short-Term Memory (LSTM) model. To solve the inherent weaknesses of SSA, this paper proposes an improved SSA-LSTM model with optimization strategies including Tent Map and Levy Flight to practice the short-term prediction of boarding passenger flow at rail transit stations. Aimed at the passenger flow at four rail transit stations in Nanjing, China, it is found that the day of a week and rainfall are the influencing factors with the highest correlation. On this basis, we apply the proposed SSA-LSTM and four baseline models to realize the short-term prediction, and carry out the prediction experiments with different time granularities. According to the experimental results, the proposed SSA-LSTM model has a more effective performance than the Support Vector Regression (SVR) method, the eXtreme Gradient Boosting (XGBoost) model, the traditional LSTM model, and the improved LSTM model with the Whale Optimization Algorithm (WOA-LSTM) in the passenger flow prediction. In addition, for most stations, the prediction accuracy of the proposed SSA-LSTM model is greater at a larger time granularity, but there are still exceptions.

Based on the rapid development of rail transit, it have a greater hidden danger of congestion and trampling, this paper proposes the construction of an urban rail transit station congestion and trampling warning system based on video detection technology, which uses video detection technology to collect the passenger flow, velocity and density data of the bottleneck channel in rail transit stations, then build and train neural network model to predict the next time passenger flow density combine with the three-parameter relationship of the traffic flow, and use the SPSS software used to fit and analyze the passenger flow parameters. So the limit value of the flow-density polynomial model is predicted by pedestrian flow mutation model and used to realize the definition of the critical passenger flow density model based on the catastrophe theory. On this basis, this article compares the real-time predicted value of passenger flow density to it and get the analysis result, then set the corresponding early warning coefficient, early warning level and early warning measures, so it can truly realize the real-time warning of congestion and trampling in rail transit stations based on passenger flow density prediction.

As residents are more and more inclined to choose rail transportation as their daily travel mode, the status of urban rail transportation is becoming more and more prominent. However, due to the level of passenger flow analysis and prediction accuracy, how to better meet passenger demand and improve operation efficiency has become a key issue to be solved by the operation department. In order to improve operational efficiency and service quality, this paper introduces weather-related data to analyze passenger flow at rail transit stations and develop short-term passenger flow prediction. Taking Beijing urban rail transit passenger flow as an example, cluster analysis and correlation analysis are conducted with corresponding weather data to verify the passenger flow characteristics in line with the actual travel. The long and short-term memory (LSTM) neural network model is selected for short-term passenger flow prediction, and weather data are added as features to improve the prediction accuracy. The results show that the passenger flow data with weather features are better fitted in the prediction, and the more accurate prediction results will play a more effective role for the relevant operation departments to schedule trains and improve the operation efficiency.

With the rapid expansion of urban rail transit, station service quality has become an important issue for improving overall operational efficiency and passenger travel experience. This study focuses on the service quality issues of rail transit stations during peak hours, analyzing factors such as passenger flow congestion, inadequate facility capacity, delayed information dissemination, and security management. Through both quantitative and qualitative analysis, the study identifies weak points in station services and proposes multi-dimensional improvement strategies, including passenger flow diversion, facility optimization, introduction of intelligent devices, and upgrades to the information release system. The research results indicate that implementing these optimization measures can significantly improve station throughput efficiency, reduce passenger waiting times, and enhance the overall passenger travel experience. Furthermore, this study provides valuable experience for other urban rail transit stations and contributes to the sustainable development of rail transit systems.

Integration between bike sharing and rail transit provides users with a more flexible travel pattern in an effort to address the “first/last mile” problem. This study aims to examine the determinants influencing the ridership of station-based bike sharing (SBBS) and free-floating bike sharing (FFBS) at rail transit stations. The empirical analysis is based on user transaction records of two bike sharing systems in Nanjing, China. We first apply the k-means cluster method to classify rail transit stations into five types according to the temporal profiles of bike sharing usage for rail transit access. Later, ordinary least squares (OLS) and partial least squares (PLS) regression models are developed respectively by differentiating SBBS and FFBS. Compared with the OLS models, PLS models could address the issue of multi-collinearity and generally have better interpretation abilities. The PLS results reveal that the usage of SBBS for rail transit access shares similarities with FFBS. For example, both of them are positively influenced by population density and the number of restaurants. Meanwhile, different types of rail transit stations exhibit different impacts on the ridership of the two bike sharing systems. Our results show that there exists a substitution effect for rail transit access between two bike sharing systems, that is, SBBS may be more frequently used for commuting trips than FFBS. The findings of this study provide a better understanding of the impact of various factors on the SBBS and FFBS ridership at rail transit stations, thereby helping to promote the integration of rail transit and bike sharing systems.