Research On Mechanism Of Passenger Flow Impact On Urban Rail Transit Stations Based On Spatiotemporal Heterogeneity

With the rapid development of China’s social economy and the continuous acceleration of urbanization,the transportation needs of urban residents have been increasing,leading to an increasingly prominent traffic problem.Faced with current urban transportation issues such as severe road congestion and mismatched supply and demand of public transportation,developing public transportation vigorously has become the optimal choice to alleviate traffic pressure while strengthening urban transportation infrastructure construction.The passenger flow characteristics of urban rail transit stations reflect the travel patterns of urban residents and the urban planning layout.It is particularly important to clarify the functional characteristics of urban rail transit station services,the characteristics of residents’ travel patterns,and the mechanism of the impact of environmental factors.At present,there is a lack of coherence in the research on the classification of urban rail transit stations and the factors affecting passenger flow,and few studies have considered the relationship between station types and passenger flow factors.Furthermore,research on the spatiotemporal mechanism of passenger flow is also lacking.Based on this,this paper proposes a research method for the mechanism of passenger flow based on the classification of rail transit stations.It uses rail transit card-swiping data,land use data,economic and population data,etc.to identify the types of urban rail transit stations and explore the spatiotemporal heterogeneity of the mechanism of passenger flow.Taking the rail transit system in Nanjing as an example,empirical research is conducted to provide scientific reference for the operation and management of rail transit stations.Firstly,based on the data cleaning of the subway card-swiping data,the passenger flow time series data at three different time granularities,15 minutes,30 minutes,and 60 minutes were extracted,and the data was standardized and analyzed by principal component analysis to extract the passenger flow clustering indicators.K-means Model and Gaussian Mixture Model(GMM)clustering models were used to classify urban subway stations,and the advantages and disadvantages of the two clustering algorithms were compared to select the optimal clustering time granularity and model.The results show that the GMM clustering algorithm is more suitable for subway station classification research,and six types of stations were identified: residential-oriented,employment-oriented,mismatched between residence and employment,mismatched and dwell-oriented,mismatched and employment-oriented,and hub tourism-oriented.Secondly,the service range of the subway station was delineated,and the passenger flow influencing factor indicators were extracted based on previous studies and subjected to collinearity testing.Using the station type as the dependent variable,a multi-nominal logit regression model was established to quantitatively analyze the impact mechanism of various influencing factors on different types of stations within the subway station service range.The results show that there is a significant relationship between the land use,population,economy,and other influencing factor variables and different passenger flow patterns of the station,with the residential-oriented station as the control group.Finally,The Geographically Weighted Regression Model(GTWR)was used to analyze the passenger flow impact mechanisms of different types of subway stations and the overall passenger flow.Using the station entrance and exit passenger flow as the dependent variable,the GTWR model was established to analyze the spatiotemporal distribution of regression coefficients.The results show that the GTWR model has a higher fitting accuracy than the OLS(OLS)and GWR(GWR)models,making it more suitable for analyzing passenger flow influencing factors.The GTWR model combines time non-stationarity with spatial features to explore the passenger flow impact mechanism from a spatiotemporal perspective.This paper conducts in-depth research on the classification of subway stations and the impact mechanism of station passenger flow,which can provide a scientific theoretical basis and practical reference for the rational development and updating of urban land,the management of urban subway,and the improvement of urban subway attractiveness。...