No abstract

The accessibility of rail transit station areas is an important factor affecting the efficiency of rail transit. Taking the Beijing rail transit station area as our research object, this paper took a 15 min walking distance as the index of station area accessibility, and investigated the status quo and influencing factors of the unbalanced distribution of rail transit station area accessibility in Beijing. In this paper, the data of Beijing rail transit stations were obtained from the Amap open platform, and the accessibility of the station area was calculated using the path planning service provided by the Amap API. The Getis–Ord Gi* method was used to analyze the overall distribution characteristics of the accessibility of the Beijing rail transit station area, then the high accessibility area and the low accessibility area were determined. To explore the factors influencing domain accessibility, multi-source data were obtained, a total of 11 indicators were constructed, and the random forest model was used to identify feature importance. Using the eight selected influencing factors, the OLS regression model, GWR model, and MGWR model were used to study the spatial heterogeneity of influencing factors. By comparison, it was concluded that the MGWR model can not only effectively analyze the spatial heterogeneity of rail transit station accessibility, which can automatically mediate the bandwidth of different influencing factors, and then reflect the spatial changes of the influencing factors of rail transit station accessibility more truly. The results show that (1) the accessibility of the Beijing rail transit station area shows obvious spatial agglomeration characteristics in space. The accessibility of the station area in the fourth ring is higher than that outside of the fourth ring road, and the accessibility near the south and north fifth ring road is higher than that of the east fifth ring road and the west fifth ring road. (2) The basic influencing factors of rail transit station accessibility include road density and functional mixing degree.

Accessibility is an important index for evaluating the efficiency of rail stations. In view of the imbalance between the supply and demand of rail station settings and population distribution, this paper takes the Shijingshan District in Beijing as an example. Based on the Gaussian two-step floating catchment area method and Gaode map’s service interface, the accessibility of rail stations is simulated and analyzed in terms of both walking and riding. Combined with the calculation results, supply and demand relationship and trip time, the current characteristics and causes are analyzed, and the corresponding optimization suggestions are put forward. The main conclusions are as follows: (1) The accessibility distribution of rail stations in the Shijingshan District is relatively coordinated with the population distribution. The effectiveness of the accessibility assessment of rail stations can be further improved by improving the causal evaluation model with traditional calculation data; (2) The change of trip mode has a small impact on the accessibility of large stations, while small stations and areas with uneven station distribution can be improved by riding; (3) According to the K-value clustering method, the results of the two calculation methods are divided into five categories, and each category of demand units has different accessibility characteristics and causes; (4) Comprehensive accessibility is positively correlated with road density and population density.

The outbreak of COVID-19 in Beijing has been sporadic since the beginning of 2022 and has become increasingly severe since October. In China’s policy of insisting on dynamic clearance, fine-grained management has become the focus of current epidemic prevention and control. In this paper, we conduct a refined COVID-19 risk prediction and identification of its influencing factors in Beijing based on neighborhood-scale spatial statistical units. We obtained geographic coordinate data of COVID-19 cases in Beijing and quantified them into risk indices of each statistical unit. Additionally, spatial autocorrelation was used to analyze the epidemic risk clustering characteristics. With the multi-source data, 20 influencing elements were constructed, and their spatial heterogeneity was explored by screening 8 for Multiscale Geographically weighted regression (MGWR) model analysis. Finally, a neural network classification model was used to predict the risk of COVID-19 within the sixth ring of Beijing. The MGWR model and the neural network classification model showed good performance: the R2 of the MGWR model was 0.770, and the accuracy of the neural network classification model was 0.852. The results of this study show that: (1) COVID-19 risk is uneven, with the highest clustering within the Fifth Ring Road of Beijing; (2) The results of the MGWR model show that population structure, population density, road density, residential area density, and living service facility density have significant spatial heterogeneity on COVID-19 risk; and (3) The prediction results show a high COVID-19 risk, with the most severe risk being in the eastern, southeastern and southern regions. It should be noted that the prediction results are highly consistent with the current epidemic situation in Shijingshan District, Beijing, and can provide a strong reference for fine-grained epidemic prevention and control in Beijing.