Analyzing the Impacts of Land Use and Network Features on Passenger Flow Distribution at Urban Rail Stations from a Classification Perspective

Round 1

Reviewer 1 Report

General evaluation of the article:

·       Title: Suitable

·       Keywords: Suitable

·       Abstract: Suitable.

·       Itemization: Correct

·       Text: clear and objective

·       This article contains interesting research but its relationship with the topic of Sustainability should be highlighted.

·       References listed in adequate quantity but composed of predominantly Chinese authors. I believe that this predominance should be highlighted and explained by the characteristics analyzed in the article by the authors.

·       Conclusions consistent with discussed logic.

Specific Comments:

The conclusions should be complemented by the analysis of the big data considered and the justification as to whether their uses were considered appropriate by the authors.

Author Response

Responses to Reviewer 1

Dear reviewers,

We extend our heartfelt gratitude for taking the time to review our paper. Your insightful comments have been invaluable in guiding us toward improving the quality of our manuscript.

After thorough consideration of your comments, we have made significant revisions to the manuscript. The careful reflection on your suggestions has indeed enhanced the overall clarity and coherence of our work.

Enclosed with this letter are our detailed responses to each of your comments, along with highlights of the major revisions made in the revised manuscript. We trust that these modifications address the concerns raised and contribute to the suitability of the paper for publication.

We eagerly await your feedback and remain hopeful that the revised paper meets the standards for acceptance.

Sincerely,

Authors

1. This article contains interesting research but its relationship with the topic of Sustainability should be highlighted.

As suggested, we have revised the abstract, introduction, and conclusion sections to highlight the study's contributions to sustainable development more explicitly. We have emphasized how our research aligns with the goal of sustainability by promoting resource-efficient transportation solutions in urban rail transit systems.

1. Abstract section

Original manuscript as follows (lines 27-29):

This study provides a new perspective and method for the refined operational management of urban rail transit, contributing to improved operational efficiency and sustainable development.

Revised as follows (lines 27-30)：

This study offers a novel approach for enhancing the operational management of urban rail transit, which not only boosts operational efficiency but also aligns with the goals of sustainable development by promoting resource-efficient transportation solutions.

1. Introduction section

Original manuscript as follows (lines 47-48):

This aids in reducing the operational costs of urban rail transit, achieving refined operation, and sustainable development.

Revised as follows (lines 27-30)：

This aids in reducing the operational costs of urban rail transit and achieving refined operation, thereby contributing to the broader goals of sustainable development.

Original manuscript as follows (lines 72-73):

Therefore, this study will examine the factors influencing passenger flow distribution at urban rail transit stations from the perspective of station classification.

Revised as follows (lines 76-80)：

Therefore, this study will examine the factors influencing passenger flow distribution at urban rail transit stations from the perspective of station classification. Understanding these factors is crucial for optimizing station management and enhancing service quality, which in turn contributes to the sustainability of urban transportation systems by promoting efficient resource utilization and reducing operational costs.

1. Conclusion section

Original manuscript as follows (lines 587-589):

This research offers targeted operational and management strategies based on the distinct characteristics of station passenger flow distribution, thereby contributing to the optimization and sustainable development of urban rail systems.

Revised as follows (lines 635-639)：

This research offers targeted operational and management strategies based on the distinct characteristics of station passenger flow distribution, thereby contributing to the optimization of urban rail systems. By enhancing efficiency and reducing resource waste, these strategies support the sustainable development of urban transportation networks.

2. References listed in adequate quantity but composed of predominantly Chinese authors. I believe that this predominance should be highlighted and explained by the characteristics analyzed in the article by the authors.

We acknowledge the predominance of Chinese authors in our references and have added more international sources to provide a balanced perspective on the literature. The focus on Chinese authors reflects the study's geographical context and the significant contributions of Chinese scholars in this field. However, we understand the importance of a diverse range of viewpoints and have addressed this in our revised manuscript.

1. Added expression of contributions to Chinese scholars

Original manuscript as follows (lines 49-50):

Research indicates a widespread interest in exploring various facets of rail transit station passenger flow characteristics.

Revised as follows (lines 51-53)：

Research indicates a widespread interest in exploring various facets of rail transit station passenger flow characteristics, particularly in China where the rapid development of rail transit has prompted significant contributions from Chinese scholars in this field.

1. Added and replaced some references

Revised as follows:

25. Xiao, G. N.; Chen, L.; Chen, X. Q.; Jiang, C. M.; Ni, A. N.; Zhang, C. Q.; Zong, F., A hybrid visualization model for knowledge mapping: Scientometrics, SAOM, and SAO. IEEE Transactions on Intelligent Transportation Systems 2023.
26. Cardozo, O. D.; García-Palomares, J. C.; Gutiérrez, J., Application of geographically weighted regression to the direct forecasting of transit ridership at station-level. Applied geography 2012, 34, 548-558.
27. Yue, Y. F.; Chen, J. J.; Feng, T.; Ma, X. W.; Wang, W.; Bai, H., Classification and determinants of high-speed rail stations using multi-source data: A case study in Jiangsu Province, China. Sustainable Cities and Society 2023, 96, 104640.
28. Nagy, V.; Balázs, H., Hidden content of passenger data in public transport. In Procedia Computer Science, 2017; Vol. 109, pp 506-512.
29. Nagy, V.; Horváth, B.; Horváth, R., Land-use zone estimation in public transport planning with data mining. In Transportation Research Procedia 2017; Vol. 27 pp 1050-1057.
30. Jiao, H. Z.; Huang, S. B.; Zhou, Y., Understanding the land use function of station areas based on spatiotemporal similarity in rail transit ridership: A case study in Shanghai, China. Journal of Transport Geography 2023, 109, 103568.

3. The conclusions should be complemented by the analysis of the big data considered and the justification as to whether their uses were considered appropriate by the authors.

In response to your suggestion, we have elaborated on the big data analysis used in our study in the conclusion section. We have justified the appropriateness of our data sources and analytical methods, ensuring that our findings are robust and relevant.

Original manuscript as follows (lines 563-568):

First, by comparing the clustering results using different similarity measurement functions within the K-Means framework, this study demonstrates that selecting an appropriate similarity measure function can effectively improve clustering performance. The research, using the AFC data of the Nanjing Metro system as an example, indicates that the DTW is more suitable for this dataset, yielding superior CH index, DB index, and S_Dbw index results.

Revised as follows (lines 588-596)：

First, this study conducts a comparative analysis of clustering results using different similarity measurement functions within the K-Means framework. The results demonstrate that selecting an appropriate similarity measure function is crucial for enhancing clustering performance. Specifically, when applied to the AFC data of the Nanjing Metro system, the DTW method emerges as the most suitable for this dataset. This is evidenced by its superior performance in terms of the CH index, DB index, and S_Dbw index. These metrics not only evaluate the quality of clustering but also indicate that the time series extracted from AFC data are well-suited for clustering analysis, with the DTW method yielding more optimal results.

Original manuscript as follows (lines 576-581):

Finally, the instance results indicate that the 171 urban rail stations can be classified into four categories based on the distribution characteristics of passenger flow entering and exiting the stations. These categories include "High Traffic Attraction Stations," " Balance Stations," "Suburban Strong Traffic Occurrence Stations," and "Distant Suburban Strong Traffic Occurrence Stations." And based on the differences in passenger flow distribution at stations, targeted operational management strategies were proposed.

Revised as follows (lines 612-629)：

Finally, the analysis of the instance results, supported by comprehensive AFC data and feature analysis derived from POI and rail network data, reveals that the 171 urban rail stations can be classified into four distinct categories based on the distribution characteristics of passenger flow entering and exiting the stations. These categories are: 'High Traffic Attraction Stations,' characterized by a high volume of incoming and outgoing passengers and located in the city's core area with mature land development; 'Balance Stations,' where the incoming and outgoing passenger flow is relatively balanced, typically situated in the peripheral regions surrounding the city's core; 'Suburban Strong Traffic Occurrence Stations,' predominantly located in suburban areas with a strong influx of passengers, featuring residential areas and supporting commercial facilities; and 'Distant Suburban Strong Traffic Occurrence Stations,' which are further away from the city center and exhibit a significant concentration of passenger traffic, primarily surrounded by residential land. The classification is validated by the features calculated from POI and rail network data, demonstrating the rationality of this categorization. Based on the unique passenger flow distribution patterns observed in each category, targeted operational management strategies were proposed to address the specific needs and challenges of each station type, thereby contributing to the efficient utilization of rail station resources and the sustainable development of rail transit.

Reviewer 2 Report

The topic of the paper is interesting, however the same analysis and calculation was done on Hungarian cities back in 2017. There are relevant references, describing the same classifications (Nagy, V. and Horváth, B. and Horváth, R.: Land-use zone estimation in public transport planning with data mining; Nagy, V. and Horváth, B.: Hidden content of passenger data in public transport).

I suggest to check carefully previous works before publishing this one. OR if you see improvment, than show why your work is better/improved in comparison with the previous works.

On the other hand Table 1 is not clear, what is the meaning of "Entry Count" and "Exit Count", please describe it more precise.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

This paper investigates the impact of land use and network features on urban rail station passenger flow distribution based on big data analytics. While the manuscript demonstrates clear organization, it also exhibits several areas for improvement. To consider its acceptance for publication, the authors are encouraged to address the following points:

1. A thorough review of grammar is recommended to rectify numerous observed errors scattered throughout the paper.

2. In the introduction, please elucidate the principal contributions of this paper, articulate the research question, and expound upon the motivations driving this research endeavor.

3. It is suggested to align the legends in certain figures with the terminology employed within the manuscript.

4. The authors are urged to provide detailed discussions on management strategies tailored to the specific characteristics of various types of stations within the discussion section.

5. The manuscript would benefit from the inclusion of additional pertinent references, such as:

Jiao, H., Huang, S., & Zhou, Y. (2023). Understanding the land use function of station areas based on spatiotemporal similarity in rail transit ridership: A case study in Shanghai, China. Journal of Transport Geography, 109, p.103568.

Yue, Y., Chen, J., Feng, T., Ma, X., Wang, W., & Bai, H. (2023). Classification and determinants of high-speed rail stations using multi-source data: A case study in Jiangsu Province, China. Sustainable Cities and Society, 96, p.104640.

Minor mistakes exist, please have a professional proofreading.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Thank you for your answers. All my questions/comments are answered. Thank you.