Research on the Factors Influencing the Spatial Quality of High-Density Urban Streets: A Framework Using Deep Learning, Street Scene Images, and Principal Component Analysis

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Abstract

1. Highlight Research Gaps: Emphasize the current research gaps, such as the lack of focus on high-density urban streets and the limited use of advanced techniques like deep learning and street scene image analysis.
2. Justify Study's Necessity: Emphasize the importance of spatial quality in high-density urban streets for improving urban residents' quality of life.
3. Summarize Main Findings: Clearly summarize the main conclusions, specifying which factors significantly influence spatial quality.

Introduction

1. Global Context and Relevance: In the first paragraph (lines 27-37), shift the focus from technical advancements to the broader global context. Emphasize how this research contributes to global issues like urban equity and high-quality urban development.
2. Clarify Perspective and Framework: Explain the perspective through which the current research framework was established and how the chosen methods align with this perspective.
3. State Research Questions: Clearly state the research questions within the introduction.

Research Framework

1. Integrate Theoretical Foundations: Adjust the framework to include theoretical foundations, goals, and perspectives. Reference studies like those using the case of  Suzhou that published in IJGI on urban vitality, and social-spatial equity in Suzhou in Land.

Figures

        Detail Figure 7 Components: Provide specific explanations for the six                 components (y1-y5) mentioned in Figure 7.

Spatial Quality Evaluation Criteria

1. Clarify Evaluation Standards, Introduce Dependent Variables for Spatial Quality: Address the major concern regarding the absence of a clear dependent variable for spatial quality. Incorporate measures such as crowd density, social perceptions, or subjective survey data to provide a more comprehensive evaluation.
2. Reassess PCA Methodology: Reevaluate the use of principal component analysis, ensuring it is appropriately justified and integrated with other evaluation methods to strengthen the study’s contributions. Discuss the Controversy Around PCA: Acknowledge the controversies surrounding using PCA and explain how your study addresses these concerns. Provide a rationale for its inclusion in the research methodology.

By incorporating these elements, you can provide a clearer and more comprehensive framework for evaluating spatial quality, thereby addressing the reviewers' concerns and enhancing the perceived value of your study.

Author Response

Reply to the Referee

 

Abstract

1. Highlight Research Gaps: Emphasize the current research gaps, such as the lack of focus on high-density urban streets and the limited use of advanced techniques like deep learning and street scene image analysis.

We sincerely appreciate the valuable opinions and suggestions you have provided. The research gaps you pointed out do indeed exist in the current literature, and the direction of modification you suggested is of significant guidance for the abstract part of our paper.

Following your recommendations, we have made corresponding revisions to the abstract section to more clearly point out the limitations of existing research and to highlight the innovation of our study. For details, please refer to lines 11 to 13, the revised content is as follows: The application of advanced technologies, such as deep learning combined with street view image analysis, has certain limitations, especially in the context of high-density urban streets.

We believe that these revisions not only respond to your comments but also enhance the academic quality and depth of the paper. We look forward to your further guidance and thank you for your support of this research.

 

2.Justify Study's Necessity: Emphasize the importance of spatial quality in high-density urban streets for improving urban residents' quality of life.

We appreciate the suggestions you have provided, as they are crucial for enhancing the quality of our paper.

We acknowledge the necessity of emphasizing the importance of street space quality in high-density cities for improving the quality of life for urban residents. Following your guidance, we have made the following revisions to the abstract section: Urban space constitutes a complex system, the quality of which directly impacts the quality of life for residents. In high-density cities, factors such as green coverage in street spaces, color richness, and accessibility to services are crucial elements affecting daily life. For details, please refer to lines 9 to 11.

We believe that these modifications have made the abstract section more clearly express the necessity of our research and highlighted the potential contribution of the study to improving the quality of life for urban residents. We look forward to your feedback and thank you for your support of our work.

 

3.Summarize Main Findings: Clearly summarize the main conclusions, specifying which factors significantly influence spatial quality.

In response to your valuable suggestions, we have conducted an in-depth revision of the abstract to more clearly summarize our main findings and identify the factors that significantly affect spatial quality.

The following is the revised content of the abstract section as per your instructions, from lines 19 to 26: The findings reveal significant variations in service-related indicators such as DLS, ALS, DCE, and MFD, reflecting the uneven distribution of service facilities. The Green Coverage Index and Color Richness Index, along with other service-related indicators, are notably influenced by tourism and commercial activities. Correlation analysis indicates the presence of land use conflicts between green spaces and service facilities in high-density urban settings. Principal Component Analysis uncovers the diversity and complexity of the indicators, with cluster analysis categorizing them into four distinct groups, representing different combinations of spatial quality characteristics.

We appreciate your suggestions and believe these revisions make our research results and conclusions more explicit and persuasive. We look forward to your further feedback.

 

Introduction

4.Global Context and Relevance: In the first paragraph (lines 27-37), shift the focus from technical advancements to the broader global context. Emphasize how this research contributes to global issues like urban equity and high-quality urban development.

We extend our sincere gratitude for the suggestions you have offered, which are crucial for enhancing the depth and breadth of our paper.

Following your feedback, we have made significant revisions to the introduction section to better reflect the global relevance of our research and emphasize its contributions to urban equity and high-quality urban development. Here are the modifications we made according to your instructions, corresponding to lines 35 to 42 and 63 to 72: As globalization continues to deepen and the process of urbanization accelerates, urban spatial quality has become a key indicator for measuring the level of urban development and the quality of life for residents (Li et al., 2016; Long & Liu, 2017). The complexity of urban spatial systems and their impact on residents' daily lives are becoming increasingly prominent (Ye et al., 2019), especially in high-density urban environments, how to achieve spatial equity and high-quality development has become a global challenge.

The recent prevalence of street view data platforms, such as Baidu Street View and Google Street View, has enabled the expedited collection of high-fidelity street imagery (Ye & Dai, 2017; Long & Liu, 2017). These data have been instrumental in studies on street safety (Naik et al., 2014), the degree of street greening (Chen et al., 2024; Jiang et al., 2017; Li et al., 2015), and the spatial quality of urban streets (Shen et al., 2017). Nonetheless, the utilization of big data and novel technologies presents certain issues, including the complexity of urban metrics and a potential disregard for human-centric perspectives. For instance, an overreliance on satellite imagery from an aerial perspective may not consistently correspond with the lived experiences of citizens, especially in terms of green space perception (Jiang et al., 2017).

We believe that these revisions not only address your suggestions but also align our study more closely with the pressing issues of current global urban development. We look forward to your further feedback and appreciate your support for our work.

 

5.Clarify Perspective and Framework: Explain the perspective through which the current research framework was established and how the chosen methods align with this perspective.

We appreciate the suggestions you have made, as they are of significant importance for enhancing the clarity and depth of our paper.

Following your advice, we have made substantial revisions to the introduction section to more clearly articulate the perspective of our research framework and the alignment of our chosen methods with this perspective. Here are the modifications we made according to your instructions, corresponding to lines 73 to 90: In the field of urban spatial system research, the consideration of numerous indicators is essential for a comprehensive assessment of urban space quality. However, previous studies have often relied on multivariate analysis methods, which not only amplify the complexity of the analysis but also struggle to address the intercorrelations among variables, especially within the context of high-density urban environments where such complexities are particularly pronounced. Therefore, this study is dedicated to identifying key indicators with significant impacts on urban space quality and employs dimensionality reduction techniques to streamline the model while retaining vital information, thereby tackling this research challenge. Against this backdrop, the indicators of street quality have become the central constructs of our research, focusing not only on the weight of each indicator but also delving into their variability and interrelationships.

The study employs deep learning and street view image analysis technologies to construct a high-precision, multidimensional evaluation framework. It aims to extract and quantify key spatial quality indicators from a vast array of street view image data. Utilizing methods such as Principal Component Analysis (PCA), semantic segmentation, and cluster analysis, this study seeks to uncover the critical factors influencing street space quality and their intrinsic connections.

We believe that these revisions have made our research framework and methodological choices clearer and more justified. We look forward to your further feedback and thank you for your support of our work.

 

6.State Research Questions: Clearly state the research questions within the introduction.

Thank you for your valuable comments; we completely agree that clearly stating the research question is an essential component of writing a scientific paper.

Based on your suggestions, we have further clarified our research questions and objectives in the introduction section, specifically from lines 90 to 95, and in the research gap section, from lines 243 to 278. Here is the revised content:

On this foundation, we pose a central research question: How can multiple key factors be synthesized in the context of high-density urban environments to optimize street space quality, thereby achieving coordinated urban development and enhancement of spatial quality? This question is pivotal for guiding urban planning and design, as well as for improving the quality of life for residents.

We believe that these modifications not only address your recommendations but also enhance the focus and depth of our paper. We look forward to your continued feedback and appreciate your ongoing support for our research.

 

Research Framework

7.Integrate Theoretical Foundations: Adjust the framework to include theoretical foundations, goals, and perspectives. Reference studies like those using the case of  Suzhou that published in IJGI on urban vitality, and social-spatial equity in Suzhou in Land.

Thank you for your suggestions, which we strongly agree are crucial for integrating the theoretical foundations, objectives, and perspectives within our research framework. Following your feedback, we have made corresponding adjustments to our paper, particularly in the introduction, conclusion, the research framework in Figure 2, and the research steps in Figure 4, to ensure that our study is more firmly grounded in theoretical foundations and engages in a thorough dialogue with prior research. Here are the modifications we have made:

We have clarified the theoretical basis of this study, referencing the research on urban vitality published by Chen et al. (2022) in the International Journal of Geographical Information Science (IJGI), as well as the study on social-spatial equity in Suzhou published in the journal Land. These studies have provided us with valuable theoretical perspectives and empirical cases, aiding in the construction of our research framework and guiding our methodological choices.

In the conclusion section, we have conducted an in-depth discussion from lines 817 to 823, further engaging in dialogue with the research by Chen et al. (2022). We discussed how this study relates to existing literature and reflected on its contributions to urban regeneration, community vitality enhancement, and spatial equity. The revised content is as follows: Furthermore, this study timely considers the community scale at the micro level, building upon the research findings of Chen et al. (2022). It integrates the "3D" theoretical perspective with urban morphology and people-oriented, environmentally friendly principles to assess and verify the quality and vitality of urban spaces. This approach is essential for formulating effective urban policies and interventions that can enhance community vitality and contribute to the sustainable development of urban areas.

We believe that these revisions have made our research more academically rigorous and have also broadened its depth and scope. We look forward to your further feedback and thank you for your continued support of our work.

 

8.Figures Detail Figure 7 Components: Provide specific explanations for the six components (y1-y5) mentioned in Figure 7.

Thank you for requesting a detailed explanation of the figures, which provides us with the opportunity to further clarify our results and enhance the clarity and accuracy of the paper.

Following your suggestion, we have provided specific explanations for the six principal components (y1-y5) depicted in Figure 7 in the discussion section, from lines 688 to 698. Here is the revised content: To provide a clear visual representation of the principal components (y1-y5) and the composite score (z) of street spatial quality, the scores of these six dimensions were mapped using ArcGIS, with particular focus on several representative streets in the Macau Peninsula as illustrated in Figure 10. The values for the first principal component (y1) range from 0.65 to 3.40; for the second principal component (y2), they range from -2.38 to 1.13; for the third principal component (y3), the range is -0.06 to 2.01; for the fourth principal component (y4), the values are between -1.21 and 1.64; and for the fifth principal component (y5), the scores fall between -1.35 and 2.27. The composite score (z) is visualized with a range from -0.84 to 1.34, which is found to be largely consistent with the bar chart presented in Figure 6.

We believe that through these detailed explanations and the specification of data ranges, readers will gain a better understanding of the aspects of urban spatial quality that each principal component represents and clearly see how they integrate into a composite score reflecting the overall spatial quality. We look forward to your further feedback and appreciate your ongoing support for our research.

 

Spatial Quality Evaluation Criteria

9.Clarify Evaluation Standards, Introduce Dependent Variables for Spatial Quality: Address the major concern regarding the absence of a clear dependent variable for spatial quality. Incorporate measures such as crowd density, social perceptions, or subjective survey data to provide a more comprehensive evaluation.

We express our sincere gratitude for the valuable suggestions you have offered. Your insights are crucial for enhancing the rigor and comprehensiveness of our research. In response to your concerns about the unclear dependent variables for spatial quality, we have given serious consideration to the issues you raised, such as urban green space equity, high-quality urban development, people-oriented and environmentally friendly approaches.

However, in our research process, we found that there are numerous indicators to consider in the study of urban spatial systems. In previous studies on urban spatial quality, most scholars have used multivariate analysis methods. In reality, too many variables often increase the difficulty and complexity of the analysis, and in many practical issues, there is a certain correlation between multiple variables. Selecting indicators with significant meaning for the research topic and reducing the dimensions of these indicators is an important and challenging aspect of the study. Therefore, urban spatial research aims to retain as much information as possible from the original variables using fewer variables. Hence, in the study of street quality, the indicators of street quality are an important consideration. That is to say, in the related research on street spatial quality, not only is the weight of the indicators a key research variable, but it is also necessary to reveal the variability of different indicators and their interrelationships, especially in the complex system research of high-density cities.

We recognize that the assessment of urban spatial quality is a multidimensional issue that requires a comprehensive consideration of various factors. Therefore, the main purpose of this study is to delve into multiple indicators of street spatial quality in high-density cities, revealing their variability and interrelationships. We will introduce more dependent variables in our future research to enhance the depth and breadth of our study.

We thank you again for your suggestions and look forward to your further guidance and feedback.

 

10. Reassess PCA Methodology: Reevaluate the use of principal component analysis, ensuring it is appropriately justified and integrated with other evaluation methods to strengthen the study’s contributions. Discuss the Controversy Around PCA: Acknowledge the controversies surrounding using PCA and explain how your study addresses these concerns. Provide a rationale for its inclusion in the research methodology.

We sincerely appreciate the suggestions you have provided, as they are crucial to our research. In light of your feedback, we have re-evaluated our research methodology, particularly regarding the use of Principal Component Analysis (PCA). The detailed revisions are as follows:

This study primarily employs Principal Component Analysis (PCA) for the dimensionality reduction of multiple street quality indicators. While the key techniques of PCA have yielded anticipated outcomes, several debates persist. For instance, PCA necessitates data standardization to ensure equitable contribution of each variable to the analysis. However, some researchers contend that improper standardization may lead to misleading conclusions (Abdi & Williams, 2010). In this research, we utilized the Z-score standardization method, ensuring all variables are compared on a uniform scale, thereby mitigating biases arising from differing units of measurement. Secondly, another contentious issue is the interpretability of the principal components extracted by PCA, which can be challenging to understand, particularly when they represent complex combinations of multiple original variables (Hair, 2009). Our study enhances the interpretability of the principal components through a detailed rotation method, ensuring each component represents a coherent set of variables. Thirdly, some scholars argue that an over-reliance on PCA and other dimensionality reduction techniques might overlook significant individual differences and subtle relationships among variables (Greenacre, 2010). By integrating additional statistical methods and qualitative analysis, we endeavor to visualize extensive data, ensuring that PCA results are not isolated but are combined with other data and theoretical frameworks for a more comprehensive perspective. Fourthly, PCA has certain requirements regarding sample size and data quality. Small samples or datasets containing noise may lead to inaccurate outcomes (Sheskin, 2003). This study utilized a sufficiently large sample size and conducted rigorous data cleaning and quality control to ensure the reliability of the analysis. Fifthly, determining the number of principal components to retain is a subjective decision-making process, with different choices potentially leading to varying interpretations and conclusions (Jolliffe, 2005). We selected the number of principal components based on the principle of cumulative contribution rate and eigenvalues greater than one. Therefore, while PCA analysis has its limitations, this study effectively circumvents potential issues, providing a robust approach to the dimensionality reduction of street quality indicators.

In the discussion section, from lines 772 to 800, we have provided a detailed argument and debate on the use of PCA and explained the rationale for our methodological choices. We believe that these revisions not only address your suggestions but also enhance the contributions and depth of our research.

We thank you again for your valuable comments and look forward to your further guidance.

 

Author Response File: Author Response.doc

Reviewer 2 Report

Comments and Suggestions for Authors

The study examines the interplay between urban environment, mobility, and life satisfaction in Reykjavik, using activity spaces and CCA for analysis. It finds socio-economic background to be a key determinant of life satisfaction and suggests urban planning focused on citizen needs to enhance wellbeing and climate outcomes. It is a well-written article. However, here are some minor remarks.

1.     Please summarize the main contributions of the study briefly in the introduction. While these points are detailed in the literature review, highlighting them in the introduction will provide a clearer overview.

2.     Ensure the references adhere to MDPI citation guidelines, as the current format appears inconsistent. Double-check the formatting to comply with MDPI standards.

3.     Include a discussion on the performance of the model used in the study.

4.     Elaborate on the applicability of the results and the main implications of your findings.

5.     It is highly recommended to compare the findings with results from other nearby cities.

 

Author Response

Reply to the Referee

 

1. Please summarize the main contributions of the study briefly in the introduction. While these points are detailed in the literature review, highlighting them in the introduction will provide a clearer overview.

We sincerely appreciate the valuable suggestions and opinions you have provided. Following your advice, we have made corresponding adjustments to the introduction section to more clearly outline the main contributions of this study. Below are the revisions we have made according to your instructions:

The study employs deep learning and street view image analysis technologies to construct a high-precision, multidimensional evaluation framework. It aims to extract and quantify key spatial quality indicators from a vast array of street view image data. Utilizing methods such as Principal Component Analysis (PCA), semantic segmentation, and cluster analysis, this study seeks to uncover the critical factors influencing street space quality and their intrinsic connections. On this foundation, we pose a central research question: How can multiple key factors be synthesized in the context of high-density urban environments to optimize street space quality, thereby achieving coordinated urban development and enhancement of spatial quality? This question is pivotal for guiding urban planning and design, as well as for improving the quality of life for residents.

For details, please refer to lines 85 to 95 of the Introduction. We believe that with these modifications, the introduction section now provides a clearer overview of the main contributions of this study and offers readers a coherent research summary. We look forward to your further feedback and thank you for your ongoing support of our work.

 

2. Ensure the references adhere to MDPI citation guidelines, as the current format appears inconsistent. Double-check the formatting to comply with MDPI standards.

Thank you for your suggestion. We have carefully reviewed and adjusted the citation format in our manuscript to ensure full compliance with the MDPI citation guidelines. All references have been double-checked and formatted consistently throughout the text. The updated references can be found in the "References" section of our paper.

We appreciate your attention to detail and are confident that the revised manuscript meets the required standards for publication.

 

3. Include a discussion on the performance of the model used in the study.

First and foremost, we express our heartfelt gratitude for your valuable comments and suggestions. Your insights into the discussion section of our study have provided significant guidance for further deepening our research.

In response to your discussion on the model's performance, we have made the following replies:

Further explanation of the correlation analysis: We agree with the positive correlation between the Green Coverage Index (GVI) and other landscape view indicators, reflecting the active role of urban green spaces in enhancing urban landscape quality. At the same time, we have noted the negative correlation between GVI and public service facility indicators, which indeed reveals potential conflicts between land uses in high-density urban environments. We will further explore the underlying causes of this conflict and consider how to balance the needs of green spaces and public service facilities in urban planning.

In-depth discussion of principal component analysis and cluster analysis: We appreciate your recognition of these analytical methods. Through these methods, we have been able to reveal the diversity of street space quality on the Macau Peninsula and effectively identify differences in street space quality. We will further refine the results of the cluster analysis to more accurately describe the characteristics of each cluster category and explore the specific impact of these characteristics on the evaluation of street space quality.

Comprehensive suggestions for urban planning and design: We fully agree on the necessity of considering multiple key factors in urban planning and design. Our research results emphasize the synergistic effect of factors such as green coverage, landscape color, and public service facilities in the process of improving street space quality. We will further explore in subsequent research how these factors interact with each other and how to achieve the optimal configuration of these factors in actual urban planning practices.

Clarification of specific guidance and potential directions: We thank you for your recognition of our research findings and agree that these discoveries provide specific guidance for urban planning and design. We will further clarify in subsequent research the strategies for improving the street space quality of the Macau Peninsula, including specific measures to increase green spaces, methods to enrich urban colors, and optimization plans for the distribution of service facilities.

For more details, please refer to the red markings in the Conclusions and Discussion section. We look forward to further communication with you and welcome more comments and suggestions on our research. We believe that through continuous discussion and feedback, our research will become more in-depth and refined.

 

4. Elaborate on the applicability of the results and the main implications of your findings.

We appreciate your in-depth discussion on the applicability and main implications of our research findings.

Here is our response to your valuable feedback:

Applicability of the research findings: We agree that this study provides a new comprehensive assessment method for evaluating the quality of street space in high-density urban environments. By integrating deep learning technology, street view image analysis, and principal component analysis, our method can quantify key indicators of street space quality, offering a new tool for urban planners and decision-makers to carry out urban renewal and design in a more refined and humanized manner.

Emphasis on multidimensional characteristics: We fully agree that street space quality in high-density urban environments has multidimensional characteristics, and it is crucial to consider these dimensions comprehensively in urban planning. Our method emphasizes the need to consider multiple key factors in the evaluation process, such as green coverage, color richness, and the distribution of service facilities, all of which are significant factors affecting the quality of life for residents.

Positive correlation between quality of life and key indicators: We are pleased to see that you have pointed out the positive correlation between indicators such as the Green Coverage Index (GCI) and the Color Richness Index (CRI) with the quality of life of urban residents. This finding provides us with a direction for further research, namely, how to improve the quality of life for residents by enhancing these indicators.

Inequality in the distribution of service facilities: Your observation on the inequality in the distribution of service facilities in urban street spaces and its impact on residents' daily lives provides us with an important perspective. We will further study the causes and consequences of this inequality and explore how to optimize the distribution of service facilities through urban planning to reduce its negative impact on residents' daily lives.

Quantitative assessment method based on empirical data: We thank you for recognizing our quantitative assessment method for street space quality based on empirical data. This method helps us to more accurately identify and address imbalances in urban development, providing a scientific basis for urban planning.

We will continue to deepen these findings and explore how to apply them in practical urban planning and design. We look forward to further communication with you and welcome more comments and suggestions on our research.

 

5. It is highly recommended to compare the findings with results from other nearby cities.

We extend our sincere gratitude for the suggestions you have proposed. Your recommendations hold significant guidance for our research, and we have given them our utmost consideration and thoughtful deliberation.

We fully concur on the importance of comparative studies in revealing the characteristics of urban spatial systems and in enhancing the depth of research. By comparing the quality of street spaces across different cities, we can achieve a more comprehensive understanding of the differences in urban development patterns and the quality of life of residents.

 In this study, we have primarily focused on the research of indicator weights and their variability and interconnectivity within the complex systems of high-density cities. Due to limitations in length and depth of research, we were unable to include comparative analysis with other cities in this study. We recognize this as a significant gap in our research and plan to address it in future studies.

We will expand the scope of comparative research in our subsequent studies, including but not limited to the assessment of street space quality in neighboring cities. We intend to compare differences among cities in aspects such as green coverage, color richness, and distribution of service facilities through both quantitative and qualitative methods, and to explore the impact of these differences on the quality of life of residents.

We eagerly anticipate further guidance and feedback from you. Your professional opinions and suggestions are crucial to our research, and we hope to refine our study through continuous communication and discussion.

Once again, we thank you for your valuable suggestions and support.

Author Response File: Author Response.doc

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The author has responded to the comments. The revised version is satisfactory for publication.