Demand-Led Optimization of Urban Park Services

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper highlighted a variety of methods and processes for optimizing urban park services focusing on demand side. While previous studies categorized demand based on demographic aspects, it is noteworthy that actual park demand has been analyzed by subdividing it into various components such as economic conditions estimating demand based on residential areas, physical living conditions like population density, and the size of green spaces per capita.

However, there are some aspects that fundamentally require improvement and modification.

1) Abstract it too long and confusing. Some parts are better to be located in introduction. Key concepts and objective need to be shortened and/or better rephrased for improving clarity.

2) The abbreviated keyword “GWO-KNN” is presented in abstract. It may be convenient to understand the paper if it is indicated what GWO-KNN stands for from the beginning.

3) Is it really possible to overcome limitations in data acquisition by utilizing Point of Interest (POI) data related to park attributes”? More solid ground for such confident statements needs to be provided.

4) Too many methods appear abruptly or unexpectedly, lacking a clear connection to the surrounding circumstances or contexts. Furthermore, each method is explained without providing sufficient description for reader’s clear understanding.

5) Among others, entropy-weight method seems to be employed in estimating residential quality and park quality. It is not clear how the method works in this research context. The definition of entropy method needs to provided in more evident manner. For example, in equation 1, how is the weight estimated? You need to explain entropy method clearly.

6) From Eq.1 to Eq6, the letters are blurry. The overall quality of presenting figures, equations, explanations etc., should be substantially improved. For example, the Figure2 is too be blurred to grasp the content. The quality of the figure needs to be improved.

Author Response

I appreciate your positive evaluation of the manuscript's structure and content. Your valuable suggestions for enhancing the logical coherence and overall quality of the paper are crucial. I will carefully address each of your recommendations and provide detailed responses accordingly.

• Point 1: Abstract it too long and confusing. Some parts are better to be located in introduction. Key concepts and objective need to be shortened and/or better rephrased for improving clarity.

Response 1: We feel great thanks for your valuable suggestions. A well-crafted abstract is crucial for effectively conveying the research results and innovations of the manuscript. Your feedback will significantly enhance the quality of the manuscript. In response to your suggestions, the abstract has been refined with redundant content removed.

The revised abstract is as follows: As the demand for cultural and recreational services grows, the mismatch between park service supply and demand significantly affects residents' well-being. Optimizing the spatial layout of park services is a focal point of urban park and green space research. Taking Hangzhou, Zhejiang Province, as a case study, this research analyzes the spatial patterns and balance of park service supply and demand. Utilizing the Grey Wolf Optimization model optimized by the K-Nearest Neighbour model (GWO-KNN), the study proposes construction objectives for optimizing park services. The results indicate: (1) Significant differences exist in the park service demands of residents in different residential environments. (2) There is a noticeable spatial disparity in park service supply among various residential areas, with an overall positive correlation between park service supply levels and resident demands, yet an imbalance exists. The study categorizes spatial types into low-service coordination, high-service coordination, low-service imbalance, and high-service imbalance. (3) The application of the GWO-KNN model, with optimization objectives being the innovative aspect of this study. Strategies for each park category are proposed: emphasizing suburban park construction by utilizing surrounding green resources and adding diverse facilities; introducing facilities friendly to vulnerable groups to meet the needs of diverse populations; enhancing the complementary advantages between "new" and "old" cities by moderately increasing park sizes and improving cultural and facility development levels; optimizing spatial structure with limited land resources to construct an urban park network system. This study aims to provide theoretical and technical support for optimizing urban park and green space systems.

• Point 2: The abbreviated keyword “GWO-KNN” is presented in abstract. It may be convenient to understand the paper if it is indicated what GWO-KNN stands for from the beginning.

Response 2: We sincerely thanks for your valuable suggestions. To enhance the comprehensibility of the "GWO-KNN model," we have provided an explanation for this key term in the first occurrence within the abstract. The "GWO-KNN model" is articulated as the "Grey Wolf Optimization model optimized by K-Nearest Neighbour model (GWO-KNN)." We hope that this expression will better clarify the content for the readers.

• Point 3: Is it really possible to overcome limitations in data acquisition by utilizing Point of Interest (POI) data related to park attributes”? More solid ground for such confident statements needs to be provided.

Response 3: Thanks for your valuable reminder; the academic rigor of the manuscript is crucial. We have incorporated discussions on this aspect in the "Introduction" section.

The added content is as follows: This study focuses on all parks in the main urban area of Hangzhou. Given the numerous and large-scale parks in the area, traditional on-site surveys to gather park information are time-consuming and labor-intensive. POI data can overcome the problem of difficult data access, while China's POI data includes all kinds of park attribute data such as sports and amenities in addition to location information, POI data can better replace field research.

• Point 4: Too many methods appear abruptly or unexpectedly, lacking a clear connection to the surrounding circumstances or contexts. Furthermore, each method is explained without providing sufficient description for reader’s clear understanding.

Response 4: We sincerely thanks for your suggestion. Clarifying the connection between research methods and context and expressing them clearly can better convey the necessity of the research methods, thus enhancing readability for readers. After careful consideration and logical refinement of the context, we have made the following additions:

• In "3.1. Evaluation of Park Service Levels," we included the statement: "The measurement of park service levels reflects the residents' access to park supply."
• In "3.2. Park Service Demand Evaluation," the following was added: "To better measure whether there is a balanced match between residents' park service supply and demand, park service demand is an important component. In this study, we assess residential demand by measuring the quality of residential areas. The higher the comprehensive evaluation result, the greater the park service demand. Combining existing research results, we selected indicators for evaluating residential quality."
• In "3.3. Coupling Coordination and Matching," the following was added: "Analyzing the spatial matching and coupling coordination of park service supply and demand can provide a better foundation for optimizing park services."
• In "3.4. Optimizing Park Service Levels: The GWO-KNN Model," the following was added: "Based on the results of park service supply and demand measurements, analyzing the matching degree between park service supply and demand, exploring differences in park supply and demand matching, and proposing optimization goals are the core content of the study. The GWO-KNN Model is an intelligent optimization algorithm capable of classifying existing datasets in highly complex situations, matching the nearest values. The model is trained based on datasets with high park service supply and demand matching, optimizing datasets with mismatched supply and demand, and obtaining the optimal solution with high coordination of park service supply and demand. The calculation formula is as follows." We hope that these additions address your concerns and provide greater convenience for readers.
• Point 5: Among others, entropy-weight method seems to be employed in estimating residential quality and park quality. It is not clear how the method works in this research context. The definition of entropy method needs to provided in more evident manner. For example, in equation 1, how is the weight estimated? You need to explain entropy method clearly.

Response 5: We really appreciate you for incorporating the suggestion to include the entropy weight method. Your input significantly contributes to improving the manuscript quality. We have added this content to the "3.1 Evaluation of Park Service Levels" section. Additionally, we have adjusted the numbering of all the formulas. The added content is as follows:

The entropy weight method is a technique that objectively assigns weights based on the variability of indicators. Analyzing the numerical values of each indicator and calculating weights can provide a foundation for evaluating park quality. The calculation formulas are as follows(If there are formulas that don't show up, you can view the manuscripts.):

(1) Standardization: We used the range normalization method to standardize the original data without dimensionality, and then shifted the data. Suppose there are m parks and n evaluation indicators in this study; the formulas are as follows:

For positive indicators:	(1)
For negative indicators:	(2)

Where i= 1, 2, …, m; j= 1, 2,…, n; y_ij is the dimensionless standardized and shifted value; x_ij is the original data value of the j-th indicator for the i-th park, x_jmax and x_jmin are the maximum and minimum original values of the j-th indicator.

• Entropy Weight Determination: The weight determination formula using the entropy weight method is as follows:

	（3）
	（4）
	（5）

Where p_ij is the proportion of the j-th indicator value for the i-th park in the sum of all park values for that indicator; d_j is the information entropy redundancy; w_j is the indicator weight.

• Point 6: From Eq.1 to Eq6, the letters are blurry. The overall quality of presenting figures, equations, explanations etc., should be substantially improved. For example, the Figure2 is too be blurred to grasp the content. The quality of the figure needs to be improved.

Response 6: We sincerely thanks for your reminder. Due to the compression of images when converting the Word version to PDF, the images became blurry. We have replaced all the images with clear ones to facilitate readability. Additionally, a ZIP folder containing the images has been uploaded with the study. If any clarity issues persist, please refer to the folder for a clearer view.

In addition, during the process of revising the manuscript, we will mark the revised content in red to make it easier for the editor in chief and reviewers to understand the revised content more clearly.

Thanks again to the reviewers for their helpful comments and the editors for their help in this process. Looking forward to your reply.

Best wishes.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The article is interesting, although the research topic is a little complex, which aims to analyze the demands of users with the level of service of the parks to determine the supply-demand relationship and how the level of services of the parks can be optimized. At the outset, it would be important to synthesize the summary to present the most important points of the work. The topic is relevant in the area but due to the complexity some results seem a bit obvious. It will be important to better describe the use of Gray Wolf Optimization (GWO) in the methodology. Unfortunately the figures in the document are not clear (quality) and it is complex to analyze them together with the text; Indeed, there are many figures and it is suggested to evaluate if all of them are necessary in the document. It is recommended to review the conclusions to better connect them with the objectives. Small additional comments are presented in the attached PDF file.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

The quality of the language is acceptable but it would be important to check some aspects of the style.

Author Response

Thank you very much for acknowledging the significance of the manuscript. Your valuable suggestions for improving the readability and overall quality of the manuscript are highly appreciated. In response to your recommendations, I will make the necessary modifications and provide feedback accordingly.

• Point 1: It will be important to better describe the use of Gray Wolf Optimization (GWO) in the methodology.

Response 1: We sincerely thanks for your professional advice. Your suggestions are highly significant for enhancing the readability of the manuscript. Addressing your recommendation for a more detailed description of the Gray Wolf Optimization (GWO) model, we have incorporated relevant content in Section 3.4, "Optimizing Park Service Levels: The GWO-KNN Model."

The added content is as follows: "Based on the results of the measurement of park service supply and demand, the study analyzes the matching degree of park service supply and demand, explores the differences in supply and demand matching, and proposes optimization goals, which are the core focus of the research. The GWO-KNN Model is an intelligent optimization algorithm capable of classifying existing datasets in highly complex situations, matching the nearest values. The model is trained on datasets with high matching degrees of park service supply and demand to optimize datasets with mismatched supply and demand, obtaining the optimal solution with high coordination between park service supply and demand [48]."

• Point 2: Unfortunately the figures in the document are not clear (quality) and it is complex to analyze them together with the text; Indeed, there are many figures and it is suggested to evaluate if all of them are necessary in the document.

Response 2: Thank you for bringing this to our attention. The blurriness of the images, resulting from the compression when converting the Word version to PDF, has been addressed. We have replaced all images with clear versions to ensure readability. Additionally, a ZIP folder containing the images has been uploaded with the study. If any clarity issues persist, please refer to the folder for clearer images.

• Point 3: It is recommended to review the conclusions to better connect them with the objectives. Small additional comments are presented in the attached PDF file.PDF

Response 3: (1) The fundamental reason for the lack of significant differences lies in the strong constraints on the "Per Capita Green area" indicator in urban development, leading to minimal internal variations. However, "Per Capita Green area" is a crucial indicator expressing and reflecting the environmental quality of residential areas. Analyzing the spatial characteristics of various types of residential areas can better characterize residential quality and meet resident demands.

(2) We appreciate the expert's alertness to the capitalization errors in the vocabulary of this study. To enhance the precision of our study's expression, we have corrected the capitalization errors in the vocabulary. For detailed information, please refer to the revised manuscript.

In addition, during the process of revising the manuscript, we will mark the revised content in red to make it easier for the editor in chief and reviewers to understand the revised content more clearly.

Thanks again to the reviewers for their helpful comments and the editors for their help in this process. Looking forward to your reply.

Best wishes.

Author Response File: Author Response.pdf