Nonlinear and Threshold Effects of the Built Environment on Dockless Bike-Sharing

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The manuscript provides valuable insights into the relationship between built environment features and bike-sharing ridership using the XGBoost model. However, several issues need to be addressed to enhance the study:

1.         Some cited works in the literature review are not directly relevant. Ensure all references are pertinent and well-integrated with the research question.

2.         Data cleaning and preprocessing steps are insufficiently detailed. Describe how missing data and outliers were handled.

3.         The explanation of built environment variables is inadequate. Clearly state the rationale for selecting these variables and their potential relationship with bike-sharing ridership.

4.         Results are presented in a confusing manner. Arrange results logically and ensure figures are referenced appropriately.

5.         There are several grammatical errors and awkward phrasings.

6.         Some references lack crucial details. Ensure all citations are complete and accurate.

Comments on the Quality of English Language

Minor editing of the English language is required.

Author Response

Authors’ responses to the comments by the reviewers on the paper, “Nonlinear and threshold effects of the built environment on dockless bike-sharing” (Manuscript ID: sustainability-3046096)

 

The authors thank the four anonymous reviewers for their insightful comments, which helped improve the previously submitted manuscript. The authors have revised the manuscript based on the reviewers’ comments. The notes below address the reviewers’ comments (in bold text) and describe how these comments were incorporated into the revised manuscript. We first summarize the major revisions made based on the reviewers’ comments:

• We have expanded and elaborated the contribution in the abstract and introduction section.
• We have added a framework diagram in the introduction section to illustrate the steps and methods employed in this study.
• We have expanded the literature review section to be more comprehensive.
• We have also employed a language editor to correct the grammatical errors and word choice issues throughout this paper.
• We have revised the word format adjusted to comply with MDPI guidelines.

The details of how each reviewer’s comments were addressed are listed below. The highlighted text in the revised paper represents the major revisions.

 

 

 

Reviewer #1:

 

1. Some cited works in the literature review are not directly relevant. Ensure all references are pertinent and well-integrated with the research question.

 

R1: Thanks for the comments. We have reviewed the literature section and removed references that were not directly relevant to our research question. Additional relevant references have been included to ensure that the literature review is well-aligned with the study’s objectives.

 

2. Data cleaning and preprocessing steps are insufficiently detailed. Describe how missing data and outliers were handled.

 

R2: Thanks for the comments. We have expanded the manuscript to include a detailed description of the data cleaning and preprocessing steps. This now includes specific methods used to handle missing data and outliers (as shown in Line 4-8,Page 10):

 

“Bike-sharing order and GPS trajectory data. This part of the data comes from the bike-sharing trajectory data (DCIC, 2021) released by Xiamen government in morning peaking hours, from 6:00-10:00 am, December 21st-25th, 2020. We first cleaned the data, including eliminating outliers trips such as riding position outside the study area and those with abnormally short or long riding times, and using interpolation method to estimate missing values to ensure data consistency. Subsequently, we carried out coordinate transformation and spatial matching, and obtained all the daily origin-destination (OD) bike-sharing ridership in the study area.”

 

3. The explanation of built environment variables is inadequate. Clearly state the rationale for selecting these variables and their potential relationship with bike-sharing ridership.

 

R3: Thanks for the comments. The selection of built environment variables was guided by their potential influence on bike-sharing ridership, based on existing literature and “3D” urban planning principles. We have expanded the manuscript to include a detailed description of the rationale for built environment variables in the section of the literature review (as shown in Page 5-6) and data description (as shown in Line 1-12, Page 11).

 

“Built environment refers to the artificial space environment made for human activities, including land use, urban design, transportation infrastructure and other factors. Accurately depicting the built environment is the key to explore the impact of the built environment on travel behavior. The built environment is measured by the three Ds, namely, density, design, land use diversity. Density measures include transportation density, public facilities and services density, subway density, bus density, point of interest (POI) density (Gaode map, 2021), the ratios of residential, industrial, and commercial land use, population density, and local population density. Design refers to the measurement of the characteristics of the road network in the area, measured by the road density. Land use diversity measures the mixing degree of different land uses in the region. Its measurement method is based on regional entropy and grid, and the entropy index ranges from 0 to 1, where the smaller the value, the lower the mixing degree, and 1 means that all land use types are allocated equally here [45]. ”

 

4. Results are presented in a confusing manner. Arrange results logically and ensure figures are referenced appropriately.

 

R4: Thanks for the comments. The results section has been reorganized to present the findings in a logical sequence. All figures have been properly referenced.

 

5. There are several grammatical errors and awkward phrasings.

 

R5: Thanks for the comments. The entire manuscript has been carefully proofread to correct grammatical errors and awkward phrasing. This has improved the overall clarity and readability of the text.

 

6. Some references lack crucial details. Ensure all citations are complete and accurate.

 

R6: Thanks for the comments. We have reviewed all citations and added any missing details. All references are now complete and accurately formatted according to the journal’s guidelines.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

1． Please check basic issues such as punctuation use in the paper.  For example, the sentence in the abstract (“This paper uses a machine learning method;  extreme gradient boosting tree model;  to identify the impacts of the built environment on the origin- destination bike-sharing ridership.”) is strange;  The word size is different in different paragraphs;  The reference format seems to be wrong for MDPI.

2． It is suggested to add a diagram in the introduction to give a brief and clear presentation of the proposed method for potential readers.

3． The format of equation is not right.

4． Have you ever tried some other methods to make the model performance better?

5． This paper should add a data availability statement for potential readers.

Author Response

Authors’ responses to the comments by the reviewers on the paper, “Nonlinear and threshold effects of the built environment on dockless bike-sharing” (Manuscript ID: sustainability-3046096)

 

The authors thank the four anonymous reviewers for their insightful comments, which helped improve the previously submitted manuscript. The authors have revised the manuscript based on the reviewers’ comments. The notes below address the reviewers’ comments (in bold text) and describe how these comments were incorporated into the revised manuscript. We first summarize the major revisions made based on the reviewers’ comments:

• We have expanded and elaborated the contribution in the abstract and introduction section.
• We have added a framework diagram in the introduction section to illustrate the steps and methods employed in this study.
• We have expanded the literature review section to be more comprehensive.
• We have also employed a language editor to correct the grammatical errors and word choice issues throughout this paper.
• We have revised the word format adjusted to comply with MDPI guidelines.

The details of how each reviewer’s comments were addressed are listed below. The highlighted text in the revised paper represents the major revisions.

 

 

 

 

Reviewer #2:

 

1. Please check basic issues such as punctuation use in the paper. For example, the sentence in the abstract ("This paper uses a machine learning method; extreme gradient boosting tree model; to identify the impacts of the built environment on the origin-destination bike-sharing ridership.") is strange; The word size is different in different paragraphs; The reference format seems to be wrong for MDPI.

 

R1: Thanks for the comments. We have revised the sentence in the abstract to improve its clarity and corrected punctuation throughout the manuscript. The word size has been standardized across all paragraphs, and the reference format has been adjusted to comply with MDPI guidelines.

 

2. It is suggested to add a diagram in the introduction to give a brief and clear presentation of the proposed method for potential readers.

 

R2: Thanks for the comments. A schematic diagram of the research framework has been added to the introduction section to visually present the proposed method. This should help readers understand the methodological approach more easily (as shown in Figure 1, Page 4-5).

 

“Fig.1. illustrates the framework of this study. The framework consists of three main components: (1) Data Input, which includes the collection and processing of built environment variables and bike-sharing ridership data at the community street level; (2) Model Construction, focusing on the application of the XGBoost algorithm to analyze the relationships between built environment factors and bike-sharing usage; and (3) Results Analysis, which involves the interpretation of nonlinear effects and the identification of thresholds for various built environment factors.

FIGURE 1 Schematic diagram of the research framework     ”

 

 

3. The format of the equation is not right.

 

R3: Thanks for the comments. The formatting of the equation has been corrected to align with standard practices, ensuring consistency and clarity in its presentation.

 

4. Have you ever tried some other methods to make the model performance better?

 

R4: Thanks for the comments. We tried different machine learning algorithms and finally chose the XGBoost method based on the prediction accuracy and interpretability. Besides, the comparison with other models is a very interesting perspective and we have added in the manuscript for the future research direction (as shown in Line 11-19, Page 28).

 

“Of course, there are still some deficiencies in this paper and the following aspects could be further explored in the future. In this paper, our research case is a typical bay city, and it is necessary to select more plain cities with different geographical and geometric characteristics to analyze and compare the heterogeneity of the nonlinear relationship between the built environment and bike-sharing ridership. Furthermore, different methods could be compared, such as multilayer neurocontrol of high-order uncertain nonlinear systems and integral robust schemes for mismatched uncertain nonlinear systems, could be compared. The impact and mechanisms of the built environment on the competition and cooperation relationship between bike-sharing and other traffic modes could be further research directions.”

 

 

5. This paper should add a data availability statement for potential readers.

 

R5: Thanks for the comments. We have added a data availability statement in the manuscript (as shown in Line 1-4, Page 29).

 

“DATA AVAILABILITY STATAMENT

The data used in this study were sourced from a bike-sharing platform.  The data can be made available upon request from authors, subject to the approval of the bike-sharing platform and the signing of a confidentiality agreement.”

 

 

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

​ Comments and Suggestions for Authors

 

1.      In the Introduction Section, the authors need to explore further the contributions that the work offers. What is the contribution to theory and practice? How can industry and organizations benefit from the results?

2.      Page 2 - Lines 22 and 23 - "to excavate the nonlinear relationship and threshold effect between them" is very vague. Please clarify.

3.      From page 5 onwards, the text presents a different structure and formatting, including titles and subtitles. For example, is a subtitle on page 4, line 8 "Bike-sharing order and GPS trajectory data "? The fact that the line numbering always restarts and there are several pages with the same numbering also hindered the review. The authors should have been more careful with the final review of the submitted text.

4.      Figure 3 is illegible. It contains many images. I recommend splitting.

5.      Figure 4? Relative importance is calculated concerning the most important predictor, taking values ​​from 0% to 100%. The most important variable has a relative importance of 100%. I didn't understand the percentages presented.

6.      Figure 5 should be positioned as close to the first reference citation. The same applies to Figure 6.

7.      The sentence "the bike-sharing ridership is higher when:" is vague. Higher in relation to which reference? For example, in the item "a) the area is greater than 2 km2," why didn't you use the largest value in the series?

8.      In the "Conclusions and Implications" section, the research limitations and the recommendations for future work must be better presented.

Comments for author File: Comments.pdf

Author Response

Authors’ responses to the comments by the reviewers on the paper, “Nonlinear and threshold effects of the built environment on dockless bike-sharing” (Manuscript ID: sustainability-3046096)

 

The authors thank the four anonymous reviewers for their insightful comments, which helped improve the previously submitted manuscript. The authors have revised the manuscript based on the reviewers’ comments. The notes below address the reviewers’ comments (in bold text) and describe how these comments were incorporated into the revised manuscript. We first summarize the major revisions made based on the reviewers’ comments:

• We have expanded and elaborated the contribution in the abstract and introduction section.
• We have added a framework diagram in the introduction section to illustrate the steps and methods employed in this study.
• We have expanded the literature review section to be more comprehensive.
• We have also employed a language editor to correct the grammatical errors and word choice issues throughout this paper.
• We have revised the word format adjusted to comply with MDPI guidelines.

The details of how each reviewer’s comments were addressed are listed below. The highlighted text in the revised paper represents the major revisions.

 

 

 

Reviewer #3:

 

1. In the Introduction Section, the authors need to explore further the contributions that the work offers. What is the contribution to theory and practice? How can industry and organizations benefit from the results?

 

R1: Thanks for the comments. The introduction has been expanded to better articulate the contributions of our work to both theory and practice (as shown in Line 3-17, Page 4) , which could provide references and policy implications for bike-sharing platform and urban planning (as shown in Line 3-10,Page 28).

 

“The main contribution of this study is the development of a novel framework integrated with the XGBoost model to elucidate the influence of various built environment factors at both origins and destinations on OD bike-sharing ridership. Additionally, this study investigates the nonlinear relationships and threshold effects between built environment factors and OD bike-sharing ridership. The findings aim to enhance the alignment between bike-sharing travel behaviors and the built environment, fostering better adaptation in future urban mobility planning. A focus is placed on community street-level bike-sharing systems to achieve more refined management of green travel initiatives.

Fig.1. illustrates the framework of this study. The framework consists of three main components: (1) Data Input, which includes the collection and processing of built environment variables and bike-sharing ridership data at the community street level; (2) Model Construction, focusing on the application of the XGBoost algorithm to analyze the relationships between built environment factors and bike-sharing usage; and (3) Results Analysis, which involves the interpretation of nonlinear effects and the identification of thresholds for various built environment factors.

FIGURE 1 Schematic diagram of the research framework     ”

 

“The findings could provide policy implications for target audiences of different groups. For urban planners, when actively planning and intervening in urban space from different dimensions such as density, diversity and design, the adaptability of bike-sharing travel activities to built environment can be appropriately taken into account to improve bike-sharing riding space. For bike-sharing operating companies, the configuration can be optimized to achieve more scientific bike-sharing delivery, provide sufficient bike-sharing services in areas with high bike demand, and appropriately reduce the shared bike capacity in areas with low bike demand, so as to improve the travel efficiency of bike-sharing and improve the turnover rate.”

 

2. Page 2 - Lines 22 and 23 - "to excavate the nonlinear relationship and threshold effect between them" is very vague. Please clarify.

 

R2: Thanks for the comments. The phrasing has been revised for clarity.

“Additionally, this study investigates the nonlinear relationships and threshold effects between built environment factors and OD bike-sharing ridership. The findings aim to enhance the alignment between bike-sharing travel behaviors and the built environment, fostering better adaptation in future urban mobility planning.”

 

3. From page 5 onwards, the text presents a different structure and formatting, including titles and subtitles. For example, is a subtitle on page 4, line 8 "Bike-sharing order and GPS trajectory data"? The fact that the line numbering always restarts and there are several pages with the same numbering also hindered the review. The authors should have been more careful with the final review of the submitted text.

 

R3: Thanks for the comments. We have corrected the formatting issues from Page 5 onwards, ensuring consistent structure and formatting throughout the manuscript. The line numbering issue has also been resolved.

 

4. Figure 3 is illegible. It contains many images. I recommend splitting.

 

R4: Thanks for the comments. We combined the images to facilitate a comparative analysis of the distribution of these explanatory variables across the regions. We have now enhanced the image clarity to meet readability requirements.

 

5. Figure 4? Relative importance is calculated concerning the most important predictor, taking values from 0% to 100%. The most important variable has a relative importance of 100%. I didn't understand the percentages presented.

 

R5: Thanks for the comments. The sum of the relative importance of all explanatory variables is 100%. Relative importance is used to accurately express the contribution of an explanatory variable to the predicted dependent variable. We have provided a more detailed description of how these percentages were calculated and their significance (as shown in Line 1-12, Page 16).

 

“In generating the decision tree, each explanatory variable has a certain probability to be selected to segment the data, and the relative importance is essentially the proportion of the number of times an explanatory variable is selected in the iterative process of generating the decision tree to the total number of times all explanatory variables are selected, and the sum of the relative importance of all explanatory variables is 100%. Relative importance is used to accurately express the contribution of an explanatory variable to the predicted dependent variable, which can be described as follows:

                         (9)

                            (10)

where  represents the explanatory variable,  and  represent the number of leaf nodes and non leaf nodes of the tree respectively, is a feature associated with node , the reduction of square loss after node splitting is expressed as .”

 

6. Figure 5 should be positioned as close to the first reference citation. The same applies to Figure 6.

 

R6: Thanks for the comments. Figures 5 and 6 have been repositioned closer to their first mentions in the text. This improves the flow and readability of the manuscript.

 

7. The sentence "the bike-sharing ridership is higher when:" is vague. Higher in relation to which reference? For example, in the item "a) the area is greater than 2 km2," why didn't you use the largest value in the series?

 

R7: Thanks for the comments. We have elaborated the explanations of these results to make it more comprehensible. We are investigating threshold effects and identifying the ranges of influence, rather than searching for largest values, with the aim of exploring nonlinear relationships.

 

8. In the "Conclusions and Implications" section, the research limitations and the recommendations for future work must be better presented.

 

R8: Thanks for the comments. This section has been revised to better address research limitations and to provide detailed recommendations for future work.

 

“Of course, there are still some deficiencies in this paper and the following aspects could be further explored in the future. In this paper, our research case is a typical bay city, and it is necessary to select more plain cities with different geographical and geometric characteristics to analyze and compare the heterogeneity of the nonlinear relationship between the built environment and bike-sharing ridership. Furthermore, different methods could be compared, such as multilayer neurocontrol of high-order uncertain nonlinear systems and integral robust schemes for mismatched uncertain nonlinear systems, could be compared. The impact and mechanisms of the built environment on the competition and cooperation relationship between bike-sharing and other traffic modes could be further research directions.”

 

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

See the comments in the uploaded attachment.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

Authors’ responses to the comments by the reviewers on the paper, “Nonlinear and threshold effects of the built environment on dockless bike-sharing” (Manuscript ID: sustainability-3046096)

 

The authors thank the four anonymous reviewers for their insightful comments, which helped improve the previously submitted manuscript. The authors have revised the manuscript based on the reviewers’ comments. The notes below address the reviewers’ comments (in bold text) and describe how these comments were incorporated into the revised manuscript. We first summarize the major revisions made based on the reviewers’ comments:

• We have expanded and elaborated the contribution in the abstract and introduction section.
• We have added a framework diagram in the introduction section to illustrate the steps and methods employed in this study.
• We have expanded the literature review section to be more comprehensive.
• We have also employed a language editor to correct the grammatical errors and word choice issues throughout this paper.
• We have revised the word format adjusted to comply with MDPI guidelines.

The details of how each reviewer’s comments were addressed are listed below. The highlighted text in the revised paper represents the major revisions.

 

 

 

Reviewer #4:

1. The organization and layout of the entire article need to be greatly adjusted. Moreover, the manuscript has some typos, ambiguous sentences and language issue that require full spell and syntax checking.

 

R1: Thanks for the comments. The manuscript has been reorganized to improve its layout and flow. We have conducted a thorough spell and syntax check to correct any typos, ambiguous sentences, and language issues.

 

2. The content in the abstract should be further condensed to highlight the innovative points of this manuscript. In introduction, the research background should be further strengthened and the descriptions of existing research should be further summarized. Moreover, the highlights of this work should be listed point by point at last of the Introduction.

 

R2: Thanks for the comments. We have expanded and elaborated the contribution in the abstract and introduction section.

 

“Dockless bike-sharing mobility brings considerable benefits to build a low-carbon transportation. However, the operators often rush to seize the market and regulate the services without a good knowledge of this new mobility option, which results in unreasonable layout and management of shared bicycles. Therefore, it is meaningful to explore the relationship between the built environment and bike-sharing ridership. This study is to propose a novel framework integrated with the extreme gradient boosting tree model to evaluate the impacts and threshold effects of the built environment on the origin-destination bike-sharing ridership. The results show that most built environment features have strong nonlinear effects on the bike-sharing ridership. The bus density, the industrial ratio, the local population density and the subway density are the key explanatory variables impacting the bike-sharing ridership. The threshold effects of the built environment are explored based on partial dependence plots, which could improve bike-sharing system and provide policy implications for green travel and sustainable transportation.”

 

“The main contribution of this study is the development of a novel framework integrated with the XGBoost model to elucidate the influence of various built environment factors at both origins and destinations on OD bike-sharing ridership. Additionally, this study investigates the nonlinear relationships and threshold effects between built environment factors and OD bike-sharing ridership. The findings aim to enhance the alignment between bike-sharing travel behaviors and the built environment, fostering better adaptation in future urban mobility planning. A focus is placed on community street-level bike-sharing systems to achieve more refined management of green travel initiatives.

Fig.1. illustrates the framework of this study. The framework consists of three main components: (1) Data Input, which includes the collection and processing of built environment variables and bike-sharing ridership data at the community street level; (2) Model Construction, focusing on the application of the XGBoost algorithm to analyze the relationships between built environment factors and bike-sharing usage; and (3) Results Analysis, which involves the interpretation of nonlinear effects and the identification of thresholds for various built environment factors.

FIGURE 1 Schematic diagram of the research framework     ”

 

 

3. The citation of relevant references regarding formulas is missing.

 

R3: Thanks for the comments. We have reviewed the manuscript and added the missing citations related to formulas. All references are now complete and accurately cited.

 

4. The following labels on page 5 are confusing, please carefully check them.

R4: Thanks for the comments. The GIS data of the study area is a crucial factor because we are investigating the relationship between the built environment factors and bike ridership. Therefore, we included the study area as part of the data section, where we introduced the basic characteristics of the city and explained the reasons for selecting this city as the study area. We have carefully checked and corrected any confusing labels to ensure they are understandable and correctly aligned with the text.

 

 

5. The units of the following values in Table 2 are missing, please carefully check them.

 

 

 

 

 

R5: Thanks for the comments. The units for all values in Table 2 have been added in the Variable Description column to ensure that all data presented in the table are clear and interpretable.

 

“TABLE 2 Variable definitions and statistics

Variables	Variable Description	Mean	S.D.	Min	Max
Orders
Daily OD bike-sharing ridership	Number of bike-sharing ridership from December 21st to 25th in 2020	9.41	42.01	0.25	1747.75
Built environment
Population desntiy	Population/area size (person per km2)	25118.58	16232.40	9.75	84332.96
Localpopulation density	Local population/area size (person per km2)	14888.19	12646.27	0	61492.02
Transportation density	Number of transportation facilities/area size (facility per km2)	93.62	70.81	1.14	347.06
Public facilities and services density	Number of public service facilities/area size (facility per km2)	173.04	125.36	6.67	560.70
Subway density	Number of subway stations/area size (facility per km2)	0.39	1.07	0	6.54
Bus density	Number of bus stations/area size (facility per km2)	6.52	4.39	0	25.45
POI density	Number of POI/area size (facility per km2)	1097.31	861.02	19.86	4594.82
Commercial ratio	Number of commercial locations/number of POI	59.91%	12.22%	25.86%	86.94%
Residential ratio	Number of residential locations/number of POI	6.20%	2.87%	0.57%	18.84%
Industrial ratio	Number of industrial locations/number of POI	6.74%	5.90%	0.40%	34.40%
Area	Area of every tract (km2)	1.02	1.57	0.08	11.69
Road density	Length of the road/area size (km/km2)	5.92	4.58	0	23.14
Travel Impedance variable
Duration	Average riding time for OD bike-sharing orders (s)	1154.35	800.01	70.00	10069.00

”

 

6. In Section 5, regarding how to select the parameters of machine learning is missing. Please carefully check them.

 

R6: Thanks for the comments. The selection of built environment variables was guided by their potential influence on bike-sharing ridership, based on existing literature and “3D” urban planning principles. We have expanded the manuscript to include a detailed description of the rationale for built environment variables in the section of the literature review and data description.

 

“Built environment refers to the artificial space environment made for human activities, including land use, urban design, transportation infrastructure and other factors. Accurately depicting the built environment is the key to explore the impact of the built environment on travel behavior. The built environment is measured by the three Ds, namely, density, design, land use diversity. Density measures include transportation density, public facilities and services density, subway density, bus density, point of interest (POI) density (Gaode map, 2021), the ratios of residential, industrial, and commercial land use, population density, and local population density. Design refers to the measurement of the characteristics of the road network in the area, measured by the road density. Land use diversity measures the mixing degree of different land uses in the region. Its measurement method is based on regional entropy and grid, and the entropy index ranges from 0 to 1, where the smaller the value, the lower the mixing degree, and 1 means that all land use types are allocated equally here [45]. ”

 

7. Many existing methods, which are widely utilized these days to solve several real world problems including the described issues, multilayer neurocontrol of high-order uncertain nonlinear systems with active disturbance rejection, asymptotic tracking with novel integral robust schemes for mismatched uncertain nonlinear systems and so on. Therefore, the authors should further clarify the progressiveness of this work.

 

R7: Thanks a lot for the comments. We have expanded and elaborated the contribution in the introduction section. Besides, the comparison with other models is a very interesting perspective and we have added in the manuscript for the future research direction (as shown in Line 11-19, Page 28).

 

“Of course, there are still some deficiencies in this paper and the following aspects could be further explored in the future. In this paper, our research case is a typical bay city, and it is necessary to select more plain cities with different geographical and geometric characteristics to analyze and compare the heterogeneity of the nonlinear relationship between the built environment and bike-sharing ridership. Furthermore, different methods could be compared, such as multilayer neurocontrol of high-order uncertain nonlinear systems and integral robust schemes for mismatched uncertain nonlinear systems, could be compared. The impact and mechanisms of the built environment on the competition and cooperation relationship between bike-sharing and other traffic modes could be further research directions.”

 

 

8. The conclusion needs to be further condensed. The format of the references needs to be adjusted to MDPI format.

 

R8: Thanks for the comments. The conclusion has been condensed to focus on key findings. We have also ensured that the reference format is consistent with MDPI guidelines.

 

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

Thanks for your contribution.

Author Response

Thank you for the valuable feedback on our manuscript. We have expanded the introduction and literature review sections to enhance the manuscript's comprehensiveness.

Reviewer 3 Report

Comments and Suggestions for Authors

Dear authors,

Thank you for addressing my comments. The manuscript is significantly improved.

With kind regards,

Author Response

We deeply appreciate your comment on our manuscript.

Reviewer 4 Report

Comments and Suggestions for Authors

The repetition rate of this article is too high, please revise it carefully.

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

We deeply appreciate your consideration of our manuscript. Thank you for bringing this to our attention. We have thoroughly reviewed the manuscript to ensure that the content is clear, concise, and free of unnecessary repetition. We have carefully reviewed the word choice and expressions throughout the manuscript to enhance its readability and clarity.