Mapping Local Climate Zones (LCZ) Change in the 5 Largest Cities of Switzerland
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe authors mapped LCZ in 5 cities of Switzerland. The research methodologies are reasonable, and the findings are interesting. However, there are still some aspects that should be improved to make the paper publishable. I focus here only on some points, which are hopefully easy for the authors to take into account in the revision.
1. Line 46-47, there are many factors influencing UHI effects, such as land cover, urban morphology, and socioeconomic factors, more details can be given. There are many works related to the topic, as follows. 1) doi: 10.1016/j.scs.2022.104374, 2) doi: 10.1016/j.scs.2024.105588.
2. Line 75-84, to my knowledge, it seems inadequate, because there are many works mapped the LCZ at global, national, and urban scales. Please highlight the innovation.
3. Sec 2.1 - please emphasize the reasons for choosing the study area, e.g., typicality.
4. Figures - it is good to add the longitude and latitude.
5. Line 215-216, it is good to add more details to introduce the workflow.
6. The authors pointed out that ‘a total of 65 Regions of Interest (ROIs) per class were gathered over stable areas (i.e. no change)’, and 70% used to train the model. However, the quantities shown in Figure 3 are inadequate.
7. Check the expression, e.g., Figure F3, F4?
8. The authors also exhibited the accuracy, in my opinion, the accuracy is low. I don't think such accuracy is sufficient for subsequent analysis.
9. The resolution of Sentinel is better than Landsat. Although the works showed that the Sentinel displayed superior performance, I think it's largely inevitable.
Author Response
We thank the reviewer for his valuable comments and we carefully addressed them.
You will find our answers in the attached Word document.
Author Response File: 
Author Response.docx
Reviewer 2 Report
Comments and Suggestions for AuthorsThis work analyses the Mapping Local Climate Zones (LCZ) change in the 5 largest cities of Switzerland. The work is interesting. In the next points, I suggest some improvements before it is published.
The contribution of the state-of-the-art should be clarified.
The figures should be improved. See as an example figure 8 and 9.
Figure 2, as an example, should be more explained.
When one figure is divided in two parts, a) and b) should be added in the legend and the sub-titles should be added in each one. See as an example figure 3. In this case the title “Training samples” and “Testing samples” should be removed to the figure and add in the legend as a) Training samples and b) Testing samples. See also as other example the figure 4.
In figure 10 the same methodology should be applied and all sub-figures should be placed in the same page.
In line 365, figure F3 should be revise.
The input of the case studied should be added. Use as an example a table.
More details about the references should be added. See as an example, [15,16], [17,18], [10,22,23], [26-28] …
Table 3 should be more explained. Add the more details about the methodology applied in the paper. In this point the RF algorithm, and other methodologies should be more explained.
In the abstract and conclusions more quantitative conclusions should be added.
Comments on the Quality of English Language
Moderate editing of English language required
Author Response
We thank the reviewer for his valuable comments and we carefully addressed them.
You will find our answers in the attached Word document.
Author Response File: Author Response.docx
Reviewer 3 Report
Comments and Suggestions for Authors- How does the growth of urban populations specifically impact the urban heat island (UHI) effect in different types of urban environments?
- In what ways might the urban heat island effect influence socioeconomic disparities within cities?
- What are the potential limitations of using satellite Earth Observation (EO) technologies in studying urban heat islands, especially in terms of data accuracy and resolution?
- How might the classification and analysis of Local Climate Zones (LCZs) differ in cities with unique geographical and climatic conditions compared to more generalized urban areas?
- What are the practical challenges urban planners face when attempting to implement UHI mitigation strategies based on LCZ maps?
- How do differences in urban morphology, climate, and socioeconomic factors across regions affect the applicability of LCZ classification schemes globally?
- How can the integration of LCZ maps and UHI data improve urban policy-making and public health strategies?
- Given the dynamic nature of urban environments, how frequently should LCZ maps be updated to maintain their relevance and accuracy?
- What interdisciplinary collaborations are essential for the successful implementation of region-specific LCZ classification and UHI mitigation strategies?
- How do current LCZ classification methodologies account for ongoing urban development and land use changes, and what improvements could be made?
Have you considered the potential impacts of atmospheric conditions (e.g., haze, cloud cover) on the accuracy of your satellite imagery analysis? How do you plan to mitigate these impacts?
How do you ensure the temporal alignment of satellite images from different years given potential differences in the date and time of capture?
Given the subjectivity in visually identifying LCZ classes and creating training/testing areas, how do you address potential biases? Are there any automated or semi-automated methods you could incorporate to reduce this subjectivity?
How does the choice of machine learning algorithm (e.g., Random Forest) influence the accuracy and reliability of your LCZ classification? Have you compared it with other algorithms (e.g., SVM, CNN)?
The Overall Accuracy, Producer’s Accuracy, and User’s Accuracy provide a good measure of classification performance, but have you considered using additional metrics such as Cohen’s Kappa or F1 Score for a more comprehensive assessment?
What are the limitations of your chosen accuracy assessment metrics, and how do you address them in your analysis?
Building height data is missing for Zürich and Basel-Land. How does this absence affect your classification results? Have you considered any alternative sources or methods to estimate building heights?
What are the challenges and limitations of integrating Google Earth and Google Maps data into your LCZ mapping process?
How do you account for changes in land use or urban development between the different years of study? How do these changes impact your LCZ classification and subsequent analysis?
Are there any seasonal variations within the selected May to September period that could influence your results? How do you address these variations?
How do the urban characteristics and climatic conditions of the five cities (Zürich, Geneva, Basel, Lausanne, and Bern) influence the LCZ classification results? Have you conducted any comparative analysis to highlight these differences?
What specific urban planning or environmental policies in these cities could influence the observed changes in LCZs?
How do you ensure that the observed changes in LCZs are primarily due to urban heat island effects rather than other environmental or socio-economic factors?
Have you conducted any ground-truthing or field verification to validate your remote sensing-based LCZ classification results? If not, how do you plan to address potential discrepancies?
How can your LCZ maps be utilized by urban planners and policymakers to mitigate the urban heat island effect? Are there any specific recommendations you can provide based on your findings?
What are the potential limitations of your study in terms of its generalizability to other cities or regions with different climatic or urban characteristics?
Given the identified limitations in the current methodology, what are some specific improvements or innovations you plan to explore in future research?
How can the integration of newer satellite technologies or higher-resolution data enhance the accuracy and reliability of LCZ mapping in future studies?
How do you envision the broader application of your LCZ classification approach in other areas of urban climate research, such as air quality assessment, flood risk analysis, or green infrastructure planning?
What are the ethical considerations in using remote sensing data for urban climate studies, particularly in terms of privacy and data accessibility?
Comments on the Quality of English LanguageThe manuscript is written in clear and concise English, with only minor grammatical errors and typographical issues. The language used is appropriate for an academic audience, and the technical terms are well-defined and consistently used. However, some sentences could be refined for better clarity and readability. Overall, the quality of the English language is good, and the manuscript is easy to follow. A thorough proofreading and minor edits will enhance the overall presentation.
Author Response
We thank the reviewer for his valuable comments and we carefully addressed them.
You will find our answers in the attached Word document.
Author Response File: Author Response.docx
Reviewer 4 Report
Comments and Suggestions for AuthorsIn the paper the authors presented the process to classify five Swiss cities into local climate zones. The paper is not recommended for publication before the following comments are taken into account/
(1) The five Swiss cities are presented individually, without an integration that includes a numerical comparison across them or an empirical study relating to their individual parameters.
(2) A Literature Review section is needed, where the authors should clearly explain what is new in this paper.
(3) Details are needed for how an error matrix is built in both Sub-sections 2.3.3 and 3.2.
(4) The authors should explain the reasons behind the LCZ change in each of the five selected cities.
Author Response
We thank the reviewer for his valuable comments and we carefully addressed them.
You will find our answers in the attached Word document.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsAll the comments have been addressed, and it can be accepted.
Reviewer 2 Report
Comments and Suggestions for AuthorsIn the actual version, in general, all suggestions given by the reviewer was commented.
Comments on the Quality of English LanguageMinor editing of English language required.
Reviewer 3 Report
Comments and Suggestions for AuthorsThe article has been significant and now it can be published in the journal.
Reviewer 4 Report
Comments and Suggestions for AuthorsThe authors have improved the paper according to reviewers' comments.
