Spatiotemporal Variation and Driving Mechanisms of Land Surface Temperature in the Urumqi Metropolitan Area Based on Land Use Change

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Dear Authors,

Congratulations on your paper entitled “Spatiotemporal Variation Analysis of Land Surface Temperature in the Urumqi Metropolitan Area Based on Land Use Change.” The study addresses a very relevant topic by analyzing changes in LST in an arid metropolitan area over 20 years, which is certainly of great interest to the scientific community focused on remote sensing and urban planning.

The manuscript presents an interesting methodological basis. However, in order for the article to reach its full potential and publication standard, we have identified some crucial points that need revision.

The main methodological concern relates to the scale mismatch between MODIS LST data (1 km) and Landsat-derived LULC data (presumably 30 m), which directly impacts the validity of the contribution analyses. There is also a need for greater clarity in the definition of land use classes (such as “wasteland”) and in the visual presentation of the results.

All detailed comments, specific suggestions by section, and recommendations to strengthen the manuscript are available in the attached review letter.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This article has been a successful study in terms of topic and method selection.It can be published after the specified arrangements are completed.

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

The paper entitled “Spatiotemporal Variation Analysis of Land Surface Temperature in Urumqi Metropolitan Area based on Land Use Change” discusses the use of the spatiotemporal relationship between LST and Land use. Using 20 years of diurnal LST data, they investigated how land use change has influenced the thermal environment of Urumqi Metropolitan Area.  The following are the comments for this paper:

1. Now while the study itself has regional relevance, as and a sound methodological framework it lacks the discussion for a strong novelty. Please give a detailed description of the novelty of this research and include them in the paper.

 

2. The analytical designs used for this study are already well-established techniques commonly applied in UHI-Land use change research. This was also submitted to “Innovations – Data and Machine Learning” section of the Journal but there is a lack of discussion in the research framework on how machine learning was applied. I suggest discussing what part of the study incorporated any innovations or advancements compared to previous studies that are similar. This paper would benefit more from integrated advanced modelling for either analysis or prediction (e.g. XGBoost, Neural networks, SHAP).

 

3. The paper mentions a “coupling mechanism of land use type–transfer process–thermal environment effect,” but this mechanism is not actually developed. The analysis mainly describes observed spatial and temporal trends rather than constructing or testing a new conceptual or theoretical model. In other words, the study shows what happens (e.g., how LST changes with different land uses) but not why or how it happens in a way that could be generalized to other regions. As a result, the contribution is largely descriptive and empirical, adding case-specific evidence rather than advancing new theoretical understanding or a transferable framework.

 

4. There are also some referenced papers in the study that also discusses the UHI phenomenon in Urumqi. However, there are no direct comparison of the results of these previous studies to the current one. What are the new analyses in this paper that were not conducted in previous research? A clearer distinction between the present findings and those of earlier works would help highlight the study’s novelty and contribution to UHI research in Urumqi. Please expand the discussion section to include comparisons of your findings with previous studies in the same area or same type of region.

 

5. Figures: some of the legends on the figures (1, 8, 9, 11) are hard to read. Fonts should be bigger in the legends, and in the numbers in pie charts.

 

Overall, the paper provides useful insights into the long-term dynamics of LST and Land use. In an arid environment. However, the absence of the discussion of novelty, limited discussion of the methodological framework, lack of use of machine learning, and lack of comparison with other studies makes this paper very limited. I suggest major revisions in the paper before it can be considered for publication.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

After analyzing the new version, I confirm that the authors were exemplary in their response to the previous round of review. They have comprehensively and satisfactorily addressed all the main concerns raised.

I highlight the following points:

• Methodological Resolution: The most important critique, regarding the scale mismatch (MODIS vs. Landsat), was resolved with the clear description of the resampling method (majority sampling).

• Analytical Innovation: The authors not only corrected the problems but also significantly elevated the quality of the article by introducing a new robust analysis (XGBoost-SHAP). This provided the necessary depth to identify the "driving mechanisms" of LST, clearly distinguishing the diurnal and nocturnal impacts.

• Clarity and Visualization: All ambiguities (such as the definition of "wasteland") were clarified, and the data visualizations were improved (notably the replacement of pie charts with stacked bar charts, as suggested).

The manuscript is immensely improved, methodologically sound, and now presents a clear and actionable scientific contribution. In my opinion, the work fully meets the journal's publication standards.

Reviewer 3 Report

Comments and Suggestions for Authors

I have read the latest version of the manuscript and the author's responses to the comments. The paper was revised properly keeping in mind the biggest issues presented during the initial review. Comments about novelty and machine learning use were addressed. I have no further questions.  Congratulations.