Assessing Land-Cover Change Trends, Patterns, and Transitions in Coalfield Counties of Eastern Kentucky, USA

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

The topic of this article had me interested. However, in my opinion, the execution left a lot to be desired. 

I made extensive notes in the PDF of the article included with the review. Essentially though, the problem is that there are several places where additional explanations would be beneficial – if not necessary.

The most prominent example is the discussion of land use/land cover changes between 2004 and 2019. It does seem possible for half of land classified as “developed” in 2004 to change to other uses – while the total amount of develop land doubled. While the Kappa accuracy scores demonstrate that this does not appear to be the result of misclassification, it does point to potential problems with different data sources over time or changes in the census block groups (which are modified every census) to technical issues.

This is the most prominent finding that may be correct based on the data but just does not make sense. In such cases, it is necessary to explain the unexpected – and in the case of land use discussions, usually there is some examples (providing “ground truthing”) to show why this information is true.

There are other issues with the paper as well. Some are similar analysis questions. Some are related to data selection. Others are more technical – from extra spaces to too small of legends on graphs.  All of these are the subject of comments on the attached PDF.

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

This paper presents an interesting piece of work on land cover change analysis using remote-sensing images and anciliary data. Authors appear to be well-versed in related data processing, information extraction, and change analyses.

 

However, it would be better if the following could be considered:

1)     Reference data collection. Furfther information is required about how training/test sample pixels were obtained. Was it necessary to select only pure pixels (at least relativeky speaking)?

2)     Also, probability sampling is strongly recommended for (change) area estimation as well as accuracy assessments. Given the time frame, if the sample data used were collected through simple random sampling (thus, post-stratification might be applied), precision in change area estimation 2004-2019 would be greatly enhanced. See “Estimating area from an accuracy assessment error matrix” (by Stehman 2013) for further detail.

3)     I don’t have objection to using Kappa coefficient of agreemnt as an accuracu indicator, But conventional indicators, such as OA, UA, and PA, should also be computed as reported.

4)     In use of RF, would it be beneficial to run a procedure of feature optimization.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

The study focuses on the impact of surface coal mining and reclamation on the landscape of eastern Kentucky, examining changes from 2004 to 2019 using Landsat images classified by a Random Forest Classifier. The paper is generally well-structured and the experiments are thorough. However, it could benefit from the following suggestions:

1.      In Table 1, some units are in meters, 'm', and feet. Please standardize the units.

2.      A Random Forest Classifier (RFC) was utilized to classify the Landsat imagery. Why not use more advanced deep learning methods? Additionally, how is the accuracy of the classification results measured, and what impact does this have on the accuracy of the subsequent analysis of changes?

3.      It would be beneficial to add geographic coordinates to Figures 8-10 and enhance the visuals of Figure 2.

4.      The paper's title is "Assessing Land Cover Change Trends," should there be a section analyzing future trends? If possible, extending the analysis beyond 2019 could provide insights into the long-term sustainability of the reclamation efforts.

 

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 4 Report

Comments and Suggestions for Authors

I have added a few comments in the attached version. I think that many parts of the paper should be discussed in a much more detailed way and improved

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

There are still a few questions to be answered. Most notably, if data availability or some other factor is the reason for the uneven time periods examined as part of this research (ranging from 2 to 6 years). 

But for the most part, the paper is immensely improved. The additional explanation provides the missing gap found in the original version.  And the other new details provide better context for the study. 

 

Comments for author File: Comments.pdf

Author Response

Thank you so much for your time and efforts for helping to enhance the quality of our work. Please see the attachement. 

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

The paper has been significantly improved after revisions; however, there are still some details that need to be refined by the authors:

l  In the sentence, "Letcher (1134 m3720 ft), Pike 27 (960 m3149 ft), and Perry (2762 m~520 ft) counties are the highest elevation points in the Eastern Kentucky region.” Please ensure consistent use of units (m/ft) throughout the text and check the rest of the manuscript for uniformity.

l  In Figure 4, it might be more appropriate and aesthetically pleasing to place the legend within the figure itself.

l  In the sentence, "The study area falls in the two ecoregions of Central Appalachian denoted by (69 in ecoregions map: (1) the Dissected Appalachian Plateau denoted by (69 d) and (2) the Cumberland Mountain Thrust Block denoted by [31]," the number "69" is sometimes within parentheses and sometimes not. Please standardize the formatting.

A recent study titled “Change Detection of Multisource Remote Sensing Images: A Review” could be cited. It will be available at

[1] Sun Y, Lei L, Li Z, et al. Similarity and dissimilarity relationships based graphs for multimodal change detection [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 208: 70-88.

Author Response

Thank you so much for your time and efforts for helping to enhance the quality of our work. Please see the attachement. with the answers and guide about revisions made in the manuscript as per your suggestions.

Author Response File: Author Response.docx

Reviewer 4 Report

Comments and Suggestions for Authors

Dear Authors,

                        please add a.s.l. to the altitudes in metres throughout the entire text

Author Response

Thank you so much for your time and efforts for helping to enhance the quality of our work. Please see the attachement and revised manuscript attached for the revisions made.

Author Response File: Author Response.docx