Downscaling Switzerland Land Use/Land Cover Data Using Nearest Neighbors and an Expert System

Round 1

Reviewer 1 Report

Dear Authors,

the manuscript does not contain any issue oriented on the remote sensing, any new approach to image acquisition, processing or analysis. You have much more GIS analyses than remote sensing.

So, from the point of view of Remote Sensing readers, the presented text is not interesting. I would like to suggest other MDPI journals e.g., Land or Sustainability.

But I think that you need to add much more details oriented on methods, which are used by other researchers developing the topic; it should be presented in the Introduction (a theoretical background)

Discussion is significantly too general, you need to add much more details, because you present a lot of well-known opinions.

Methods should be better described, a chapter Validation is significantly too general, and accuracy assessment and validation of used models are important in case of all spatial analyses.

Some figures need to have bigger fonts, e.g.  please try to read values presented on the graphs (Figure 7). Figures 5, 6 have a lot of empty spaces on the left and right sides, and the maps are so small, legend is very small, too.

Please, look at guidelines, e.g. you need to use short names of the cited journals (References).

Best regards

Reviewer

Reviewer

Author Response

You will find our answers in the attached Word document.

Author Response File: Author Response.docx

Reviewer 2 Report

My comments were proper addressed. However, in the revised version I see one aspect that I consider to modify. There are mixed acronyms in the manuscript. In the text there is “LC/LCU” (e.g. line 12), “LC/LU” (e.g. line 15), and at the same time title got different order of these words “Land Use/Land Cover”. In line 64 there is “Land Cover and Land Use Change (LC/LUC)”. That could be misleading for readers. However, that does not influence high quality of this research.

Author Response

You will find our answers in the attached Word document.

Author Response File: Author Response.docx

Reviewer 3 Report

Reviewer’s report

on the manuscript entitled

Downscaling Switzerland Land Use/Land Cover data using nearest neighbors and an expert system

Submitted to Remote Sensing MDPI journal (Manuscript ID: remotesensing-1629517)

General remarks

I have got the manuscript named “Downscaling Switzerland Land Use/Land Cover data using nearest neighbors and an expert system” for the second time. In this manuscript the authors downscaled the land use and land cover (LU/LC) information for Switzerland by integrated the LU/LC having scale of 100m with the digital base map having scale of 1:25,000. They applied this method for three different periods to evaluate LU/LC change. The authors try to improve the manuscript, however, still there are several typos and linguistic mistakes existed.

• My main problem with this manuscript is that the authors used inverse distance weight (IDW) method to downscale the LC/LU map. As I mentioned in the previous report that “I disagree with changing the discrete LU/LC map using inverse distance weight (IDW) method. Where the discrete format means changing without any continues weight. In other words, the neighbor pixel is unexpected. Therefore, using the IDW downscaling for the LU/LC is not acceptable (for me at least).” The authors cited (lines #121-134) that the downscaling have been used by several papers. That is right, however, these papers downscaled the continuous data, such as temperature, rainfall, and soil moisture. While Remm [82], used the land LCLU for prediction.   
• I have asked to modified the abbreviation of the land cover and land use; however, the authors sometimes wrote it as LC/LU (lines #64, 71, 79, 80, etc.), and other times LU/LC (lines #14, 70, and 192). The author used the abbreviation of LC/LUC for the term of land cover and land use change but there are some sentences include the term “LC/LU change” (lines #104, 394, 457).
• The manuscript is written in a well-readable and clear English, however, it has also some formal problems. Therefore, the manuscript needs to read for the second time (e.g., uppercase is used without any necessary (e.g., lines #108-109). Moreover, some mixing in the British and American English (e.g., line #133: “greyscale” should be changed to “grayscale”). Also, some places missing to the comma (e.g., line #61 between “transport” and “and”, line #68 between “[25]” and “or”, line #108 between “approaches” and “such”, and so on).

In summary, my suggestion is to reject the manuscript.

Author Response

You will find our answers in the attached Word document.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Dear Authors,

thank you very much for your revision, I think that the Land journal is the proper one. I have some minor comments:

• all equations need to be cited in the main text,
• the big table ( Figure 4, 10th page of the manuscript) should be presented as a full page table in the Appendix, the current version is not readable,
• figure 6 has too big fonts of the year, and too small for the legend units,
• figure 9 has too small fonts,
• Discussion should contain much more references directly comparing your more important achievements with references highlighting innovative solutions proposed by you.
• please add more conclusions from your studies, the current version is too general.

Best regards

Reviewer

Author Response

Please find our answers in the attached Word document

Author Response File: Author Response.docx

Reviewer 3 Report

Dear authors,

congratulations, the manuscript is improved a lot. Some issues related to the figures need to be fixed. The figures missing coordinates grid and north arrows, please modify them.

 

Author Response

Please find our answers in the attached Word document

Author Response File: Author Response.docx

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.

Round 1

Reviewer 1 Report

Dear Authors,

thank you very much for your manuscript. Reading your abstract I was excited because it is my research topic, but reading the content I was a little bit disappointed because the manuscript is much more oriented on GIS analysis not remote sensing, the readers of the journal like to read about new algorithms and image processing. Another point is that you present the text as a good report of an interesting experiment, there should be much more direct links with current state-of-the-art, you need to highlight  innovative solutions, which you used focusing on remote sensing, but please, consider if you should process the manuscript in the MDPI's Land journal, because from remote sensing point of view I cannot find any new contributions.

Best regards

Reviewer

 

Much more direct comments you can find in the attached manuscript

Comments for author File: Comments.pdf

Reviewer 2 Report

This paper presents a learning method, which could be assimilated to a case-based approach, for downscaling LC/LU information for Switzerland from a 100m lattice of points to a 25m resolution grid, taking advantage of an existing 1:25,000 digital base map and building an expert system defining possible correspondences between the base map and the land use categories. This method is then applied for three different periods of time to assess land use and land cover change. The purpose of this paper is important to generate detailed information for land use and land cover management and environmental studies. The paper is supported by the data and methodology available in the literature. The results are reasonable and useful for several applications. The paper is clearly presented.

Reviewer 3 Report

The paper presents an interesting research which fits to the scope of the journal. Below I present some minor comments which should be taken into account while improving the paper.

 

1. Line 62: Land Cover and Land Use Change was introduced as “LC/LUC”, however, later in the manuscript “LC/LUC” or “LC/LU” are used. Please unified it.
2. While introducing LC/LUC identification systems I suggest to mention also those approaches which are automatized in order to reduce time-consuming process of manual verification of data (see for instance: A framework for path-dependent industrial land transition analysis using vector data. European Planning Studies 2019 27(7): 1391-1412; Automatic generation of land use maps using aerial orthoimages and building floor data with a Conv-Depth Block (CDB) ResU-Net architecture. International Journal of Applied Earth Observation and Geoinformation 2022 107: 102678; and other papers in similar field).
3. As far as I am aware, MDPI style allows figures wider than column of text, therefore, I suggest to enlarge figure 1. It can increase visibility of the zoomed areas. Similarly figure 2 can be changed.

 

I encourage the Authors to correct the paper, as in my opinion it presents an interesting study and might constitute a valuable paper after improvements mentioned above.

Reviewer 4 Report

Reviewer’s report

on the manuscript entitled

Downscaling Switzerland Land Use/Land Cover data using nearest neighbors and an expert system

Submitted to Remote Sensing MDPI journal (Manuscript ID: remotesensing-1583482)

General remarks

I consider myself an expert in remote sensing, therefore I find the topic of the paper very interesting, and for the international readers, it might also deliver general and useful information. In other words, the method and the goal of the paper would fit the scope of the Remote Sensing journal. The authors downscaled the land use and land cover (LU/LC) information for Switzerland by integrated the LU/LC having scale of 100m with the digital base map having scale of 1:25,000. They applied this method for three different periods to evaluate LU/LC change. The manuscript is written in readable and clear English, however, there are several typos and linguistic mistakes existed. In summary, my suggestion is to reject the manuscript. In the below, I present some more detailed arguments to support my suggestion of rejection.

• I disagree with changing the discrete LU/LC map using inverse distance weight (IDW) method. Where the discrete format means changing without any continues weight. In other words, the neighbor pixel is unexpected. Therefore, using the IDW downscaling for the LU/LC is not acceptable (for me at least).    
• The manuscript is written in a well-readable and clear English, however, it has also some formal problems. Therefore, the manuscript needs to read for the second time (e.g., uppercase is used without any necessary (e.g., line #79). Also, there is a space after the comma (e.g., line #73). Moreover, some places missing to the comma (e.g., line #102 between “applications” and “such”).
• The abbreviations should come at the first time between two brackets after the full names that explain these abbreviations. Thereafter, it can be used without write the full names. The authors (in some places) used the abbreviations without gave the explaining (e.g., line #23 “HPC”, #215 “NA”) or they changed the abbreviations (e.g., land use land cover some time they write it as LU/LC (lines #12, 14, 15) and others LC/LU (lines #62, 71, 77, 350).