Next Article in Journal
Conditional Feature Selection: Evaluating Model Averaging When Selecting Features with Shapley Values
Previous Article in Journal
Urban Planning with Rational Green Infrastructure Placement Using a Critical Area Detection Method
 
 
Technical Note
Peer-Review Record

Transformation of a Classified Image from Pixel Clutter to Land Cover Map Using Geometric Generalization and Thematic Self-Enrichment

Geomatics 2024, 4(3), 271-285; https://doi.org/10.3390/geomatics4030015
by Geir-Harald Strand 1,*, Eva Solbjørg Flo Heggem 1, Linda Aune-Lundberg 1, Agata Hościło 2 and Adam Waśniewski 3
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Reviewer 4: Anonymous
Geomatics 2024, 4(3), 271-285; https://doi.org/10.3390/geomatics4030015
Submission received: 15 May 2024 / Revised: 8 July 2024 / Accepted: 22 July 2024 / Published: 29 July 2024

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Semi-automatic land cover classification procedures are an interesting topic overall, so any new methods and developments that could be implemented on a large scale deserve to be shared among the scientific community. THere is, therefore, some merit in the authors' proposal.

However, I believe it is necessary to explain in more detail the statistical procedures outlined at the end of 3. Also, I recommend explaining in further detail hwo generalization procedures were carried out. The authors mention classification was performed by a random forest algorithm (in which environment) and that generalization was performed according to Strand et al., but how? Same exact procedures? Same software/programming language?

Finally, sections 4 and 5 are duplicated. Please revise those.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

The article introduces a generalized framework for converting a classified image from pixel clutter into a landcover map. This research holds substantial practical value in the field of land use remote sensing classification. The author is kindly requested to make the following modifications:

1.      Chapter 2: Materials and Methods: It is recommended to add a schematic diagram of raster generalization processes, including expansion, contraction, removal, and enrichment.

2.      Figure 3 demonstrates a reduction in the area of construction land when compared to the original classified image, as evidenced by the road section in the center. This raises questions about the limitations of these methods in addressing linear features.

3.      It is suggested to incorporate comparisons with alternative methodologies, including rudimentary classification post-processing techniques.

4.      Is this methodology applicable to diverse land types, including linear features and small-area features?

Author Response

Please see the atachment

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

The topic is interesting, while there are typos and poor sentences in the whole manuscript, which should be taken care of before submission. Here, I have several major questions/concerns that need to be explicitly addressed.

Major issues

1.        Your generalization process consists of five components: generalization methodology, enrichment, examination, conceptual improvement, and comparing statistics and accuracy, all of which are interconnected in sequential manner. However, I did not find a clear explanation of how your current work addresses the research problems. Instead, you treat the method section like a laboratory report! Please re-structure it.

2.        Your results section lacks a comparison with other validation parameters, making it challenging to assess the superiority of your findings over other products. Additionally, there's a lack of detail regarding the process-related your method. Could you elaborate on how to evaluated the quality of your results and discuss any improvements made during the research process?

3.        The discussion is well founded, while I still want to suggest you state the key issues in concise language and show the limitations of the study. Because results and findings of this work need to be framed in a broader context for your reader.

4.        In conclusion section, the contents lack strict logical inference, which cannot highlight the significance or implications of your main findings. Additionally, the limitations of the study and your future research or action also need to be stated.

 

Minor issues:

1. The figures have poor quality, please use high-resolution images.

3. When you illustrated your findings, please add figure number in detail (for example, Fig 3b or Fig 3 bottom), so that help readers get the essence of your work quickly.

4. I have realized that the manuscript has two discussion and conclusion, please check it.

Comments on the Quality of English Language

English writing and grammar still need to be polished

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 4 Report

Comments and Suggestions for Authors

In the review section, there are only 27 references in this paper, and none of them are after 2020 (the last three years), which shows that the authors lack a review of the field. In the Experiments and Results section, this paper lacks a description of the experimental data and the setting of the experimental parameters, making it difficult for the reader to obtain reliable guidance from it. The discussion section further lacks comparative analysis with other methods. Therefore, this paper must be completely revised and improved.

 

In addition, the figures and tables of the paper need to be improved:

 

1. table 1 and table 3 avoid crossing the border.

 

2. figures 2 and 3 use a variety of green colors, but it is difficult to distinguish them, for example, woodland broadleaf, woodland conifer, and low vegetation in the figures.

 

3. p13, the discussion and conclusions are repetitive, so we suggest the authors double-check them.

 

 
4. please add latitude and longitude grids to all the figures.

Author Response

Please see attachment

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

Thanks to the authors for their revisions, which have significantly improved the article's quality and readability. Nevertheless, there remain a few minor adjustments that need to be addressed:
1. The flowcharts in Figure 1 and Figure 2 should be relocated to the methods section, as these are the authors' novel methodologies; however, they represent technical procedures rather than results.

2. In the results part, it is suggested to add the display graph of different sub-steps, even if only a small area is studied.

Author Response

Please see attachment

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

Thank you for considering my feedback. Your manuscript is quite clear.  I have only one comment:

  Please review the guide for authors to ensure that your body text adheres to the prescribed formatting guidelines. Additionally, format the references according to the specifications outlined in the guide for authors.

Author Response

Please see attachment

Author Response File: Author Response.docx

Back to TopTop