Mapping and Monitoring Spatio-Temporal Patterns of Rainfed Agriculture Lands of North Darfur State, Sudan, Using Earth Observation Data

Round 1

Reviewer 1 Report (Previous Reviewer 4)

Dear Authors

I have reviewed your manuscript, entitled Mapping and Monitoring Spatio-Temporal Patterns of Rainfed Agriculture Lands of North Darfur State, Sudan, Using Earth Observation Data. The study aimed to map and monitor the Spatio-temporal patterns of rainfed agriculture using RF, from 1984 to 2019 In North Darfur State. The study provides an interesting topic amid the lack of data infrastructure.

In my view, several improvements are required for this manuscript and I suggest as following

-authors need to improve the abstract. I do not see the connection between sentences Line 11 to line 15.

-authors should reduce the introduction section (too long) by omitting irrelevant information. 

-authors may improve Section 2 and remove redundancy. Remove also unimportant and irrelevant information such as Table 1, Table 2, and Table 3. Authors should focus only on rainfed agriculture. Other land uses are irrelevant, considering the objective of this study.

-Authors again should present only rainfed agriculture in Section 3. 

-The map is unclear as to much noise from other types of land use. on map show only rainfed data and highlight changed areas. 

-Table presentation should be modified and can be one table and focus only on rainfed. The current table presentation of Table 6 to Table 9 is tedious

-Omit also redundancy data presentation in text and table. 

-in section 4, discuss map accuracy assessment and its consequences. Figure 4 and Table 5 need more explanation.

-in section 4, also discuss the limitation of this study

-in section 5, improve the conclusion. The conclusion address the research objective and only includes topics presented in the result and discussion sections. 

-Authors should make sure the abstract does not copy the conclusion, and vice versa. 

-detail comments and suggestions can be found in the attached annotated pdf

best regards

Comments for author File: Comments.pdf

Author Response

We would like to thank you for your valuable comments and suggestions that have now greatly improved the manuscript. We have gone through the comments one-by-one and revised the manuscript and responses to each comment are set out in the table in the responses to the reviewer upload below. 

Author Response File: Author Response.docx

Reviewer 2 Report (Previous Reviewer 2)

Authors have well addressed my concerns in the resubmitted manuscript.

Author Response

 Authors have well addressed my concerns in the resubmitted manuscript.

Reviewer 3 Report (New Reviewer)

The manuscript presented is well written and well structured only minor revisions have to be performed before going ahead in the pubblication phase. If authors will follow the suggestion given I will certainly recommend this manuscript to be published on Land.

The introduction is a little bit too long I sugget you to try to sum up some parts. Moreover there is a lack concerning on Mapping and Monitoring Spatio-Temporal Patterns in land cover changes in Africa and also worldwide considering climate change, therefore I strongly advice to include in the references all the works below in order to fill this gap in the introduction and deeply improve the quality of your work. Here they are:

- https://doi.org/10.3390/cli9030047

- https://doi.org/10.3390/rs12213542

- https://doi.org/10.3390/land10121368

- https://doi.org/10.3390/ani12081049

- https://doi.org/10.1117/12.2533110

- https://doi.org/10.1080/01431161.2021.1992035

- https://doi.org/10.1007/978-3-030-87007-2_5

Then I sugget to include in each map the EPSG or the datum (in the masp or in the caption section)

Finally, lease better describe the software adopted to realize the whole processing and the settings adopted.

All the other parts are fine!

Author Response

We would like to thank you for your valuable comments and suggestions that have now greatly improved the manuscript. We have gone through the comments one-by-one and revised the manuscript. Responses to each comment are set out in the table (responses to comment) upload below.

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

The authors presented an interesting study on changes in Rainfed Agriculture Lands of North Darfur State during 1984-2019. 

However, the results from only satellite remote sensing didnot support the finding in the conclusion. Additional data are needed to support the claim that "Population growth and climate hazard (drought and desertification) are considered the main factors of agricultural land use changes in North Darfur State over the period 1984-2019". Furthermore, the major contribution of the study need to be refined. The presentation of the study also needs major revison.

1. It is better to add the country name after North Darfur State in the title. 

2. Abstract: Too much background information. The main results and finding are drowned.

3. Line 171. Why not use the radiometrically corrected Landsat products?

4. Line 192. It is better to show the spatial distribution of the samples.

5. Section 3.1 and 3.2.  Random forest is not a new classifier. It is not necessary to show such detailed results about the algorithm. 

6. The presentation of section 3.5 is poor. Too much redundant detail. It is difficult to see the most important results.

7. The major conclusion needs more support by the results from the authors, but not from literature.

Reviewer 2 Report

This study used multitemporal Landsat images to analyze dynamics of the rainfed agriculture in North Darfur State from 1984 to 2019. Random forest method was applied to perform the land use classification. Generally, this manuscript was well written and well structured. Personally, I recommended this manuscript to be published in Land after minor revisions.

Line 25: Images should be images.

Line 149: Improve the resolution of all figures. In addition, the labels should be inside the frame.

Line 159: 176 scenes were used. Suggest authors to provide these scenes' ID as a supplementary materials.

Line 190: In table 2, suggest authors to provide the typical images of each land use types.

Line 196: In section 2.4, suggest authors to provide formulas of random forest machine learning algorithm. Same to section 2.5, change detection method should also be provided.

Reviewer 3 Report

·   ·         The contribution and novelty of the work are absent. Major issues presented in this workout are within typical applications. The paper represents a traditional classification exercise using random frost (No contribution and No methodology). At least 2- 3 artificial and machine learning methods should be used and compared to validate the efficiency of the results

 ·         Standard elements of the abstract were not transparent and vague. This includes main objectives, methodology, contribution, and main results. For instance, some details sound trivial to be included in the abstract “example, the severe droughts and famine in Darfur, Sudan, during the 1970s, 1980s and 18 mid-1990s have repeatedly resulted in violent clashes between nomadic tribes and resi-19 dent farmers, causing large transboundary environmentally-induced migrations.”

  ·         The research could have some value if the authors consider rainfall Time series analysis and seasonality patterns in relation to drought.

 ·         The tables and illustrations were not appropriate. Graphs and visual interpretations were barred

o   Table 1: very well know information that has been published on many websites. This information was not used significantly to illustrate any issue in this research.

o   Table 3: just numbers that cannot be interpolated; why charts and visual aids were created  !!

 ·         The section related to optimization of Random Forest Classifier, including Figure 2, was low quality and poorly illustrated

 ·         The Authors lack knowledge of Remote Sensing information and spectral indicators. A brief literature review can figure out the NDVI. The authors dedicated a whole section of this paper to review the relative importance of Landsat bands in discriminating between different rainfed agriculture without any breakthrough . 

Reviewer 4 Report

Dear Author

This is a nice manuscript, and I believe you have worked hard to finalize it.

The result is essential, but presenting results is also important.  You write the manuscript for the reader, not for you.

You may improve the manuscript your manuscript and may consider my following comment and suggestion

Abstract

Authors should re-check if it is 200 words.

I don’t think that the sentence.  “ For example……migrations” is irrelevant in the abstract.

Introduction

Authors should keep in mind that one paragraph is one idea or topic.

Authors should check and omit redundancy and connectivity;

Line 57-60 seem redundancy with Line 69-72

Line 103-105 seem to be a standalone paragraphs.

Authors should improve the introduction for better flow

Material and methods

Authors use common, standard, existing methods.  Nothing is new.

Results

Authors should focus on the study; based on the objective, this study consent on mapping and monitoring, not the methodology.  Hence, section 3.1 and 3.2 is irrelevant.

Authors may combine Figure 4 to 7 into one figure.

Authors may create one additional table presenting  coverage of LULC based on the period in section 3.4

Authors may create one additional table presenting coverage change in section 3.5

Authors may combine section 3.5 and 3.6 because both look like redundancy

Discussion

Authors should rewrite and observe irrelevant and redundancy.

Line 501-507 seems irrelevant.  The study was to map and monitor rain-fed agriculture, not to discuss the use of Landsat and method.

Line 507-513: redundancy.  See Line 107-112

Conclusion

The authors should answer the research question in conclusion.  Line 573-578 is not relevant.

Reference:

Authors should verify and improve the reference list; several  entries use uppercase in the title (16), and several have no complete reference item (for example, 33, 30, 23, 20, etc.)

Comments for author File: Comments.pdf