Putting Abandoned Farmlands in the Legend of Land Use and Land Cover Maps of the Brazilian Tropical Savanna

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

All my comments and suggestions are contained in the attached file.

Comments for author File: Comments.pdf

Comments on the Quality of English Language

The level of English is satisfactory, but needs to be revised to make it more accessible to Land's diverse readership.

Author Response

"Please see the attachment."

 

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

This study utilized deep learning and Sentinel-2 imagery to conduct a detailed identification and mapping of farmland abandonment in the Brazilian Tropical Savanna, providing practical insights for regional land use monitoring. To enhance the impact of this paper, it is suggested that the authors consider the following points:

(1) Introduction

① Summarize the relevant methods used for abandoned farmlands identified in current research (line 65-75).

② Create a new paragraph before line 76 to clarify the FCNN method (its main application areas) and to state the innovative contribution of this research explicitly (moved line 83 to the new Paragraph).

(2) Methods

① The Methods introduction (lines 123-178) does not provide a sufficiently clear description of the study. Furthermore, it is recommended that concise titles be added to each step in the flowchart of Figure 2 to facilitate a clearer understanding of the technical workflow.

② It is suggested that the data sources, formats, and dates (lines 109-116) be presented in a separate table for clarity.

③ The methods used for validating identification accuracy should be added to this section.

(3) Discussion

A Discussion section is recommended.

① In this section, a comparison should be added between the identification accuracy of this study and that of existing methods.

② The reasons for abandonment should be clarified in this section. And it is recommended to move the content from lines 196-280 and Figure 8 from the Results to the part.

③ The study's potential applications and policy implications should also be elaborated in this section.

④ The limitations of the study should be discussed in a Discussion part. For example, the points in lines 321-324 would be more appropriately placed here rather than in the Conclusion part.

Author Response

"Please see the attachment."

 

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Dear authors, it is with great pleasure that I reread your article entitled "Putting Abandoned Farmlands in the Legend of Land Use and Land Cover Maps of the Brazilian Tropical Savanna." My recommendations have been taken into account. The text is now scientifically sound. There are just a few small elements to add and it will be fine overall.

1. The scientific logic behind the concept of "abandoned agricultural land" needs to be clarified and reinforced. This is the central point of the manuscript but is insufficiently justified.
2. Explain how the transition from grassland to shrubland represents abandonment rather than simply resting or rotation.
3. The recommendation on the transition matrix has not been sufficiently addressed. I recommend this author: Takada T, Miyamoto A, Hasegawa SF. Derivation of a yearly transition probability matrix for land-use dynamics and its applications. Landscape ecology. 2010 Apr;25(4):561-72.

Comments on the Quality of English Language

The level of English is satisfactory, but needs to be revised to make it more accessible to Land's diverse readership.

Author Response

Please, see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The author has completed the revisions. I have no further comments.

Author Response

Thanks a lot for helping us for such important comments. We appreciated very much.