AgriSen-COG, a Multicountry, Multitemporal Large-Scale Sentinel-2 Benchmark Dataset for Crop Mapping Using Deep Learning

Round 1

Reviewer 1 Report

In this paper, author propose a new large-scale benchmark dataset for crop type mapping based on Sentinel-2 data (AgriSen-COG).

Public Comment section:

1.   In the abstract, author should mention the deep learning models applied on these datasets and their performance.

2.   References from [75] to [79] should be reformulated

3.   Resume the main difference between this paper and the proposed papers given below in additional references.

Additional References:

[1]Sykas, Dimitrios & Sdraka, Maria & Zografakis, Dimitrios & Papoutsis, Ioannis. (2022). A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning.

[2]Komisarenko, V., Voormansik, K., Elshawi, R. et al. Exploiting time series of Sentinel-1 and Sentinel-2 to detect grassland mowing events using deep learning with reject region. Sci Rep 12, 983 (2022). https://doi.org/10.1038/s41598-022-04932-6

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear Author,

I have completed a thorough review of the manuscript titled "AgriSen-COG, a Multi-country, Multi-temporal Large Scale Sentinel-2 Benchmark Dataset for Crop Mapping using Deep Learning". Based on my assessment, I recommend this manuscript for publication in the Remote Sensing journal.

The introduction is clear, providing a comprehensive overview of the current context and the paper's overall contribution to the field of remote sensing and artificial intelligence. 

The author has also successfully given a concise summary of the current datasets and compared them against theirs, providing an enlightening context for the readers.

Moreover, the paper presents a good amount of literature review on two crucial matters - image datasets and the necessity of deep learning methods. 

The author has conducted experimental results, noting the metrics obtained on this dataset, which will undoubtedly serve as a basis for future research comparisons. 

In terms of linguistic presentation, the English language used in the manuscript is clear and easy to follow, with no need for extensive revisions. 

Lastly, the title and abstract are concise and informative, and highlight the significant aspects of the research, attracting potential readers to engage with the content of the paper.

Considering the manuscript's comprehensive nature, and the overall importance and necessity of more curated datasets in the remote sensing domain, I recommend this paper to be accepted in the Remote Sensing journal.

Author Response

Dear Reviewer,

Thank you for taking the time to review my manuscript. Grateful for your insights from the submitted manuscript.