Land Cover Classification Based on Double Scatterer Model and Neural Networks
Round 1
Reviewer 1 Report
This paper proposes a land cover classification method based on double scatterer model and neural networks. The reviewer’s comments are as follow.
1) Please divide the introduction into two separate sections: Introduction Section and Related works Section. In the introduction please clearly mention about the main contributions with bullets.
2) In introduction, for the sentence of “ Land cover classification is one of the major topics being investigated in the field of Remote Sensing” please cite some research such as
[1] A New Algorithm for Land-Cover Classification Using PolSAR and InSAR Data and Its Application to Surface Roughness Mapping Along the Gulf Coast, IEEE Transactions on Geoscience and Remote Sensing , vol. 60, 2021
[2] Hyperspectral Image Classification Using A Spectral-Spatial Random Walker
Method", International Journal of Remote Sensing, 40:10, pp. 3948-3967, 2019
[3] Land - Use and Land - Cover Classification Methods: A Review, 2021 Fourth International Conference on Microelectronics, Signals & Systems (ICMSS).
3) Please provide a Section for Data description and insert the features of your dataset in this Section. If it is possible, please refer the online website of datasets for readers.
4) Please provide a sub-section to introduce criteria for quantitative and qualitative evaluations. For quantitative evaluation, please provide at least 2 criteria and for qualitative criterion please insert classification map.
5) Please compare your proposed method with at least three techniques having been published recently.
6) In Experimental Results Section, please provide reference number of methods in Figures and Tables.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
The manuscript’s topic is appropriate for the journal. The authors proposed a Double Scatterer Model and Neural Networks for Land Cover classification using a fully polarimetric Single Look Complex (SLC) dataset. The issue considered in the manuscript is important to the concerned community. The scientific approach is acceptable and it is scientifically sound and deserves to be published in Geomatics Journal with minor changes.
The abstract needs to be developed by adding the obtained results. Also, it is recommended that the section titled "Results" be presented separately from the section titled "Conclusion," and that it includes a in-depth explanation and discussion of the results that were achieved through the application of the methodology described in the section titled "Proposed Classification Procedure."
>> Figure 1: It is possible to add the arrow pointing north.
>> Figure 2: The figure is not completely clear, the coordinates, scale, and legend need to be added, and it would be ideal if an inset map was provided as well.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The current manuscript has been revised according to the comments. However, there are still some concerns that should be revised.
The reviewer’s comments are as following.
1) One of important criteria for classification research is classification map. Please insert classification maps of proposed method and compared techniques to prove the performance of your technique and discuss about them.
2) Please arrange the comparison table and add the results of proposed method and discuss about them.
3) Please insert time consumption for all methods and discuss about it.
4) Please mention whether all methods were run on the same computer.
5) Please show your innovation in the introduction Section with bullet and why this innovation is important.
6) Your method has been compared with only one quantitative criterion. Please add another criterion such as kappa.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
