Using Vector Agents to Implement an Unsupervised Image Classification Algorithm

Round 1

Reviewer 1 Report

No further questions to the authors.

Author Response

Thank you for checking the revised version.

Reviewer 2 Report

Dear editor,

I checked the paper carefully and in my opinion it is interesting work now and have improved a lot.

However I still have some minor comments before the paper to be accepted.

However, I still think that it lack the recent literature review especially regarding the machine learning techniques. I would suggest author to improve the introduction section by reviewing the recent papers, for example I copy some relevant works here..

Feizizadeh, B., Kazamei, Garajeh, M., Blaschke, T., Lakes, T.,2021. A deep learning convolutional neural network algorithm for detecting saline flow sources and mapping the environmental impacts of the Urmia Lake drought in Iran, Catena, 105585.

Kazemi Garajeh, M.,  Malaky, F.,   Weng, Q.,  Feizizadeha, B., Blaschke, T., Lakes, T.,2021. An automated deep learning convolutional neural network algorithm applied for soil salinity distribution mapping in Lake Urmia, Iran, Science of The Total Environment, doi.org/10.1016/j.scitotenv.2021.146253.

 The conclusion section also needs to be improved and the stat of art to be highlighted. I consider it as progressive research in remote sensing but it ha to be pointed out in this section. Especially, the transferability of methods for future studies has to be acknowledge.

Author Response

“I checked the paper carefully and in my opinion it is interesting work now and have improved a lot. However I still have some minor comments before the paper to be accepted. However, I still think that it lack the recent literature review especially regarding the machine learning techniques. I would suggest author to improve the introduction section by reviewing the recent papers, for example I copy some relevant works here. 
Feizizadeh, B., Kazamei, Garajeh, M., Blaschke, T., Lakes, T.,2021. A deep learning convolutional neural network algorithm for detecting saline flow sources and mapping the environmental impacts of the Urmia Lake drought in Iran, Catena, 105585. 
Kazemi Garajeh, M.,  Malaky, F.,   Weng, Q.,  Feizizadeha, B., Blaschke, T., Lakes, T.,2021. An automated deep learning convolutional neural network algorithm applied for soil salinity distribution mapping in Lake Urmia, Iran, Science of The Total Environment, doi.org/10.1016/j.scitotenv.2021.146253. 

The conclusion section also needs to be improved and the stat of art to be highlighted. I consider it as progressive research in remote sensing but it ha to be pointed out in this section. Especially, the transferability of methods for future studies has to be acknowledge. 

The introduction section has been revised (Page 2) and four new recent references have been added to the paper (Page 21-22). The conclusion section has been updated to further clarify the advantages of the proposed method and its transferability to future research (Page 21).  

A ‘marked up’ version of the revised paper has been attached as supplemental material with this submission.  

We hope this sufficiently addresses the reviewers’ comments. If there is anything else you need to help you make a decision, do not hesitate to ask. 

Yours faithfully, 
Dr. Kambiz Borna (on behalf of the authors)