Using Artificial Intelligence for Space Challenges: A Survey
Round 1
Reviewer 1 Report
please see the attached comments
Comments for author File: 
Comments.pdf
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
This paper made a survey for Artificial Intelligence for Space Challenges. The presentation of this paper is clear. However, there are still some crucial problems that need to be carefully addressed before a possible publication. More specifically,
1. The motivations or remaining challenges are not so clear or what kinds of issues or difficulties are this task that is facing. Please give more details and discussion about the key problems solved in this paper, which is largely different from existing works.
2. A deep literature review should be given, particularly some advanced deep learning methods in remote sensing. Therefore, the reviewer strongly suggests discussing and analyzing some related works by citing the following papers in the revised manuscript, e.g.,10.1109/TGRS.2020.3015157 and 10.1109/TIP.2019.2893068.
3. A mind map should be provided to give a big picture for this topic.
4. It is well-known that the remote sensing data tend to suffer from various degradation, noise effects, or variabilities in the process of imaging. Please give the discussion and analysis by referring to the paper titled by “An Augmented Linear Mixing Model to Address Spectral Variability for hyperspectral unmixing”. The reviewer is wondering what will happen in the studied topic.
5. Some future directions should be pointed out in the conclusion.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Dear authors,
this paper is great overview of challenges and benefits of AI in space challenges.
I believe it can be accepted in present form.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 4 Report
Article review
Antonia Russo and Gianluca Lax
«Using Artificial Intelligence for Space Challenges: a Survey»
I fully agree with the statement of the authors, expressed in the Introduction, that the need for reviews on the use of Artificial Intelligence for Space Challenges is very great, and there are few such reviews themselves. So little that it is desirable that almost any review of this topic be published and as soon as possible.
Therefore, I believe that the proposed article may be published without changes. Below are some notes on this article that the authors may consider if they make corrections to it, or when writing the next version.
The review is based on more than 100 publications selected by the authors from Google Scolar. The selection procedure is described in detail in the Introduction. But then the authors, apparently, limited the amount of text for themselves. As a result, the text of the article turned out to be very concise, the description of each reference has 2-3 sentences. The answer to any question, even the simplest one, requires reading the original article. At the same time, the grouping of the problems considered in the publications into several directions, carried out by the authors, is of little use, since articles of very different directions are still grouped in the directions.
In addition to this review, I would suggest that the authors write an extended version of it, increasing the volume by 5-10 times, with more detailed descriptions of publications. Such a review will also be in demand.
There is a technical note to the text of the article related to the numbering of the bibliography. Articles are numbered as they appear in the text. But in section 4 there is a jump from reference [44] to reference [112]. The jump is associated with figures 1 and 2 containing bibliographic references. Perhaps it makes sense to move these figures to the end of the article or to the appendix so as not to violate the consistent description of the articles.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Accept in present form
Author Response
We thank the reviewer.
Reviewer 2 Report
- The authors saw the authors’ efforts to deal with the reviewer’s concerns. However, some important review works are still missing, e.g., 10.1109/TGRS.2020.3015157. Moreover, How about the computational complexity of the proposed method? And some future directions should be pointed out in the conclusion.
Author Response
Question 1: The authors saw the authors’ efforts to deal with the reviewer’s concerns. However, some important review works are still missing, e.g., 10.1109/TGRS.2020.3015157.
Response 1: In the revised manuscript, we inserted this useful reference in Section 3 as [102]. We added it also to our taxonomy.
Question 2: Moreover, How about the computational complexity of the proposed method?
Response 2: Please observe that in this survey we do not propose a novel method.
Question 3: And some future directions should be pointed out in the conclusion.
Response 3: We added future directions. A first direction concerns applying artificial intelligence techniques to the field of satellite communication with the purpose of making communication systems more efficient and secure. Another interesting direction regards the next frontiers of artificial intelligence for navigation, as far as the global navigation satellite systems.
