Multi-Objective Multi-Satellite Imaging Mission Planning Algorithm for Regional Mapping Based on Deep Reinforcement Learning

Round 1

Reviewer 1 Report

This paper focuses on the multi-objective multi-satellite imaging mission planning algorithm for regional mapping based on deep reinforcement learning. In my opinion, the topic is very interesting and significant, because scheduling plays a fundamental role in the effective acquisition of regional images, and deep reinforcement learning is a very novel technology in designing optimization algorithms. It is a good idea to use Deep reinforcement learning to optimize MOEA. The optimization performance of MOEA is motivated as far as possible, reducing the calculation and time consumption of solving application problems. I think this paper is good for multi-objective optimization techniques and its application. The proposed method is noteworthy and the paper is worth to be published. However, there are still several improvements required for publication:

 

(1) The reference is not sufficient, and more related studies should be reviewed and included in this paper.

(2) Some English presentation is too long to be clear enough, and I suggest the authors proofread the paper carefully.

 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

In this study, a multi-objective learning evolutionary algorithm (MOLEA) was proposed to solve the optimal configuration problem of multiple EPs and used to solve effective imaging satellite task planning for region mapping. In the MOLEA, population state encoding provides comprehensive population information on the configuration of EPs. Furthermore, the EPs of each generation are configured autonomously through deep reinforcement learning (DRL), enabling each generation of parameters to gain the best evolutionary benefits for future 

evolution. Thus, MOLEA optimization performance is improved. The superiority of the proposed method was verified by comparing the optimization performance, stability, and running time of the MOLEA with existing multi-objective optimization algorithms by using four satellites to image two regions of Hubei and Congo (K). Considers the quality of current version, the authors should improve this version according to the following suggestions.

 

(1) The abstract should be organized according to the following aspects: problem, method, results and conclusions.

 

(2) In the first section, the research motivation should be strengthened.

 

(3) In section 2, the authors should summarize the main characteristics and solving difficulties of Multi-Satellite Mission Planning Model.

 

(4) The proposed method is too simple. The authors should design the proposed method according to the above main characteristics and solving difficulties of Research Problem.

 

(5) In the experimental results, please explain why the proposed method outperforms other methods.

 

(6) The references are outdated. Some recently published papers should be added.

The overall English level of this paper should be improved.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

Please check the attached file.

Comments for author File: Comments.pdf

Please check the attached file.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

It is okay.

It is okay.