Retrievals of Chlorophyll-a from GOCI and GOCI-II Data in Optically Complex Lakes

Round 1

Reviewer 1 Report

This study focused on the retrievals of chlorophyII-a from the remote sensing imagery perspective. GOCI and GOCI-II satelliate data were used to map the spatial distribution of chlorophyII. Then, three lakes in China was selected to do this. Three methods were applied to construct the model. Generally, this topic is traditional, the methods also belonged to traditional method. This manuscript had some shortcomings that need to further address before considering its suitablity of publication.

The structure of the abstract is unreasonable or the elements in the abstract are incomplete. A good abstract contains four elements: background, methods, results, and conclusions. The abstract had better been revised according to the following structural arrangement: background and aim, methods, results or findings, conclusions or significance.

The section of Discussion need to be improved. The structure of the Discussion part of this article is incomplete. The section of Results represents the heart of a paper, and the section of Discussion is the paper’s nerve center. The section of Discussion in a paper is generally involved with 3 or 4 parts: (1) main points, which response to the questions put in introduction; (2) comments on related studies or problems; (3) shortcomings or deficiency in study method or process; (4) conclusions, which can be separated to make the final section.

 Conclusions are confused with results in this paper. Conclusions are different from results. Generally speaking, results come from or are directly based on data analysis. In contrast, conclusions come from discussion and represent the climax of discussion. If the result is regarded as the heart of an academic paper, the discussion can be treated as the nerve center of the paper. Discussions form a bridge between results and conclusions.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

To the authors

The work is quite interesting.

The goal is clear and has been successfully achieved.

I have inserted some considerations in the attached file in order to improve it a little for publication.

Congratulations to the authors for their excellent work.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

1. Recommendation:

Major revision

 

2. Overview and general recommendation:

The manuscript by Guo et al. presents a study of using random forest (RF) model to detect the variation of Chla in three optically complex lakes based on GOCI and GOCI-II data. The current topic is meaningful for improving the accuracy of monitoring eutrophication in water bodies. The English expression of the article is fluent, the writing format is standardized, there are rich and reasonable citations, the text is well-organized, and the logic is clear. Despite this, further explanations are still needed on some concerning issues. The decision of this review is ‘Major revision’. Major and minor comments were listed as follows.

 

3. Major comments:

(1) Please added introduction of random forest (RF) model in section 2. Materials and Methods.

(2) Line 325-346: Is it better to use principal component analysis (PCA) to capture the diurnal variation in Chla for much reliable feature extraction and classification? This approach may provide a more reliable basis for classification, eliminating situations which may avoid phenomenon that the patterns in Figure 10d1 and f1 are similar, but that in Figure 10f1 and f2 are different.

(3) In figure 11: Why does the accuracy of the RF model decrease gradually as the number of samples increases? In traditional concepts, the more samples there are, the better the model’s accuracy should be. Does this imply that the RF model with the inclusion of AFAI in this article performs equivalently or even worse than the AFAI model directly, especially in large sample simulations? If so, relevant statements can be added in section 4.2.

(4) Can it be explained in discussion that why the estimation using RF model is better than that from empirical model?

 

4. Minor comments:

(1) Line 185: format error, “3.1.1. Subsubsection” should be deleted?

(2) Line 249: where is Table 2.3.3. Formatting of Mathematical Components?

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Authors have addressed all comments.