A Systematic Classification Method for Grassland Community Division Using China’s ZY1-02D Hyperspectral Observations

Round 1

Reviewer 1 Report

All the comments I proposed in the previous version have been followed. I have no more doubts and I recommend the publication of the manuscript

Reviewer 2 Report

The authors did a lot of good work on the previous version of the manuscript. The revised  version manuscript has been significantly improved and in my opinion, it is suitable for publication.

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.

Round 1

Reviewer 1 Report

In this manuscript, the authors proposed a systematic classification method (SCM) for grassland communities, including sample selection, pre-classification processing, feature-based classification, and post-classification processing.

The introduction should be summarised 
The Results are well developed.
Discussion section: The Results are poorly discussed. This section should be improved (Just two references ??)

The conclusions are too general. The authors should improve this section.

What is the implication of your study? PLZ add this to the conclusions section.

Reviewer 2 Report

 

In this paper, the authors use remote sensing to clasificate the grasslands in the inner Mongolia region (China). The paper presents sentences too long that can be shorted to easily the lecture. In addition, too much space is used in figures or tables that do not provide new information. I encourage the authors to correct these errors.

The acronym OCA presented in the abstract it is not defined. Define this acronym or use another word such as “classification error”.

 

The paper presents sentences too long (4 lines). Divide these sentences into shorter sentences for easy reading.

 

“It consists of certain species has a certain appearance and structure, has a certain distribution range and has other basic characteristics, in which the species composition of the community is the most important factor used to determine the nature of the community and is the basic characteristic used to identify different community types”.

 

“Grasslands are one of the most widely distributed vegetation types in the world, covering nearly 25% of the land area, are an important component of terrestrial ecosystems, provide an important food supply for ruminant milk and meat production, and store approximately 20% of the global carbon stock, thus playing a key role in balancing green house gas concentrations”.

 

“China is one of the richest countries in the world in terms of grass resources, with a total grassland area of approximately 400 million ha, accounting for approximately 40% of the country’s total land area, and grassland vegetation dominates China’s green ecological barrier from the northeastern plains through the Inner Mongolia Plateau and Loess Plateau to the Xinjiang Mountains and the Qinghai-Tibet Plateau [2,5].”

 

Add a paragraph at the end of the introduction with the structure of the paper. “The rest of the paper is structured as follows. In section 2, material and methods are shown.....”

 

Change “September 12, 2019” to “September 12^th, 2019” or (12^th September 2019 in British English). The same for “May 21, 2021” and August 13, 2021.

 

The information in Table 1 is repeated in the text. Consider eliminating Table 1 o the information of the text.

 

The paper names different scientific name of plants. However, the names are incorrect. Because the authors do not include the author’s name that clasificated the specie, for example, Achnatherum splendens (Trin.) Nevski.

 

The size of the figures are excessively large. Reduce them.

 

Figures 1b) and 1 c) are not presented in the text before they appear. Change the position of these figures.

 

Figure 3 is difficult to read. I propose that the authors use letters in the different dots colored.

 

Section 3.1 should be in the material and methodology because it discusses how the experiment was carried out. In addition, in my opinion, the capacity of the computer used in the experiment is not necessary.

 

In section 4, the paper should name the disadvantage of using remote sensing and say why using this technology is better than other alternatives.

 

Include future work in the conclusion of the paper.

 

In the conclusions, add numerical information about the results obtained.

Reviewer 3 Report

This is good topic considered by the authors for grassland species mapping using Hyperspectral data.

Abstract:

1. Line 13 o 16 too complex, consider breaking in two sentences.
2. What is Hyperspectral based grassland community ? do you mean - hyperspectral based identification of grassland communities ? "  explain and reconsider .
3. which Hyperspectral data used in study-  not mentioned in abstract ? mention it
4. SCM is proposed?  what is the flowchart of proposed method ? this utilised Random forest for classification and at later stage this is also employed ?  so what is the new in this classification algorithm ? 

Data and methods:

1. ZY1-02D satellite launched by which country? mention as reader wont understand with name only thisnis not very popular among community.
2. How you have matched the spatial resolution of 30 m and 10 m, during not mentioned. 
3. figure 1 what is the size of quadrat ? 
4. Figure 1, C- spectral curve of grassland community should be replaced with appropriate terms. spectral curve of grass species in grassland (give name of grassland) ? 
5. 125 sampling points should be shown on the map , to check its distribution. ? provide sampling points on maps in separate figure
6. Table 2 illustartes 11 grass species (in chosen grassland), while authors have shown the spectral curve for only three species. ?  needs to see all spectral curve? 

Table 2 is entirely wrong- TESTING column total is 1948 ( while first species has 8824, second has 563, 4th has 3348, 7th and 8th have 1094 & 1287 respectively, then how come total of TESTING COlumn as 1948. Only first row total is 4 times of total. (8824)

check and correct. 

Figure 3, shows cloud- in the RGB image ? cloud removal process/ step is entirely missing- which may results in erraneous results during classification-  has this been considered ?

Figure 4, is classified.  cloud is classified as buildings. kindly check and correct.