Next Article in Journal
Imprints of Soil Microbial Activity Accredited to Residue-Management and Tillage Practices for Boosting Rice and Wheat Production
Next Article in Special Issue
Risk Assessment of Debris Flow Disasters Triggered by an Outburst of Huokou Lake in Antu County Based on an Information Quantity and Random Forest Approach
Previous Article in Journal
Female CEOs and Green Innovation: Evidence from Asian Firms
Previous Article in Special Issue
Comparative Tests on Failure Characteristics and Mechanisms of Mine Waste Dumps with Different Material Layouts
 
 
Article
Peer-Review Record

Remote Sensing Identification and Information Extraction Method of Glacial Debris Flow Based on Texture Variation Characteristics

Sustainability 2024, 16(21), 9405; https://doi.org/10.3390/su16219405
by Jun Fang 1,2,*,†, Yongshun Han 1,2,*,†, Tongsheng Li 2,†, Zhiquan Yang 3, Luguang Luo 1, Dongge Cui 4, Liangjing Chen 2 and Zhuoting Qiu 1
Reviewer 1: Anonymous
Reviewer 2:
Reviewer 3: Anonymous
Reviewer 4:
Sustainability 2024, 16(21), 9405; https://doi.org/10.3390/su16219405
Submission received: 14 August 2024 / Revised: 9 October 2024 / Accepted: 24 October 2024 / Published: 29 October 2024
(This article belongs to the Special Issue Remote Sensing in Geologic Hazards and Risk Assessment)

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This article is not innovative enough and the results of the study obtained are generalized and lack value for use, therefore, it is not recommended for publication in this journal.

(1)The paragraphs are not well designed and some of them are too long, and changes are suggested;

(2)The sentences in this article need to be revised and improved appropriately.

(3)The literature review in the introduction fails to summarize the shortcomings of the previous studies as well as the wear newness of this study.

(4)The names and layout of the charts and graphs in the text need to be improved appropriately.

(5)Carefully check the spelling of this paper, e.g., 2.2.1 has an extra number 8 in the title. There is an error in labeling the subheadings of this paper, e.g., the next level of heading for the 2.2.2 Extra Information section should be 2.2.2.1 or (1), not 1. Please refer to the published literature for corrections.

(6)The first occurrence of an abbreviation should have the full name corresponding to the abbreviation.

(7)Section 2 does not show the data underlying the research in this paper, making it difficult to be convinced of the reliability of the study.

(8)Section 3.1.1 (line 205) no heading.

(9)Section 3.1.1 Multi-Feature Spatiotemporal Extraction Model, are these methods proposed by the authors themselves? Or are they references to other people's methods?

(10) The conclusions could be improved.

Comments on the Quality of English Language

 Moderate editing of English language required.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

In the second paragraph of Introduction. The major two problems of glacier debris flow identification is not very well introduced. Please rewirte to enhance the logic and highlight the shadow and fast changing features which bring the difficulty.
In the third paragraph of the introduction, Please specify what you are going to do to tacle the above problems. And breifly introduce the section arrangements.
The major problem is that there are too much text to follow the highlight of each paragraph. Please don't introduce some very basic concept, for example, texture is important in gully type classification. RF is a machine learning method that can handle large datasets..., this is not related to your process.
Please shorten every paragraph, only keep the core of your ideas. I'm sorry to say that a lot of sentences are too long to follow.
Please add a flowchart to the Method section.
Some term like MNF, GDFI was firstly appears in the Result section, which is supposed to apear in method section.
some minor revises are included in the attached file.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

This work developed the multi-feature spatiotemporal information extraction model to identify glacier 21 debris flows. Authors show the higher accuracy than the existed models. The main finding is convincing but there are a few points need to clarify. Here are my questions and concerns:

 

1. In the abstract, authors claimed that there is significant information loss due to deep shadows in the developed model. But in the conclusion, authors showed that this technique can extract glacier debris flows, even under very dark conditions, fully exploiting the information of images in time dimension. Authors should clarify whether this model will cause significant information or not, under dark conditions.

 

2. In figure 6, the figure quality should be improved. There are some Enter signs in the figure.

 

3. For equation (2), what's the meaning of T. Please define it.

 

4. For equation (4), the factor in each variable and the value of the factor need further discussion and investigation. How to determine such factor values and the what's the procedure. Authors should give details so that other researcher can follow such method. The current version is lack of details, and it is hard to follow. 

Comments on the Quality of English Language

The English language should be revised. Some sentences can cause misunderstanding.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

Comments and Suggestions for Authors

The authors have put significant effort into developing an innovative model for the identification of glacial debris flows, which is well-constructed and makes a substantial contribution to the field. The purpose of the article is to develop and implement a multi-feature spatiotemporal extraction model for glacial debris flows, utilizing advanced image analysis techniques such as the Random Forest algorithm to effectively identify and extract these phenomena in challenging terrain conditions. The article introduces a model that eliminates disturbances caused by mountain shadows and changes in ice and snow phases, thereby improving the accuracy of the analysis. The results show that the proposed method outperforms other techniques, such as neural networks and support vector machines, in terms of overall accuracy. The methodology based on the Random Forest algorithm and multi-feature spatiotemporal analysis is well-justified. Since the study focuses on a specific region, it would be worth considering the application of this method in other areas with similar conditions. The study is well-organized, which is significant both scientifically and practically, especially in the context of natural hazard management. The experimental design is sound, but additional testing in different conditions would help confirm the repeatability of the results. The figures and tables are appropriate, and the conclusions are consistent with the data presented in the article. The literature is appropriately selected and relevant, although the chapter numbering needs improvement. The article effectively identifies a gap in the field of accurate identification of glacial debris flows under shadow and ice phase change conditions.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

After careful revision by the author, I think this paper can be  published as the present form.

Back to TopTop