Next Article in Journal
Impacts of Climate Change, Glacier Mass Loss and Human Activities on Spatiotemporal Variations in Terrestrial Water Storage of the Qaidam Basin, China
Next Article in Special Issue
Impacts of Land-Use Change on the Spatio-Temporal Patterns of Terrestrial Ecosystem Carbon Storage in the Gansu Province, Northwest China
Previous Article in Journal
Spatial Surface Reflectance Retrievals for Visible/Shortwave Infrared Remote Sensing via Gaussian Process Priors
Previous Article in Special Issue
A Novel Efficient Method for Land Cover Classification in Fragmented Agricultural Landscapes Using Sentinel Satellite Imagery
 
 
Article
Peer-Review Record

R-IMNet: Spatial-Temporal Evolution Analysis of Resource-Exhausted Urban Land Based on Residual-Intelligent Module Network

Remote Sens. 2022, 14(9), 2185; https://doi.org/10.3390/rs14092185
by Chunyang Wang 1,2, Yingjie Zhang 2, Xifang Wu 2,*, Wei Yang 3, Haiyang Qiang 4, Bibo Lu 1 and Jianlong Wang 1
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3:
Reviewer 4: Anonymous
Remote Sens. 2022, 14(9), 2185; https://doi.org/10.3390/rs14092185
Submission received: 7 April 2022 / Revised: 25 April 2022 / Accepted: 29 April 2022 / Published: 3 May 2022
(This article belongs to the Special Issue Remote Sensing in Land Use and Management)

Round 1

Reviewer 1 Report

This paper analyzes the spatiotemporal patterns of land use and land cover change in Jiaozuo city from 2000 to 2020 using a residual-intelligent module network. Overall, this paper is well organized and analyzed. However, some revisions are also needed to improve the paper accordingly, including Line 185: Eq. 1, Line 370: Fig. 7, Line 469: Fig. 8, Line 539: Fig. 9. Make sure that figures, tables and equations in your paper are clearer and have relatively uniform formats.

Comments for author File: Comments.docx

Author Response

Please see the attachment!

Author Response File: Author Response.docx

Reviewer 2 Report

The authors submitted a well written and an interesting manuscript. However, they need to improve it before it could be considered for publication. Below are some comments and suggestions to improve the manuscript.

Lines 18, 26,30: The date for the dataset (2000-2020) and the results (1993-2020) are different. Please check.

Lines 40-41: Please correct “ ...the essential characteristics of the Earth.“ to“ ...the essential characteristics of the Earth surface“.

Lines 114-115: in Introduction, the authors should provide an brief introdution on how “Residual-Intelligent Module Network“ was constructed in this study. The authors should provide a short review of previous studies conducted using the proposed methody.

Line 151: Please indicate if you used pansharpening technique to improve the spatial resolution of Landsat-TM/OLI images from 30 m to 15 m. If not please discuss why.

Lines 160-161: Please provide the description of these six land use types.

Lines 167-168: Please provide formulas or provide references for e NDVI(Normalized Difference Vegetation Index), NDWI(Normalized Difference Water Index) and NDBI(Normalized Difference Building Index).

Line 172: Information provided in the Table 1 for Remote Sensing image characteristics are not relevant. Please provide the band combination interpretated for each land use type. The Table 1 is not cited in the text, please check.

Line 238: Please provide the scale and the orientation for the classification maps presented on the Figure 5. Please provide the legend below or on the maps, (not above).

Line 469: Please provide sharper images for the Figure 8.

Lines 54-55: Please provide references of recent studies. Please refere to (1) Randazzo, G.; Cascio, M.; Fontana, M.; Gregorio, F.; Lanza, S.; Muzirafuti, A. Mapping of Sicilian Pocket Beaches Land Use/Land Cover with Sentinel-2 Imagery: A Case Study of Messina Province. Land 202110, 678. https://doi.org/10.3390/land10070678, (2)WaÅ›niewski, A.; HoÅ›ciÅ‚o, A.; Chmielewska, M. Can a Hierarchical Classification of Sentinel-2 Data Improve Land Cover Mapping? Remote Sens. 202214, 989. https://doi.org/10.3390/rs14040989 for recent works dealing with Land use from remote sensed data.

Author Response

Please see the attachment!

Author Response File: Author Response.docx

Reviewer 3 Report

There are some deficiencies in this paper, and it would be perfect if the deficiencies are corrected:

 

 

Line 13-36, the method of driving force analysis (the Principal Component Analysis and Regression Analysis) is neglected, I think it must be mentioned.

 

Line 49-88 the paragraph is too long, maybe you need to add a concluding sentence at the beginning or divide it into two paragraphs.

(traditional survey methods ---> learning methods ---> deep learning)

 

Line 54-55, the word ”are” will be used in the singular; the word “and” is redundant.

 

Line 124, “4,071.1 km2” need to be “4,071.1 km2

 

Line 135-136, you said “However, in March 2008, it was listed as the country’s first resource-exhausted cities”, I don’t know the context or reason of the condition, you’d better give some evidence. I think it’s one of your innovations in this paper, you should describe it more clearly.

 

Line 150-151, if the date of collecting Landsat remote sensing images and remote sensing images source are added, it would be better.

 

Line 482-483, you select 17 driving factors from only a reference [55]. It’s a little incredible and not scientific, you should show more details about your selection and give more references. The innovation of your selected driving factors needs to be emphasized.

 

Line 517-527, the sample of linear regression analysis should be added. From the figure 9, it seems that you select 9 samples.

 

Line 548-550, you maybe omit a conjunctive word before “the construction land area”.

Line 572-573, you maybe omit a conjunctive word or some other words before “causes the construction”.

Author Response

Please see the attachment!

Author Response File: Author Response.docx

Reviewer 4 Report

Dear Editor,

Please find my review of a manuscript titled "R-IMNet: Spatial-temporal evolution analysis of resource-exhausted urban land based on Residual-Intelligent Module Network" by Chunyang Wang, Yingjie Zhang, Xifang Wu, Wei Yang, Haiyang Qiang, Bibo Lu, Jianlong Wang" submitted for consideration for possible publication in MDPI Special Issue: Remote Sensing in Land Use and Management.

This study proposed a residual-intelligent module network to solve the problems of low classification accuracy and missing objects edge information in traditional computer classification methods. A case study for classification of four Landsat-TM/OLI images Landsat remote sensing images (1993, 2003, 2011 and 2020) for Jiaozuo city has been conducted. The results of classification had an overall accuracy of about  98% in 2020 images and  were better than the comparison with three other models. The findings of this study can be utilised for land use planning and land reclamation in mining areas in resource-exhausted cities such as Jiaozuo.

The subject of this study is suitable for this special issue of Remote Sensing journal. Data and methodology are robust.

Some revision is required before publishing the manuscript.

Line 232. Therefore, a residual link is introduced (figure 3). => Figure 3

Line 235. The structure is shown in figure 4.  => Figure 4

Lines 279, 286, 299: replace" formula" with "equation"

This reviewer recommends accepting the manuscript after suggested minor revision.

Yours faithfully,

The Reviewer

Author Response

Please see the attachment!

Author Response File: Author Response.docx

Back to TopTop