Next Article in Journal
Remote Sensing Derived Indices for Tracking Urban Land Surface Change in Case of Earthquake Recovery
Next Article in Special Issue
Landslide Susceptibility Mapping: Machine and Ensemble Learning Based on Remote Sensing Big Data
Previous Article in Journal
X-Net-Based Radar Data Assimilation Study over the Seoul Metropolitan Area
Previous Article in Special Issue
Sentinel-1 DInSAR for Monitoring Active Landslides in Critical Infrastructures: The Case of the Rules Reservoir (Southern Spain)
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Remote Sensing
Volume 12
Issue 5
10.3390/rs12050894
Review Report
remotesensing-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Letter
Peer-Review Record

Research on Post-Earthquake Landslide Extraction Algorithm Based on Improved U-Net Model

Remote Sens. 2020, 12(5), 894; https://doi.org/10.3390/rs12050894
by Peng Liu 1,2, Yongming Wei 3, Qinjun Wang 1,2,4,*, Yu Chen 1 and Jingjing Xie 1,2
Reviewer 1: Anonymous
Reviewer 2:
Farid Javadnejad
Reviewer 3: Anonymous
Remote Sens. 2020, 12(5), 894; https://doi.org/10.3390/rs12050894
Submission received: 14 January 2020 / Revised: 25 February 2020 / Accepted: 25 February 2020 / Published: 10 March 2020
(This article belongs to the Special Issue Landslide Monitoring, Susceptibility, Hazard Assessment and Prediction with Remotely Sensed Big Data)

Round 1

Reviewer 1 Report

OK

Author Response

Thank you for your suggestions and recognition of my work. They have important guiding significance for my paper writing and research work!

Reviewer 2 Report

In this work, the authors represented a procedure for mapping post-earthquake landslides using an improved Neural Network approach named U-Net

The title has been chosen properly to describe the content of the paper. The abstract is written well as a stand-alone document to represent the manuscript. he literature review is coherently written and consistently to allow the reader to smoothly follow the scheme of the paper. Not all figures are required for understanding the paper. For example, Figures 1 and 3 represent the same concept. Elements in the manuscript have logically related to the objective of this research. Results and discussion parts are well written. The study only uses one sample data to test the validity of the approach. It is recommended to do the study on a different site as well. The conclusions are sound and justified and follow the presented data.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

Please fully describe the high resolution data used. Both the DEM and imagery. Is it available VERY soon after an earthquake? We need to see a comparison of the time and cost between the manual interpretation of images, and the 3 computer tests performed. This is important to evaluate the practical use of the method proposed. Describe in simpler terms, what is the impact of splitting the image into 256x256 blocks. Present a realistic estimate of application of your method during a real earthquake emergency. How long to get the imagery? How long to prepare the imagery? How long and where to get the very high resolution DEM? How long to process the imagery? How long (and how) to validate the results of improved Uline? Who will use the data? Have they seen these results, and are they willing to accept them?

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

apparently, you did not incorporate any of your thoughtful answers to reviewers' suggestions in re-submitted manuscript

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Back to TopTop