Integration of an InSAR and ANN for Sinkhole Susceptibility Mapping: A Case Study from Kirikkale-Delice (Turkey)

Round 1

Reviewer 1 Report

Dear Authors,

First, I am honored to review Your paper: “Integration of InSAR and ANN for Sinkhole Susceptibility Mapping: A case study from Kirikkale-Delice (Turkey)” by the authors Hakan A. Nefeslioglu, Beste Tavus, Melahat Er, Gamze Ertugrul, Aybuke Ozdemir, Alperen Kaya and Sultan Kocaman.

 

After full review, my recommendation is major revision but not in a bad sense. I give You all my suggestions in the pdf attached. Some crucial points need to be fixed, explained and rewritten:

- There are points in the methodology that needs to more extensive elaboration. For example, ANN and DEM from inSAR

- Morphological lineaments are not structural lineaments and there is nothing structural-geological in the paper.

- Results and Discussions needs to be separated

 

Best regards!

Comments for author File: Comments.pdf

Author Response

Dear Reviewer 1,

First of all, we would like to thank for your valuable contributions to our manuscript. We have modified the paper according to your suggestions as well as the inputs of other reviewers. Please see our responses to your comments bellow. We would be grateful if you could review the modified version.

Kind regards,

Authors

 

Dear Authors,

First, I am honored to review Your paper: “Integration of InSAR and ANN for Sinkhole Susceptibility Mapping: A case study from Kirikkale-Delice (Turkey)” by the authors Hakan A. Nefeslioglu, Beste Tavus, Melahat Er, Gamze Ertugrul, Aybuke Ozdemir, Alperen Kaya and Sultan Kocaman.

After full review, my recommendation is major revision but not in a bad sense. I give You all my suggestions in the pdf attached. Some crucial points need to be fixed, explained and rewritten:

- There are points in the methodology that needs to more extensive elaboration. For example, ANN and DEM from inSAR

- Morphological lineaments are not structural lineaments and there is nothing structural-geological in the paper.

- Results and Discussions needs to be separated

Best regards!

 

Authors’ reply

By considering all the comments given by the Reviewer, the necessary improvements and corrections were provided. The methodologies given for ANN and DEM from InSAR were clarified. The term "structural lineament" was changed to "morphological lineament". The results and discussions were separated.

 

Sinkhole symbol should be circle of the same size as on the map.

Authors’ reply

By considering the reviewer’s comment, the necessary improvements were provided. The sinkhole vector data were represented by circles of the same size on the maps.

 

I would like to see a bit more geological features on the map since map have enough space to do that. For example, age of evaporites (for example Permian evaporites). Structural lineament (are these faults, fold axis…). Some more geological data could be on the map (it is not mandatory, if You have geologist in the team make it, if not, this is enough).

Authors’ reply

By considering the reviewer’s comment, the necessary improvements were provided. The geological age of the Incik formation and Sekili member of this unit was provided on the map as well as in the manuscript. Additionally, the term “structural lineament” was changed to “morphological lineament”.

 

Check if this is the correct citation style for this journal...

Authors’ reply

By considering the reviewer’s comment, the necessary correction was provided.

 

Age of these geological formations...

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. As mentioned in the previous comment, the geological age of the Incik formation and Sekili member of this unit was provided on the map as well as in the manuscript.

 

Hmm are this anhydrite-rich mudstones or anhydrite and mudstones are lateral equivalents?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. The expression was corrected as “anhydrite-rich mudstones”.

 

Some numbers here... How thick?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. The thickness of the Sekili member in the basin varies between 150-700 m (Donmez et al., 2005).

 

Donmez, M.; Bilgin, Z.R.; Akcay, A.E.; Kara, H.; Yergok, A.F.; Esenturk, K. 1:100 000 Olcekli Turkiye Jeoloji Haritalari, No: 47, Kirşehir-I32 Paftasi. Maden Tetkik Arama Genel Mudurlugu, Jeoloji Etutleri Dairesi, Ankara, 2005.

 

It would be useful to have graph or table with sinkhole properties (area, diameter, long axis, short axis). So reader can visualize size distribution of these sinkholes...

Authors’ reply

By considering the reviewer’s comment, the necessary improvements were provided. The descriptive statistics of the geometric properties of the sinkholes observed in the study area were provided in revised Table 1.

 

So correct me if I am wrong, resolution of DEM is 31 m? Could You get DEM with higher resolution (from some ministry or some geotetic institute of Turkey).

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. The output DEM has a resolution of 10 m. We could in fact obtain DEMs with a better resolution, i.e. 5 m grid, from national mapping agencies; but we wanted to exploit the usability of InSAR data for our purposes solely.

 

This comment applies to the entire manuscript. Make a statement and refer to the figure in the brackets. For example: The methodology consists from 4 main steps (Fig. 3).

Authors’ reply

By considering the reviewer’s comment, the necessary improvements were provided in the entire manuscript.

 

I don't think this is a usual procedure. Make more detail explanation or cite paper where this was applied.

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided.

“One of the possible solutions, in order to prepare a sinkhole inventory, is the use of data extracted from incident reports publicly available (Subedi et al., 2019). Additionally, according to the methodology published by Benson et al. (2003), identifying potential karst-related problems from remote sensing is also involved in the stages of a site investigation for karst hazard assessment. In this study, the sinkhole inventory was produced by using the satellite images provided on the Google Earth platform and checked through the short field studies performed in the study area…”

 

Benson, R.C.; Yuhr, L.; Kaufmann, R.D. Assessing the risk of karst subsidence and collapse. American Society Civil Engineers Geotechnical Special Publication 2003, 122, 31-39.

 

Subedi, P.; Subedi, K.; Thapa, B.; Subedi, P. Sinkhole susceptibility mapping in Marion County, Florida: Evaluation and comparison between analytical hierarchy process and logistic regression based approaches. Scientific Reports 2019, 9, 7140. https://0-doi-org.brum.beds.ac.uk/10.1038/s41598-019-43705-6

 

Delete "published by"

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

What means DS and what are the differences?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. The DS means “Dataset ID”.

 

As I know, SRTM is 30 DEM that can be enhanced by SAR to 10 m... Did you do that procedure?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. Here, a new DEM was produced with a higher spatial resolution by using SRTM as external input. Since we have a good coherence between the interferometric pair, which we used for DEM generation purpose, we assume that the output DEM has better accuracy then the SRTM as suggested by Braun (2020). However, we have not evaluated the absolute accuracy of our InSAR DEM by using external reference with superior resolution since this was not a specific focus of the study. We have explained this fact in the manuscript.

Braun 2020:

http://step.esa.int/docs/tutorials/S1TBX%20DEM%20generation%20with%20Sentinel-1%20IW%20Tutorial.pdf

 

Which software did you used?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. To develop the ANN model a program was written in Python by using the scikit-learn libraries.

 

You definitely need to divide results and discussion in to two chapters. By this, it is hard to asses which is your results and which is discussion.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided. The results and discussions were separated.

 

Obtained from inSAR or SRTM enhanced by InSAR?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. As explained previously in this document, the InSAR DEM has higher spatial resolution and reflect the topography of the considered date better than the SRTM data. The phase unwrapping process and topography extraction with the help of SRTM yields to a new InSAR DEM with better accuracy under optimal data acquisition conditions, such as dry weather and very-short temporal baseline.

 

Delete the word.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

ANN seems to be one of the most important part of the paper but ANN methodology is very thin. Explain ANN methodology in more detail, from input data, over processing to obtaining results.

Authors’ reply

By considering the reviewer’s comment, the necessary clarifications were provided.

“To develop the ANN model a program was written in Python by using the scikit-learn libraries. In the procedure, the data is first normalized between the closed interval of [0, 1]. Afterwards, the data matrix is separated, depending on the presence and absence information of target (the presence and absence groups “1” and “0”). To have the ratio 50% between the presence and absence information in training data set, random sampling is performed from the absence group “0” by considering the number of rows in the presence group “1”. In this study, a total of six topographic parameters and one line-ament parameter were used as the independent features; and the sinkhole formations were used as the dependent target in the construction of the ANN model. Therefore, a data matrix consists of topographic parameters and the lineaments was produced. In the matrix, the dependent target was the field represented by the existing sinkholes, and the in-dependent features were the parameters that control sinkhole formation. Using these features and the target, the ANN model was developed. The training dataset is composed of a matrix including 258 grid cells having an equal portion of the presence and absence in-formation of the recent sinkholes. 10% of the training data set was also selected at random as the testing dataset. Additionally, in the construction of the model with the training dataset, k-fold cross validation was applied. In the analysis performed using 10 folds, the most successful model was obtained in the learning process where the learning coefficient was 0.0001, 3 hidden layers containing 100 neurons and the rectified linear unit (ReLU) transfer function were used…”

“By considering the best parameters and structure explained in Section 3.2, the final ANN model was trained and tested. The Root Mean Square Error (RMSE) obtained from the model was 0.451. Considering the standard deviation value of the testing data that is 0.476 and the calculated RMSE, the model was found to be successful. As a result, the constructed ANN model was run by using the data matrix of the study area involved 158,902 grid cells and the resultant sinkhole susceptibility map was obtained…”

 

This is a huge overstatement. As I see on the figure, you extracted some morphological lineaments. You didn't identify any faults or other structures. Delete this sentence!

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Sinkhole symbol, for all figures here.

Authors’ reply

By considering the reviewer’s comment, the necessary improvements were provided.

 

Sinkholes need to have larger symbols; they are practically invisible on the maps.

Authors’ reply

By considering the reviewer’s comment, the necessary improvements were provided.

 

Boundary of evaporite region not visible on the map. Where are sinkholes?

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

By what criteria are your lines structural lineaments? They are not confirmed at the terrain or by any geophysical method... they can be in best case morphological lineaments.

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided.

 

This should be in the conclusions also. This is important result.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Then how you have 10 m DEM that have lower accuracy then SRTM? If the accuracy is lower why You didn't use SRTM or ALOS?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. The accuracy of the InSAR DEM is affected by imaging conditions, such as the atmospheric conditions, noise, surface deformation, etc. as stated by Braun (2020). The respective information from the page 11 in Braun (2020) is shown below. We have analyzed the coherence and the interferograms for our interferometric pair and found high coherence and low noise. Therefore, we prefer to use our InSAR DEM since it represents the topographical state for the date we selected and with 10 m spatial resolution, even if the DEM accuracy is equivalent to the accuracy of SRTM.

“To derive a DEM of sufficient quality, these fringes must be visible throughout the entire image. Areas of phase decorrelation appear as noise in the interferogram.”

 

Braun, 2020; Page 11.

Braun, A. (2020). DEM Generation with Sentinel-1 Workflow and Challenges. SkyWatch Space Applications Inc.: Waterloo, ON, Canada. http://step.esa.int/docs/tutorials/S1TBX%20DEM%20generation%20with%20Sentinel-1%20IW%20Tutorial.pdf

 

The following statements are also added to the manuscript:

“The accuracy of the InSAR DEM is affected by imaging conditions, such as the atmospheric conditions, noise, surface deformation, etc., as stated by Braun [45]. In the coherence and the interferograms for the interferometric pair, a high coherence and low noise was observed. Even though the InSAR DEM accuracy is possibly equivalent to the accuracy of SRTM DEM or slightly better [46]; the use of InSAR was favorable in the study; since it represents the topographical state for the study date and higher spatial resolution (10 m) could be obtained.”

 

Discussable... Rephrase that you did your work only in evaporates...

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Same as previous, symbol and size of sinkhole symbols.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Move to results!

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Results!

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

Author Response File: Author Response.pdf

Reviewer 2 Report

Please find selected comments on the Nefeslioglu et al paper “Integration of InSAR and ANN for Sinkhole Susceptibility Mapping: A case study from Kirikkale-Delice (Turkey)”.

Specific comments have been inserted in the pdf version of manuscript that I have sent back to the Editor.  My intention was to strengthen and clarify this paper identifying places in the text where better writing and/or organization could improve the final paper version.

Due to only few corrections associated to submitted manuscript I am in opinion that submitted manuscript after minor corrections can be accepted for publication. All necessary text corrections, suggestions, comments are indicated in submitted revised version.

Comments for author File: Comments.pdf

Author Response

Dear Reviewer 2,

First of all, we would like to thank for your valuable contributions to our manuscript. We have modified the paper according to your suggestions as well as the inputs of other reviewers. Please see our responses to your comments bellow. We would be grateful if you could review the modified version.

Kind regards,

Authors

 

Dear Authors,

Please find selected comments on the Nefeslioglu et al paper “Integration of InSAR and ANN for Sinkhole Susceptibility Mapping: A case study from Kirikkale-Delice (Turkey)”.

Specific comments have been inserted in the pdf version of manuscript that I have sent back to the Editor. My intention was to strengthen and clarify this paper identifying places in the text where better writing and/or organization could improve the final paper version.

Due to only few corrections associated to submitted manuscript I am in opinion that submitted manuscript after minor corrections can be accepted for publication. All necessary text corrections, suggestions, comments are indicated in submitted revised version.

Authors’ reply

By considering all the comments given by the Reviewer, the necessary improvements and corrections were provided. The written part and the organization of the paper were improved.

 

This paragraph is redundant. There is no need for additional explanation for the paper outline.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided. Redundant paragraph was deleted.

 

Add age for the mentioned formation.

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. The age of the geological formation was given.

“The sinkhole formations observed in the study area develop within Late Eocene-Early Miocene aged…”

 

Add at the end; e.g., Location (wgs84 coordinates); Photo taken by: xxxxxx, October, 20xx,

Authors’ reply

By considering the reviewer’s comment, the necessary clarifications were provided. The coordinates and the date of the photographs were given in the figure caption.

“Photographs were taken at the location X=586366 m, Y= 4406890 m in UTM Projection and WGS84 Datum on 26 Febru-ary 2019 by H.A. Nefeslioglu”

 

See my comment for Fig.2. Move a) and b) in upper left corner. It would be nice to have more close-view photos here...

Authors’ reply

By considering the reviewer’s comment, the necessary clarifications and improvements were provided. The coordinates and the date of the photographs were given in the figure caption. The locations of the letters were changed according to the reviewer’s recommendation.

“Photographs were taken at the location X=584463 m, Y= 4405431 m in UTM Projection and WGS84 Datum on 26 February 2019 by H.A. Nefeslioglu”

 

Add sentence which software was used for this purpose.

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided.

“The DEM of the study area was produced using the SAR interferometry in the SNAP software.”

 

Same comment as for DEM

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided.

“To develop the ANN model a program was written in Python by using the scikit-learn libraries.”

 

These parameters should be explained further in text using appropriate Formulas. this description does not appear sufficient and clear.

Authors’ reply

By considering the reviewer’s comment, the necessary explanations were provided. As the authors, considering the extent of the details, we would like to provide the key references for the readers.

“The theoretical background of the topographic parameters evaluated in SAGA GIS were given in Olaya and Conrad (2009) and Gruber and Pecham (2009).”

 

Olaya, V.; Conrad, O. Chapter 12 Geomorphometry in SAGA. Developments in Soil Science 2009, 33, 293-308.

 

Gruber, S.; Peckham, S. Chapter 7 Land-Surface Parameters and Objects in Hydrology. Developments in Soil Science 2009, 33, 171-194.

 

Explain in previous section

Authors’ reply

By considering the reviewer’s comment, the necessary explanations were provided.

 

Add short description in which software you

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided.

“To develop the ANN model a program was written in Python by using the scikit-learn libraries.”

 

Developed in?

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

“Using these features and the target, the ANN model was developed.”

 

Add this abbreviation in line 348 where you define it...

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. The abbreviation “SSM” was added where the term “sinkhole susceptibility map” was first used in the Introduction section.

 

Add a-f in the left corner (with whitish background) and standardize position for legend and scale for all figures here.

Authors’ reply

By considering the reviewer’s comment, the necessary improvements were provided.

Author Response File: Author Response.pdf

Reviewer 3 Report

Dear authors,

thank you for your interesting and useful study concerning the analysis and susceptibility to sinkholes in a region of Turkey. The study is interesting and well designed but there are several problems that do not allow a full understanding of the manuscript.

The biggest problem concerns the methodology and results. In fact, in the paragraph of the methodology many things are taken for granted (for example they are not explained why the topographical parameters have been considered and how they influence the genesis of sinkholes or in any case they have been cleared with 1-2 lines each). In the methodologies, I want to know everything that was considered in the study and the exhaustive reasons that led you to take that step. As for the results, only the results and what was obtained in the study should be explained here, while it is a mixture of methodological (there are almost more here than in the methodology paragraph) and introductory sentences, with very few sentences that really explain the results of the study.

Furthermore, I suggest to significantly improve the quality of the images (I would also suggest not to use the same color palette for all the topographic maps which are then summarized in a single image, it can create confusion).

Ultimately, I would suggest better restructuring the entire article, putting everything methodological in the methodology paragraph and specifying well and exhaustively the why of things, and adding real results that are now really poor.

More detailed comments are included in the attached pdf.

Comments for author File: Comments.pdf

Author Response

Dear Reviewer 3,

First of all, we would like to thank for your valuable contributions to our manuscript. We have modified the paper according to your suggestions as well as the inputs of other reviewers. Please see our responses to your comments bellow. We would be grateful if you could review the modified version.

Kind regards,

Authors

 

Dear authors,

thank you for your interesting and useful study concerning the analysis and susceptibility to sinkholes in a region of Turkey. The study is interesting and well-designed but there are several problems that do not allow a full understanding of the manuscript.

The biggest problem concerns the methodology and results. In fact, in the paragraph of the methodology many things are taken for granted (for example they are not explained why the topographical parameters have been considered and how they influence the genesis of sinkholes or in any case they have been cleared with 1-2 lines each). In the methodologies, I want to know everything that was considered in the study and the exhaustive reasons that led you to take that step. As for the results, only the results and what was obtained in the study should be explained here, while it is a mixture of methodological (there are almost more here than in the methodology paragraph) and introductory sentences, with very few sentences that really explain the results of the study.

Furthermore, I suggest to significantly improve the quality of the images (I would also suggest not to use the same color palette for all the topographic maps which are then summarized in a single image, it can create confusion).

Ultimately, I would suggest better restructuring the entire article, putting everything methodological in the methodology paragraph and specifying well and exhaustively the why of things, and adding real results that are now really poor.

Authors’ reply

By considering all the comments given by the Reviewer, the necessary improvements, clarifications, and corrections were provided. The written part and the organization of the paper were improved.

 

More detailed comments are included in the attached pdf.

I suggest to better structure the abstract, also following the instruction for authors of the Journal. The abstract should be structured as follows;

(1) Background: Place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: briefly describe the main methods or treatments applied; (3) Results: summarize the article's main findings; (4) Conclusions: indicate the main conclusions or interpretations

In your abstract you start with the aim of the work.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please cite:

1. Bozzano, F.; Carabella, C.; De Pari, P.; Discenza, M.E.; Fantucci, R.; Mazzanti, P.; Miccadei, E.; Rocca, A.; Romano, S.; Sciarra, N. Geological and geomorphological analysis of a complex landslides system: the case of San Martino sulla Marruccina (Abruzzo, Central Italy). J. Maps 2020, 16, 126–136. Doi:10.1080/17445647.2019.1702596
2. Bozzano, F.; Mazzanti, P.; Perissin, D.; Rocca, A.; De Pari, P. Basin scale assessment of landslides geomorphological setting by advanced InSAR analysis. Remote Sens. 2017, 9. Doi: 10.3390/rs9030267

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

After this sentence I would expect to see a major bibliography cited.

See for example:

1. Gutiérrez, F.; Galve, J.P.; Lucha, P.; Castañeda, C.; Bonachea, J.; Guerrero, J. Integrating geomorphological mapping, trenching, InSAR and GPR for the identification and characterization of sinkholes: A review and application in the mantled evaporite karst of the Ebro Valley (NE Spain). Geomorphology 2011.
2. Intrieri, E.; Gigli, G.; Nocentini, M.; Lombardi, L.; Mugnai, F.; Fidolini, F.; Casagli, N. Sinkhole monitoring and early warning: An experimental and successful GB-InSAR application. Geomorphology 2015.
3. Atzori, S.; Antonioli, A.; Salvi, S.; Baer, G. InSAR-based modeling and analysis of sinkholes along the Dead Sea coastline. Geophys. Res. Lett. 2015.
4. Nof, R.N.; Abelson, M.; Raz, E.; Magen, Y.; Atzori, S.; Salvi, S.; Baer, G. SAR interferometry for sinkhole early warning and susceptibility assessment along the Dead Sea, Israel. Remote Sens. 2019.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please add some references to support this sentence

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided. The statement is based on the field observations made by the authors of this study.

 

Add Turkey label

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Have these sinkholes been extrapolated from an existing catalog or have they been mapped by you for this study? Please specify.

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided.

“In this study, the sinkhole inventory was produced by using the satellite images provided on the Google Earth platform and checked through the short field studies performed in the study area.”

 

Please move these letters (a) and (b) so that they are more ordered. You could put them either in any corner (perhaps with a white circle as a background) or you could put them under the photos in the center

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Often, the consideration of both geometries (ascending and descending) allows the detection of displacements that might go unseen by using only one geometric condition. Why did you only use descending geometry?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided in the manuscript as following:

“Considering the relatively flat topography and the expectation of mainly a vertical displacement in the sinkhole prone areas, further processing was carried out to obtain the vertical deformation component as shown in Equation 1.

 

                                                                 (1)

 

Division of the LOS displacement to the cosine of the radar wave incident angle ( ) was found as an easily applicable approach to determine the vertical deformation in the literature [49, 50]. The method ignores the contribution of horizontal deformation to LOS displacement [51]. Afterwards, the vertical displacement was georeferenced in the geographic coordinate system with WGS84 (World Geodetic System 1984) datum for further analysis. The vertical displacement maps produced by this method for each data set. The steps of this process are also provided in the workflow (Figure 5c).”

 

The equation 1 utilizes one SAR dataset only; and does not require both ascending and descending geometries.

 

What is the resolution of the obtained DEM?

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided.

 

Why have these parameters been used? What are they for? How do they influence the genesis or hazard of sinkholes? it was not explained in the methodology anywhere!

Authors’ reply

By considering the reviewer’s comment, the necessary clarification was provided.

“Bedrock type, proximity to geological boundaries and structures, topography, recent sinkholes, and drainage history can be considered to be the main conditioning factors in sinkhole formation (Waltham et al., 2005). In this study a unique bedrock type Late Eocene-Early Miocene aged evaporites were evaluated. The topographic parameters convergence index, closed depressions, topographic wetness index, vertical distance to channel network are completely related to the drainage history of the region. The topographic parameter slope length factor indicates spatially sediment transport capacity in the region (Moore and Burch, 1986). The areas having low values of slope length factor, which means sediment transport capacity is low, are considered to be more prone to sinkhole formation. Morphological lineaments mapped by using satellite imageries were considered to be related with the geological boundaries and structures.”

 

Waltham, T.; Bell, F.; Culshaw, M. Sinkholes and subsidence, Karst and Cavernous Rocks in Engineering and Construction; Spring-er, Praxis Publishing: Chichester,2005; p.382

 

Moore, I.D.; Burch, G.J. Sediment transport capacity of sheet and rill flow: application of unit stream power theory. Water Resources Research 1986, 22, 1350-1360.

 

Add the number of the references in square brackets.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

This should be written above, when explaining how the DEM was created.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

These are methodological aspect

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

These are methodological aspect.

Why? How? add details of how this parameter affects soil erosion.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Why? add some more details. Furthermore, these are methodological aspects

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

An image should be placed near the first time it was cited. Here, however, it appears even 3 pages after the first quote.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

These cannot be regarded as results. To me it seems more like an introductory sentence!

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

These are methodological aspects

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

These cannot be regarded as results, but they are methodological aspects

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please add a fill (black or white) to the north arrow to make it more visible

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please always put the legend in the same position in all figures

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please move these letters (a), (b), etc. so that they are more ordered. You could put them either in any corner (perhaps with a white circle as a background) or you could put them under the photos in the center

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please add a white background to the scale bar to make it more visible and always place it in the same place in all figures

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please move these letters (a) and (b) so that they are more ordered. You could put them either in any corner (perhaps with a white circle as a background) or you could put them under the photos in the center

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please add a fill (black or white) to the north arrow to make it more visible

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please try to improve the quality of this image. At present, it appears very blurry

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please add a white background to the scale bar to make it more visible.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

These are methodological aspects

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please add a fill (black or white) to the north arrow to make it more visible

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please move these letters (a) and (b) so that they are more ordered. You could put them either in any corner (perhaps with a white circle as a background) or you could put them under the photos in the center

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Please add a white background to the scale bar to make it more visible.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

 

Put the north arrow in the in the upper right corner, as well as in the other figures.

Authors’ reply

By considering the reviewer’s comment, the necessary improvement was provided.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Dear Authors,

First, I am honored to review Your paper: “Integration of InSAR and ANN for Sinkhole Susceptibility Mapping: A case study from Kirikkale-Delice (Turkey)” by the authors Hakan A. Nefeslioglu, Beste Tavus, Melahat Er, Gamze Ertugrul, Aybuke Ozdemir, Alperen Kaya and Sultan Kocaman.

 

After a full review, my recommendation is to accept the paper but with English language improvements. 

Author Response

Authors’ reply

By considering the Reviewer’s comment, the necessary improvement was provided. The language of the manuscript was check by MDPI Language Editing Service. The language edit certification was also provided as a supplementary file in the revision submission.

Reviewer 3 Report

Thank you for the opportunity to review your very interesting article and for having considered, accepted, and fully responded to my reviews.  

In my opinion, the article is now acceptable for publication.

Best regards

Author Response

Authors’ reply

We would like to thank you for your valuable contributions to our manuscript.