Mapping Young Lava Rises (Stony Rises) Across an Entire Basalt Flow Using Remote Sensing and Machine Learning
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThe manuscript entitled "Mapping young lava rises (stony rises) across an entire basalt flow using remote sensing and machine learning" presents very interesting applications of remote sensing. As the authors write, "This paper aims to map stony rises using remotely sensed and geophysical data at a landscape level on a younger lava flow …within the Victorian Volcanic Plain …by utilizing a machine learning approach". They first explain the geological and cultural significance of the studied object (objects). The very aim of studying cultural heritage draws attention. Then they present identifiers of the studied structures, 34 in number (slope gradient, local elevation, DEM, Normalized Difference Water Index, Clay Mineral Ratio, the concentration of radiometric elements …). So the scope of the work is also a pleasant surprise. The above-mentioned content is very concisely included in the abstract itself. However, in this part they do not provide information on how they managed to achieve their goal. It is probably to arouse interest. The abstract is therefore very eye-catching. In my opinion, an editorial error was made in the introduction. Is this the part of the work where detailed information about the location, characteristics of the area and drawings documenting it are provided? One rather expects information about the subject matter of the problem. The next chapter (Study Area) is a continuation of this characteristic. Therefore, there is no general characteristic of the work, a description of the research concept in the introduction.
Consider it please.
It seems to me that this manner is more appropriate to the work of a geographer than an engineer. The description of the research methodology presented in the further part of the text does not raise any objections. The authors describe the methods and research material in great detail and to a sufficient extent. Then they further present the results, together with statistics, errors. The extensive discussion of the results is a good indication of their research instinct. Most often, the authors of this type of work leave the reader with the results and a short commentary. It is clear that a lot of time and work was devoted to the analytical part. However, the last paragraph "Overall, this study was able to successfully map stony rises using an established methodology, highlighting that the predictor variables, thresholds, and training data and data availability, may need to be altered and tailored to the landscape to produce a successful result when mapping recurring landforms across different study areas" should be included in the next chapter (Conclusions).
Due to the fact that one of the authors is a native speaker, the language level is very good. However, there are minor errors:
“Figure 6: subsections of the final output, highlighting how the Random Forest algorithm preformed”
Performed?
“Whereas the southern parts of the study area where the terrain is flatter.”
Maybe: believing in the southern parts of the study area where the terrain is flatter.
“training data and data availability, may need to be altered and tailored to the landscape”
Maybe: training data and data availability may need to be altered and tailored to the landscape
There is also a problem with page numbering.
The work is very interesting, of practical importance. It is a great pity that the authors did not present some new, scientific approach …
Author Response
Shaye Fraser
RMIT University
s3661928@student.rmit.edu.au
30 May 2025
Mr. Vergil Di
Remote Sensing
Dear Mr. Vergil Di,
We would like to thank Remote Sensing for reviewing our paper. Thank you for your time and passing on the reviewer feedback from the anonymous reviewers. Additionally, my co-authors and I would like to thank the reviewers for their time and effort into improving the quality of our paper.
We have taken the time to review and apply the reviewers’ feedback where necessary. The response to the reviewer comments have been attached below. We have outlined what the comment was, our response to the comment and our action to the comment. We hope our answers satisfy the reviewers.
Please see the attachment for updated manuscript with the updated figures (as per the reviewer feedback). Changes to the text have been highlighted in red font. Where figure changes have occurred, red text stating “Figure updated as per reviewer comments” have been added to the end of the caption.
My co-authors and I look forward to hearing back from you and Remote Sensing.
Sincerely,
Shaye Fraser
Reviewer Comment 1: The manuscript entitled "Mapping young lava rises (stony rises) across an entire basalt flow using remote sensing and machine learning" presents very interesting applications of remote sensing. As the authors write, "This paper aims to map stony rises using remotely sensed and geophysical data at a landscape level on a younger lava flow …within the Victorian Volcanic Plain …by utilizing a machine learning approach". They first explain the geological and cultural significance of the studied object (objects). The very aim of studying cultural heritage draws attention. Then they present identifiers of the studied structures, 34 in number (slope gradient, local elevation, DEM, Normalized Difference Water Index, Clay Mineral Ratio, the concentration of radiometric elements …). So the scope of the work is also a pleasant surprise. The above-mentioned content is very concisely included in the abstract itself. However, in this part they do not provide information on how they managed to achieve their goal. It is probably to arouse interest. The abstract is therefore very eye-catching. In my opinion, an editorial error was made in the introduction. Is this the part of the work where detailed information about the location, characteristics of the area and drawings documenting it are provided? One rather expects information about the subject matter of the problem. The next chapter (Study Area) is a continuation of this characteristic. Therefore, there is no general characteristic of the work, a description of the research concept in the introduction. Consider it please.
Response to Comment 1: We are pleased you recognise the merit of our work. Thank you for your comments and suggestions. Upon reviewing your comments, we agree that more information regarding the challenges of current stony rise mapping practices is needed.
Action to Comment 1: In the abstract, we have made it clear that an object based random forest machine learning approach has been used. Within the introduction, a few sentences have been added expanding on the challenges of mapping stony rises and directly relating them to the Warrion Hill and Red Rock lava flows. (Lines 83-87)
Reviewer Comment 2: It seems to me that this manner is more appropriate to the work of a geographer than an engineer. The description of the research methodology presented in the further part of the text does not raise any objections. The authors describe the methods and research material in great detail and to a sufficient extent. Then they further present the results, together with statistics, errors. The extensive discussion of the results is a good indication of their research instinct. Most often, the authors of this type of work leave the reader with the results and a short commentary. It is clear that a lot of time and work was devoted to the analytical part. However, the last paragraph "Overall, this study was able to successfully map stony rises using an established methodology, highlighting that the predictor variables, thresholds, and training data and data availability, may need to be altered and tailored to the landscape to produce a successful result when mapping recurring landforms across different study areas" should be included in the next chapter (Conclusions).
Response to Comment 2: Thank you for your positive feedback and for your suggestion.
Action to Comment 2: The paragraph in question: "Overall, this study was able to successfully map stony rises using an established methodology, highlighting that the predictor variables, thresholds, and training data and data availability, may need to be altered and tailored to the landscape to produce a successful result when mapping recurring landforms across different study areas,” has now been moved to the end of the conclusion.
Reviewer Comment 3: “Figure 6: subsections of the final output, highlighting how the Random Forest algorithm preformed”
Performed?
Response to Comment 3: Thank you for catching this. We agree that this figure caption can be worded better.
Action to Comment 3: Changed to: subsections of the final output, highlighting how the output of Random Forest algorithm against the training data and the newly identified stony rise sites…
Reviewer Comment 4:“Whereas the southern parts of the study area where the terrain is flatter.” Maybe: believing in the southern parts of the study area where the terrain is flatter.
Response to Comment 4: Thank you for your suggestion.
Action to Comment 4: The sentence has been reworded to: … whereas the southern part of the study area has terrain that is flatter and undulating, hosting the dominant EVC of Plains Grassy Woodland. (Lines 525-526)
Reviewer Comment 5: “training data and data availability, may need to be altered and tailored to the landscape”
Maybe: training data and data availability may need to be altered and tailored to the landscape
Response to Comment 5: Thank you for your suggestion.
Action to Comment 5: This sentence has been amended to: …training data and data availability may need to be altered and tailored to the landscape.... (Lines 576-577).
Reviewer Comment 6: There is also a problem with page numbering.
Response to Comment 6: Thank you for bringing this to our attention.
Action to Comment 6: Page numbers have been fixed. However, where landscape pages are occurring there is an issue with the software (we have tried everything to fix this but for some reason the formatting removes the page number). We suggest the editors help with this issue.
Reviewer Comment 7: The work is very interesting, of practical importance. It is a great pity that the authors did not present some new, scientific approach …
Response to Comment 7: Thank you for this comment. The aim of this paper was to compare similarities and difference between stony rise landscapes using an existing method rather than creating a new approach. This paper has highlighted considerations that are needed when trying to map landforms of different ages across different areas.
Action to Comment 7: No action required
Author Response File: 
Author Response.docx
Reviewer 2 Report
Comments and Suggestions for AuthorsThe aim of this paper is to contribute to the mapping of stony rises, universally recognised as important landforms not only from a strictly geological but also from an ecological and cultural perspective. The study highlights how remote sensing techniques, integrated with a machine learning approach, have greatly enhanced the mapping of stony rises, which is currently mostly conducted manually and at the level of individual case studies. The promising results obtained make it possible to imagine that this type of approach could be used as a standard to identify not only stony rises but also other similar forms such as tumuli, worldwide.
The subject matter of the paper and the methodologies employed are of great interest and have the potential to attract a broad readership of the journal Remote Sensing.
This paper presents a really interesting and well-executed study that's relevant to a wide range of academic subjects. The study is really well written, and it's clear and easy to understand what it's trying to do and what the results could mean. The author explains the aims, innovation, and potential applications of the research really clearly and precisely.
In a previous recent paper (Fraser et al., 2024), the same Authors had adopted a combination of techniques such as Object Based Image Analysis and Random Forest, using remotely sensed and geophysical data to map stony rises from the Mt Fraser lava flow in metropolitan Melbourne. I particularly appreciated how the evolution of the methodological approach used by the same Authors in the previous paper was very well explained highlighting the substantial differences in the geographic and temporal context, the different accuracy of the survey and the predictive variables used.
The methodological approach adopted is not only appropriate for the research questions posed, but is also thoughtfully situated within the wider framework of existing literature. This contextualisation enhances the study's credibility and underscores its contribution to ongoing scholarly discourse. Furthermore, the conclusions are logically derived from the evidence and arguments provided, demonstrating a strong alignment between the study's findings and its interpretative claims. In conclusion, the submitted manuscript makes a valuable and scientifically sound contribution to the field, and it is found to have minimal shortcomings with regard to its rigour or resonance.
The bibliography impresses with its thoroughness, listing a total of 74 references: it is interesting to note that a significant proportion of these references are very recent, with a maximum age of approximately 10 years. It is notable that there are no occurrences of self-citation (with the exception, naturally, of Fraser et al., 2024).
The primary issue identified in this paper pertains to the quality and resolution of the figures, which, in general, are of substandard quality and consequently difficult to read. This is regrettable, as it precludes a comprehensive interpretation of the study's findings, except in the most general terms. Given the sheer magnitude of the identified objects, it is impractical to expect a comprehensive graphical representation. To address this issue, the insertion of detailed maps of selected sample areas is recommended to underscore the efficacy of the obtained results. It is further recommended that the font size be increased, with particular reference to those of certain legends (e.g. Figures 1 and 3).
It is also crucial to include the coordinates on the axes of the maps in Figures 5 and 6, as this allows for precise geographical referencing of the areas.
Despite my own non-native status in English, I found the English language to be appropriate, comprehensible, and adequate for the majority of the text.
It is my final recommendation that the paper be accepted for publication in the Journal of Remote Sensing, pending minor revisions that take my suggestions into account, with particular reference to those evidenced for the figures, which, in my opinion, are of crucial importance.
Should further review of the manuscript be required, I would be pleased to undertake this at a later date.
Author Response
Shaye Fraser
RMIT University
s3661928@student.rmit.edu.au
30 May 2025
Mr. Vergil Di
Remote Sensing
Dear Mr. Vergil Di,
We would like to thank Remote Sensing for reviewing our paper. Thank you for your time and passing on the reviewer feedback from the anonymous reviewers. Additionally, my co-authors and I would like to thank the reviewers for their time and effort into improving the quality of our paper.
We have taken the time to review and apply the reviewers’ feedback where necessary. The response to the reviewer comments have been attached below. We have outlined what the comment was, our response to the comment and our action to the comment. We hope our answers satisfy the reviewers.
Please see the attachment for updated manuscript with the updated figures (as per the reviewer feedback). Changes to the text have been highlighted in red font. Where figure changes have occurred, red text stating “Figure updated as per reviewer comments” have been added to the end of the caption.
My co-authors and I look forward to hearing back from you and Remote Sensing.
Sincerely,
Shaye Fraser
Reviewer Comment 1: The aim of this paper is to contribute to the mapping of stony rises, universally recognised as important landforms not only from a strictly geological but also from an ecological and cultural perspective. The study highlights how remote sensing techniques, integrated with a machine learning approach, have greatly enhanced the mapping of stony rises, which is currently mostly conducted manually and at the level of individual case studies. The promising results obtained make it possible to imagine that this type of approach could be used as a standard to identify not only stony rises but also other similar forms such as tumuli, worldwide.
The subject matter of the paper and the methodologies employed are of great interest and have the potential to attract a broad readership of the journal Remote Sensing.
Response to Comment 1: Thank you for your comment. We are pleased to know that this paper is of interest to the diverse readership of Remote Sensing.
Action to Comment 1: No action required
Reviewer Comment 2: This paper presents a really interesting and well-executed study that's relevant to a wide range of academic subjects. The study is really well written, and it's clear and easy to understand what it's trying to do and what the results could mean. The author explains the aims, innovation, and potential applications of the research really clearly and precisely.
Response to Comment 2: Thank you for your comment. We are pleased you found the paper easy to understand.
Action to Comment 2: No action required
Reviewer Comment 3: In a previous recent paper (Fraser et al., 2024), the same Authors had adopted a combination of techniques such as Object Based Image Analysis and Random Forest, using remotely sensed and geophysical data to map stony rises from the Mt Fraser lava flow in metropolitan Melbourne. I particularly appreciated how the evolution of the methodological approach used by the same Authors in the previous paper was very well explained highlighting the substantial differences in the geographic and temporal context, the different accuracy of the survey and the predictive variables used.
Response to Comment 3: Thank you for your comment. It’s great to hear the paper clearly communicates the methods we used and how these have evolved from past research.
Action to Comment 3: No action required
Reviewer Comment 4: The methodological approach adopted is not only appropriate for the research questions posed, but is also thoughtfully situated within the wider framework of existing literature. This contextualisation enhances the study's credibility and underscores its contribution to ongoing scholarly discourse. Furthermore, the conclusions are logically derived from the evidence and arguments provided, demonstrating a strong alignment between the study's findings and its interpretative claims. In conclusion, the submitted manuscript makes a valuable and scientifically sound contribution to the field, and it is found to have minimal shortcomings with regard to its rigour or resonance.
Response to Comment 4: Thank you for your comment.
Action to Comment 4: No action required
Reviewer Comment 5: The bibliography impresses with its thoroughness, listing a total of 74 references: it is interesting to note that a significant proportion of these references are very recent, with a maximum age of approximately 10 years. It is notable that there are no occurrences of self-citation (with the exception, naturally, of Fraser et al., 2024).
Response to Comment 5: Thank you for your comment.
Action to Comment 5: No action required
Reviewer Comment 6: The primary issue identified in this paper pertains to the quality and resolution of the figures, which, in general, are of substandard quality and consequently difficult to read. This is regrettable, as it precludes a comprehensive interpretation of the study's findings, except in the most general terms. Given the sheer magnitude of the identified objects, it is impractical to expect a comprehensive graphical representation. To address this issue, the insertion of detailed maps of selected sample areas is recommended to underscore the efficacy of the obtained results. It is further recommended that the font size be increased, with particular reference to those of certain legends (e.g. Figures 1 and 3).
Response to Comment 6: Thank you for your comment. Initially all figures were exported with a minimum DPI of 300. However, in the figures that have detailed maps, we can increase the export quality.
Thank you for the feedback on the text within the figures, we can increase the font size on the legend to improve readability
Action to Comment 6: Figure 1 has been amended to improve readability of legend. Additionally Figure 1b, has had its scale amended to improve readability.
Figure 3 has had the font size of its legend increased.
All Figures have been exported in at higher DPI quality.
Reviewer Comment 7: It is also crucial to include the coordinates on the axes of the maps in Figures 5 and 6, as this allows for precise geographical referencing of the areas.
Response to Comment 7: Thank you for your suggestion.
Action to Comment 7: Coordinates on the axes of Figures 5 and 6 have now been added. As well as 1 and 3.
Reviewer Comment 8: Despite my own non-native status in English, I found the English language to be appropriate, comprehensible, and adequate for the majority of the text.
Response to Comment 8: Thank you for your comment.
Action to Comment 8: No action required
Reviewer Comment 9: It is my final recommendation that the paper be accepted for publication in the Journal of Remote Sensing, pending minor revisions that take my suggestions into account, with particular reference to those evidenced for the figures, which, in my opinion, are of crucial importance.
Should further review of the manuscript be required, I would be pleased to undertake this at a later date.
Response to Comment 9: Thank you for your comment. The figures have been updated as per your suggestions above.
Action to Comment 9: No action required
Author Response File: Author Response.docx
