Dear Dr. ROCCETTI,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Apr 30 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols .

We look forward to receiving your revised manuscript.

Kind regards,

Shai Gordin, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. In your manuscript, please provide additional information regarding the specimens used in your study. Ensure that you have reported human remain specimen numbers and complete repository information, including museum name and geographic location.

If permits were required, please ensure that you have provided details for all permits that were obtained, including the full name of the issuing authority, and add the following statement:

'All necessary permits were obtained for the described study, which complied with all relevant regulations.'

If no permits were required, please include the following statement:

'No permits were required for the described study, which complied with all relevant regulations.'

For more information on PLOS ONE's requirements for paleontology and archeology research, see https://journals.plos.org/plosone/s/submission-guidelines#loc-paleontology-and-archaeology-research .

3. Thank you for stating the following financial disclosure:

“The 2022-2024 Abu Ghraib survey project, directed by N. Marchetti, has been authorized by the Iraqi State Board of Antiquities and Heritage (SBAH) and funded by the University of Bologna and the Italian Ministry of Foreign Affairs and International Cooperation. The research presented in this paper was supported through the “KALAM”. Analysis, protection and development of archaeological landscapes in Iraq and Uzbekistan through ICTs and community-based approaches” project, coordinated by N. Marchetti and funded by the Volkswagen Foundation (www.kalam.unibo.it).”

Please state what role the funders took in the study.  If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."

If this statement is not correct you must amend it as needed.

Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

Reviewer #1: Partly

Reviewer #2: No

**********

2. Has the statistical analysis been performed appropriately and rigorously? -->?>

Reviewer #1: Yes

Reviewer #2: No

**********

3. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: Yes

Reviewer #2: No

**********

Reviewer #1: This is a paper focused on using deep learning techniques to auto-discover archaeological sites in Mesopotamia. The paper reflects a growing trend in the use of AI-based techniques to automate discovery of archaeological sites. Overall, the paper is interesting but requires more work prior to publication. I list some of my comments below.

1). The review of previous literature misses quite a lot of developments in the area of remote sensing and archaeology using AI-based techniques. There have been various studies on also using mounds on maps or imagery to find sites. Although many of these do not focus on CORONA, perhaps incorporating these could be useful as it shows where the methodology is best understood in this growing literature. I think incorporating what has been done with UAVs, non-optical data, and other areas could be useful for better understanding many of these related techniques and ultimately how this work is different.

2) The methodology, which is described and presented, needs a lot more description in the main text in my opinion. I think a better discussion on the steps and algorithm is critical. I understand that the details are best presented elsewhere, such as the code, but the paper should also have enough detail to give the reader they understand the mechanics of the technique. To me this needs more work and detail. There is not much discussion on the loss function, parameterisation, and other steps.

3). Its good to see the tests done regarding accuracy. However, do we get a sense of sites being missed by survey and this technique? I know it is hard to tell without knowing what sites exist but random survey of the region studied could help identify what is being missed by these more focused approaches that are looking at areas seen on the results.

4). Although tell sites are obviously common, many sites are flat in Mesopotamia or show little mounding. I understand that these might be difficult on optical data but this may mean other data should be used such as LiDAR (e.g., from UAVs), multispectral, and even higher resolution optical. It seems to me many sites could be missed with this technique. In fact, if one were to use Digital Elevation Data and use that to find sites, as tells become obvious with that data, could we not simply use that to find mounded sites? I would have tested how accurate this technique is relative to someone using DEM data to find sites and see which is more accurate. In any case, I think more discussion on the limitations of the research and why other data sources could not be used to find non-tell (mounded) sites is warranted as there are now a number of papers on finding mounded sites using deep learning in archaeology (see my comment on the literature review).

5. More discussion on usability of this would be good. For instance, on scaling the approach, time it takes to do this work, and benefits of this technique versus other techniques in the literature, such as Mask R-CNN, Random Forest, and other DL techniques.

Reviewer #2: Overall, this is an interesting article employing a methodology which I hope to become more developed and common in broadscale settlement analysis. However, a concern is that the authors present this method as a novel approach, when uses of machine learning algorithms have been employed to this end before in similar areas (Menze et al 2006, Soroush et al 2020, Guyot et al 2018, Orengo et al 2020, etc.). It is concerning that other studies such as these are not cited. I am also concerned at the apparent conflation of “tells” with archaeological sites more broadly. One of the main benefits of this technology is that it should not just be able to identify tells, which are easily identifiable without ML. However, throughout the article, it is difficult to understand if the authors are referring only to the identification of tells (which seems to be the case) or all archaeological sites. Certainly, there are plenty of “flat” sites.

My second main concern with this article is that the AI/ML approach used to identify sites does not actually assist the preexisting survey methods in a meaningful way. If I am reading this correctly, then it appears that the ultimate result of this study is 4 sites and 4 false positives identified that were not initially discovered during survey. However, when compared to the 80+ sites that were identified and surveyed, this number seems almost negligible and not at all like a “real breakthrough” that the authors purport it to be. In fact, in the conclusions section they suggest that these "discovered" sites by the model had "the appropriate morphological characteristics" - does that mean that normal exploratory foot survey would have discovered these sites? Ultimately, it doesn't seem that the model made much of a difference at all to the results of a survey that was using CORONA imagery to identify potential sites in the first place. The authors have given information for the accuracy of the different models they tested, but how does it compare to the accuracy of "normal" site identification with satellite imagery? While the accuracy here is 50/50 in terms of "newly identified" sites, in my experience a normal positive-false positive ratio is more akin to 60-75%-40-25%. (It is also unclear why CORONA makes such a difference in the case of this model - I'm assuming it's the result of modern urbanization and industrial agriculture which have now obscured these sites, but this is unclear in the text itself.)

I think that an article discussing this approach has merit, but should be tested on a larger dataset with more distinct results to merit publication in this journal. My conclusion is to reject this manuscript, but with hope that the authors will continue to develop and apply this model to further material to produce meaningful results in the future.

**********

what does this mean? ). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy

Reviewer #1: No

Reviewer #2: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/ . PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org . Please note that Supporting Information files do not need this step.

Dear Dr. ROCCETTI,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Aug 10 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols .

We look forward to receiving your revised manuscript.

Kind regards,

Shai Gordin, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

Reviewer #1: (No Response)

**********

2. Is the manuscript technically sound, and do the data support the conclusions??>

Reviewer #1: Partly

**********

3. Has the statistical analysis been performed appropriately and rigorously? -->?>

Reviewer #1: No

**********

4. Have the authors made all data underlying the findings in their manuscript fully available??>

The PLOS Data policy

Reviewer #1: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English??>

Reviewer #1: Yes

**********

Reviewer #1: I still find a few things missing in this work based on this current version. I think they need to be addressed before the manuscript can be accepted. I list these below.

1) The review of existing literature in this area is still somewhat minimal. I know this is not a review paper, so referencing all works is not that critical but I think more around the specific architecture chosen and the background into that would help because there are other architectures one could have chose and it is not clear to me why this particular method say is better or more appropriate over other CNN-based or DL models/architectures.

2) Validation test are somewhat limited. A broader range of statistical tests could be applied to test how accurate and reliable the quality of the image identification is. Usually I would expect a wider range, including RMSE and other tests to be there.

3) I still think more can be done with the non-tell based sites but I can accept to leave that for now. Some discussion at least as to how this could be an improvement in the future might be warranted (i.e., how to improve non-tell based site identification as this would really be transformative if we can go beyound mound identification).

**********

what does this mean? ). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy

Reviewer #1: No

**********

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/ . PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org

AI-ming backwards: Vanishing archaeological landscapes in Mesopotamia and automatic detection of sites on CORONA imagery

PONE-D-24-47137R2

Dear Dr. ROCCETTI,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager®  and clicking the ‘Update My Information' link at the top of the page. For questions related to billing, please contact billing support .

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Shai Gordin, Ph.D.

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments: