[PRE REVIEW]: AlignSAR: An open-source toolbox of SAR benchmark dataset creation for machine learning applications

[editorialbot]

Submitting author: @LC-SAR (Ling Chang)
Repository: https://github.com/AlignSAR/alignSAR
Branch with paper.md (empty if default branch): main
Version: v1.1
Editor: @rwegener2
Reviewers: Pending
Managing EiC: Kristen Thyng

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f"><img src="https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f/status.svg)](https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f)

Author instructions

Thanks for submitting your paper to JOSS @LC-SAR. Currently, there isn't a JOSS editor assigned to your paper.

@LC-SAR if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). You can search the list of people that have already agreed to review and may be suitable for this submission.

Editor instructions

The JOSS submission bot @editorialbot is here to help you find and assign reviewers and start the main review. To find out what @editorialbot can do for you type:

@editorialbot commands

[editorialbot]

Hello human, I'm @editorialbot, a robot that can help you with some common editorial tasks.

For a list of things I can do to help you, just type:

@editorialbot commands

For example, to regenerate the paper pdf after making changes in the paper's md or bib files, type:

@editorialbot generate pdf

[editorialbot]

⚠️ An error happened when generating the pdf.

[kthyng]

@LC-SAR can you try to fix the compilation error?

[kthyng]

👋 Here is some more info: @LC-SAR - note that your paper does not compile. Please follow the example paper and note that you can click on the error above to find out more about it. In addition, you could work on the possibly missing DOIs that editorialbot suggests, but note that some may be incorrect. Please feel free to make changes to your .bib file, then use the command @editorialbot check references to check again, and the command @editorialbot generate pdf after making changes to the .md file or when the references are right to make a new PDF. editorialbot commands need to be the first entry in a new comment.

[LC-SAR]

@editorialbot check references

[LC-SAR]

@editorialbot commands

[editorialbot]

Hello @LC-SAR, here are the things you can ask me to do:

# List all available commands
@editorialbot commands

# Get a list of all editors's GitHub handles
@editorialbot list editors

# Adds a checklist for the reviewer using this command
@editorialbot generate my checklist

# Set a value for branch
@editorialbot set joss-paper as branch

# Run checks and provide information on the repository and the paper file
@editorialbot check repository

# Check the references of the paper for missing DOIs
@editorialbot check references

# Generates the pdf paper
@editorialbot generate pdf

# Generates a LaTeX preprint file
@editorialbot generate preprint

# Get a link to the complete list of reviewers
@editorialbot list reviewers

[LC-SAR]

@editorialbot generate pdf

[editorialbot]

⚠️ An error happened when generating the pdf.

[LC-SAR]

Submitting author: @LC-SAR (Ling Chang) Repository: https://github.com/AlignSAR/alignSAR Branch with paper.md (empty if default branch): https://github.com/AlignSAR/alignSAR/tree/main/paper/paper.md Version: v1.1 Editor: Pending Reviewers: Pending Managing EiC: Kristen Thyng

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f"><img src="https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f/status.svg)](https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f)

Author instructions

Thanks for submitting your paper to JOSS @LC-SAR. Currently, there isn't a JOSS editor assigned to your paper.

@LC-SAR if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). You can search the list of people that have already agreed to review and may be suitable for this submission.

Editor instructions

The JOSS submission bot @editorialbot is here to help you find and assign reviewers and start the main review. To find out what @editorialbot can do for you type:

@editorialbot commands

Dear Editor, Thanks for reviewing our paper. I have updated my paper.bib (https://github.com/AlignSAR/alignSAR/blob/main/paper/paper.bib) and added the missing doi for all the articles (expecting a book published in 1991 which does not have doi). I have no problem generating the pdf by running https://github.com/AlignSAR/alignSAR/blob/main/.github/workflows/draft_pdf.yml. But when I ran '@editorialbot generate pdf', I encountered the same issue as you identified. I suspect there should be because when submitting, I gave the absolute path for 'Branch with paper.md', like this 'Branch with paper.md (empty if default branch): https://github.com/AlignSAR/alignSAR/tree/main/paper/paper.md'.
Could you please help me remove 'https://github.com/AlignSAR/alignSAR/tree/main/paper/paper.md' for Branch with paper.md (empty if default branch). I think if we leave Branch with paper.md as empty, bot can generate the pdf. Thank you.

[LC-SAR]

Submitting author: @LC-SAR (Ling Chang) Repository: https://github.com/AlignSAR/alignSAR Branch with paper.md (empty if default branch): https://github.com/AlignSAR/alignSAR/tree/main/paper/paper.md Version: v1.1 Editor: Pending Reviewers: Pending Managing EiC: Kristen Thyng

Status

Status badge code:

HTML: <a href="https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f"><img src="https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f/status.svg"></a>
Markdown: [![status](https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f/status.svg)](https://joss.theoj.org/papers/0ca20174f004319d43ed8756f8e48f8f)

Author instructions

Thanks for submitting your paper to JOSS @LC-SAR. Currently, there isn't a JOSS editor assigned to your paper.

@LC-SAR if you have any suggestions for potential reviewers then please mention them here in this thread (without tagging them with an @). You can search the list of people that have already agreed to review and may be suitable for this submission.

Editor instructions

The JOSS submission bot @editorialbot is here to help you find and assign reviewers and start the main review. To find out what @editorialbot can do for you type:

@editorialbot commands

Regarding the potential reviews, I propose those peers in the field of Earth Science. SAR (Synthetic Aperture Radar) and machine learning, with GitHub names: weiji14, jiangyuinsar and rogerkuou

[kthyng]

@editorialbot set main as branch

[editorialbot]

Done! branch is now main

[kthyng]

@editorialbot generate pdf

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[editorialbot]

Five most similar historical JOSS papers:

Geodata-Harvester: A Python package to jumpstart geospatial data extraction and analysis
Submitting author: @sebhaan
Handling editor: @hugoledoux (Active)
Reviewers: @lukasbeuster, @martibosch
Similarity score: 0.6936

PolSAR tools: A QGIS plugin for generating SAR descriptors
Submitting author: @Narayana-Rao
Handling editor: @hugoledoux (Active)
Reviewers: @liberostelios, @HenrikJanPersson
Similarity score: 0.6790

Synaptus: A Matlab/Octave toolbox for synthetic aperture ultrasound imaging
Submitting author: @mh-skjelvareid
Handling editor: @Kevin-Mattheus-Moerman (Active)
Reviewers: @emanuelhuber, @Kevin-Mattheus-Moerman
Similarity score: 0.6778

Trash AI: A Web GUI for Serverless Computer Vision Analysis of Images of Trash
Submitting author: @wincowgerDEV
Handling editor: @arfon (Active)
Reviewers: @domna, @luxaritas
Similarity score: 0.6705

deeplenstronomy: A dataset simulation package for strong gravitational lensing
Submitting author: @rmorgan10
Handling editor: @pdebuyl (Active)
Reviewers: @shreyasbapat, @jiwoncpark
Similarity score: 0.6644

⚠️ Note to editors: If these papers look like they might be a good match, click through to the review issue for that paper and invite one or more of the authors before considering asking the reviewers of these papers to review again for JOSS.

[kthyng]

@LC-SAR Sorry I missed that!

Hi and thanks for your submission! I am looking for some specific items to make sure your submission fits our requirements at a high level (not at the more detailed review level) before moving on to finding an editor or putting this on our waitlist if no relevant editors are available. I'll comment over time as I have a chance to go through them:

• OSI-approved license
• Installation instructions
• Documentation exists at all
• Tests of some sort
• Check paper (make sure compiles, read through, check for length 250-1000 words)
• Substantial scholarly effort
• Clear research application

In the meantime, please take a look at the comments above ⬆️ from the editorialbot to address any DOI, license, or paper issues if you're able (there may not be any), or suggest reviewers. For reviewers, please suggest 5 reviewers from the database listed above or your own (non-conflicted) extended network. Their github handles are most useful to receive but please don't use "@" to reference them since it will prematurely ping them.

[LC-SAR]

@LC-SAR Sorry I missed that!

Hi and thanks for your submission! I am looking for some specific items to make sure your submission fits our requirements at a high level (not at the more detailed review level) before moving on to finding an editor or putting this on our waitlist if no relevant editors are available. I'll comment over time as I have a chance to go through them:

• OSI-approved license
• Installation instructions
• Documentation exists at all
• Tests of some sort
• Check paper (make sure compiles, read through, check for length 250-1000 words)
• Substantial scholarly effort
• Clear research application

In the meantime, please take a look at the comments above ⬆️ from the editorialbot to address any DOI, license, or paper issues if you're able (there may not be any), or suggest reviewers. For reviewers, please suggest 5 reviewers from the database listed above or your own (non-conflicted) extended network. Their github handles are most useful to receive but please don't use "@" to reference them since it will prematurely ping them.

Thank you Kristen for your help. Our AlignSAR toolbox follows Apache-2.0 license; Installation instruction is introduced in AlignSAR_tutorial.pdf (https://github.com/AlignSAR/alignSAR/blob/main/AlignSAR_tutorial.pdf), see Section 1.1.; Documentation can be found in https://github.com/AlignSAR/alignSAR/tree/main; demonstration can also found in AlignSAR_tutorial.pdf; Submitted paper has 965 words. Considering research fields in earth science, radar remote sensing, and machine learning, five potential reviewers could be: GitHub names: weiji14, jiangyuinsar, rogerkuou, yotarazona, talha-q

[kthyng]

@editorialbot check repository

[editorialbot]

Software report:

github.com/AlDanial/cloc v 1.90  T=0.34 s (652.8 files/s, 380103.2 lines/s)
---------------------------------------------------------------------------------------
Language                             files          blank        comment           code
---------------------------------------------------------------------------------------
C++                                     32           5012          10190          40132
C                                       22           2460           5027          22001
Python                                  73           2767           2278          10051
C/C++ Header                            34           1325           4135           4386
C Shell                                 20            824           1737           3655
Bourne Shell                            11            612            835           2997
Jupyter Notebook                         8              0           5975            743
XML                                      8              6              3            463
make                                     4             74            195            311
Markdown                                 3             47              0            119
TeX                                      1              6              0            107
Windows Module Definition                1              1              2             52
JSON                                     1              0              0             39
Bourne Again Shell                       1              5              0             38
Dockerfile                               1              6              4             27
YAML                                     1              2              4             18
---------------------------------------------------------------------------------------
SUM:                                   221          13147          30385          85139
---------------------------------------------------------------------------------------

Commit count by author:

    70	Ling Chang
    58	espiritocz
    45	LC-SAR
    16	XuZhangUT
    13	Milan Lazecky
     6	AlignSAR
     2	Anurag
     1	Jose Manuel Delgado Blasco
     1	unknown

[editorialbot]

Paper file info:

📄 Wordcount for paper.md is 1087

✅ The paper includes a Statement of need section

[editorialbot]

License info:

✅ License found: Apache License 2.0 (Valid open source OSI approved license)

[kthyng]

@LC-SAR some high level comments:

• something like readthedocs (hosted docs) or using your already-existing website for more docs would be more user-friendly rather than the tutorials being a bit buried on github (for both the pdf tutorial and the notebook)
• I see your installation is docker-based. Can a user install without using docker? It is difficult for a user to contribute to development of an open source tool if installation is exclusively docker-based, with some exceptions.
• What tests do you have so users know their code is working correctly?
• Your inline and parenthetical references aren't setup correctly. Take a look at the syntax here: https://joss.readthedocs.io/en/latest/example_paper.html

[LC-SAR]

@LC-SAR some high level comments:

• something like readthedocs (hosted docs) or using your already-existing website for more docs would be more user-friendly rather than the tutorials being a bit buried on github (for both the pdf tutorial and the notebook)
• I see your installation is docker-based. Can a user install without using docker? It is difficult for a user to contribute to development of an open source tool if installation is exclusively docker-based, with some exceptions.
• What tests do you have so users know their code is working correctly?
• Your inline and parenthetical references aren't setup correctly. Take a look at the syntax here: https://joss.readthedocs.io/en/latest/example_paper.html

Dear Kristen,
please see my response to your four points below:

• For every functionality, we also have a brief description in its gihub folder. For intance, for the modified Doris software, in the folder 'itd-doris_5_patch2023', https://github.com/AlignSAR/alignSAR/tree/main/itc-doris_5_patch2023, we provide its description on the github website.
• Docker is one option to run our tool. We also describe how to install all required software manually on the user's local computer and list troubleshooting. For instance, the guideline to install Doris, see https://github.com/AlignSAR/alignSAR/blob/main/AlignSAR_tutorial.pdf, Appendix A (page 30).
• We have offered a set of sample data (NetCDF), see https://github.com/AlignSAR/alignSAR/tree/main/jupyter_notebook_demo, which allows the users to test without creating SAR signatures from raw SAR (Single-Look-complex) data. More sample data have been uploaded on EOTDL: https://www.eotdl.com/datasets/Alignsar/, https://www.eotdl.com/datasets/AlignSAR-Groningen-Sentinel1-Q0/ by us.
• I have modified the paper.md (https://github.com/AlignSAR/alignSAR/blob/main/paper/paper.md), for instance, changed '## Summary' to '# Summary', updated Figure index and caption, changed reference from [@zhu2021deep], [ @kulshrestha2022use] to [@zhu2021deep; @kulshrestha2022use]. I tried to add the year like [@zhu2021deep:2021], but compiling pdf failed. So I excluded the year while the reference format in the new pdf is the same as JOSS paper format. Hope it suffices.

[LC-SAR]

Dear @kthyng Kristen,
It is about a month since our last contact. I wonder whether you have any further questions regarding my response to your points (see above).
Thanks and with regards,
Ling

[kthyng]

Sorry @LC-SAR, I will follow up now.

For every functionality, we also have a brief description in its gihub folder. For intance, for the modified Doris software, in the folder 'itd-doris_5_patch2023', https://github.com/AlignSAR/alignSAR/tree/main/itc-doris_5_patch2023, we provide its description on the github website.

I don't really understand this response. Can you explain again? I am particularly curious about docs and tutorials that a user could use to start using your software and understand its functionality. The tutorial pdf is excellent, it is just a bit difficult for a user to jump into compared to more modern html like readthedocs. Also having everything in one place is less confusing.

Docker is one option to run our tool. We also describe how to install all required software manually on the user's local computer and list troubleshooting. For instance, the guideline to install Doris, see https://github.com/AlignSAR/alignSAR/blob/main/AlignSAR_tutorial.pdf, Appendix A (page 30).

Is Doris all of the library, or just part of it?

We have offered a set of sample data (NetCDF), see https://github.com/AlignSAR/alignSAR/tree/main/jupyter_notebook_demo, which allows the users to test without creating SAR signatures from raw SAR (Single-Look-complex) data. More sample data have been uploaded on EOTDL: https://www.eotdl.com/datasets/Alignsar/, https://www.eotdl.com/datasets/AlignSAR-Groningen-Sentinel1-Q0/ by us.

Ok, this is good. Normally there would also be unit tests to make sure the software is working correctly during development and for any users who want to contribute to development. This would probably come up during review.

[kthyng]

@editorialbot generate pdf

[editorialbot]

👉📄 Download article proof 📄 View article proof on GitHub 📄 👈

[editorialbot]

Five most similar historical JOSS papers:

Geodata-Harvester: A Python package to jumpstart geospatial data extraction and analysis
Submitting author: @sebhaan
Handling editor: @hugoledoux (Active)
Reviewers: @lukasbeuster, @martibosch
Similarity score: 0.6934

Synaptus: A Matlab/Octave toolbox for synthetic aperture ultrasound imaging
Submitting author: @mh-skjelvareid
Handling editor: @Kevin-Mattheus-Moerman (Active)
Reviewers: @emanuelhuber, @Kevin-Mattheus-Moerman
Similarity score: 0.6775

PolSAR tools: A QGIS plugin for generating SAR descriptors
Submitting author: @Narayana-Rao
Handling editor: @hugoledoux (Active)
Reviewers: @liberostelios, @HenrikJanPersson
Similarity score: 0.6758

Trash AI: A Web GUI for Serverless Computer Vision Analysis of Images of Trash
Submitting author: @wincowgerDEV
Handling editor: @arfon (Active)
Reviewers: @domna, @luxaritas
Similarity score: 0.6716

deeplenstronomy: A dataset simulation package for strong gravitational lensing
Submitting author: @rmorgan10
Handling editor: @pdebuyl (Active)
Reviewers: @shreyasbapat, @jiwoncpark
Similarity score: 0.6660

⚠️ Note to editors: If these papers look like they might be a good match, click through to the review issue for that paper and invite one or more of the authors before considering asking the reviewers of these papers to review again for JOSS.

[kthyng]

Please check that your inline vs. parenthetical references are correct. You can compare with the example paper here: https://joss.readthedocs.io/en/latest/example_paper.html. For example, in line 11 you have references in parentheses that shouldn't be.

[LC-SAR]

Please check that your inline vs. parenthetical references are correct. You can compare with the example paper here: https://joss.readthedocs.io/en/latest/example_paper.html. For example, in line 11 you have references in parentheses that shouldn't be.

Thank you Kristen. I have updated the reference according. See line 11 for the updated manuscript.

[kthyng]

@LC-SAR great, did you see my other questions/comments above?

[LC-SAR]

Five most similar historical JOSS papers:

Geodata-Harvester: A Python package to jumpstart geospatial data extraction and analysis Submitting author: @sebhaan Handling editor: @hugoledoux (Active) Reviewers: @lukasbeuster, @martibosch Similarity score: 0.6934

Synaptus: A Matlab/Octave toolbox for synthetic aperture ultrasound imaging Submitting author: @mh-skjelvareid Handling editor: @Kevin-Mattheus-Moerman (Active) Reviewers: @emanuelhuber, @Kevin-Mattheus-Moerman Similarity score: 0.6775

PolSAR tools: A QGIS plugin for generating SAR descriptors Submitting author: @Narayana-Rao Handling editor: @hugoledoux (Active) Reviewers: @liberostelios, @HenrikJanPersson Similarity score: 0.6758

Trash AI: A Web GUI for Serverless Computer Vision Analysis of Images of Trash Submitting author: @wincowgerDEV Handling editor: @arfon (Active) Reviewers: @domna, @luxaritas Similarity score: 0.6716

deeplenstronomy: A dataset simulation package for strong gravitational lensing Submitting author: @rmorgan10 Handling editor: @pdebuyl (Active) Reviewers: @shreyasbapat, @jiwoncpark Similarity score: 0.6660

⚠️ Note to editors: If these papers look like they might be a good match, click through to the review issue for that paper and invite one or more of the authors before considering asking the reviewers of these papers to review again for JOSS.

Dear Kristen,
Thank you. I am afraid that I don't know which action I should take in response to this message. Is this message about proposing potential reviewers for our manuscript? If so, on 27 September, I checked the 'database' you shared and suggested five potential reviewers could be: GitHub names: weiji14, jiangyuinsar, rogerkuou, yotarazona, talha-q, considering research fields in earth science, radar remote sensing, and machine learning.

[LC-SAR]

Sorry @LC-SAR, I will follow up now.

For every functionality, we also have a brief description in its gihub folder. For intance, for the modified Doris software, in the folder 'itd-doris_5_patch2023', https://github.com/AlignSAR/alignSAR/tree/main/itc-doris_5_patch2023, we provide its description on the github website.

I don't really understand this response. Can you explain again? I am particularly curious about docs and tutorials that a user could use to start using your software and understand its functionality. The tutorial pdf is excellent, it is just a bit difficult for a user to jump into compared to more modern html like readthedocs. Also having everything in one place is less confusing.

Docker is one option to run our tool. We also describe how to install all required software manually on the user's local computer and list troubleshooting. For instance, the guideline to install Doris, see https://github.com/AlignSAR/alignSAR/blob/main/AlignSAR_tutorial.pdf, Appendix A (page 30).

Is Doris all of the library, or just part of it?

We have offered a set of sample data (NetCDF), see https://github.com/AlignSAR/alignSAR/tree/main/jupyter_notebook_demo, which allows the users to test without creating SAR signatures from raw SAR (Single-Look-complex) data. More sample data have been uploaded on EOTDL: https://www.eotdl.com/datasets/Alignsar/, https://www.eotdl.com/datasets/AlignSAR-Groningen-Sentinel1-Q0/ by us.

Ok, this is good. Normally there would also be unit tests to make sure the software is working correctly during development and for any users who want to contribute to development. This would probably come up during review.

Dear Kristen,

Regarding your comment '> I don't really understand this response. Can you explain again? I am particularly curious about docs and tutorials that a user could use to start using your software and understand its functionality. The tutorial pdf is excellent, it is just a bit difficult for a user to jump into compared to more modern html like readthedocs. Also having everything in one place is less confusing.', here is my further explanation:
The idea of offering this tutorial is to give a detailed and stepwise description of how to install and run our AlignSAR toolbox, the basic methodologies behind it, and the expected outputs based on a user case. I understand pdf format is not recommended in this case, so I converted this tutorial into html and shared it on Github, see https://lc-sar.github.io/alignsar_tutorial_html/. Would this html file suffice? If so, I can finalize this html file.

Regarding your question '> Is Doris all of the library, or just part of it?', Doris is one of the tools within AlignSAR toolbox. If you read our manuscript, on page 2, from line 63, we have listed all other tools besides Doris.

Thank you,

Ling

[LC-SAR]

@LC-SAR great, did you see my other questions/comments above?

@kthyng , yes, I saw your questions. Some questions required more time, so I didn't answer them in one go. But I addressed all of them yesterday, please check. Ling

[kthyng]

@LC-SAR Ok I reread your comments to see that you said all the software can be installed manually, not just Doris. I misunderstood.

Thank you for trying with the html vs the pdf. It looks like the formatting doesn't work out very well on the html the way it's processed so best not to do it this way.

Some of the comments in this issue are from a bot, editorialbot, and they are just to help out.

We have a backlog of submissions so I will add this to our waitlist. Thanks for your patience.

[kthyng]

@rwegener2 Can you edit this submission?

[kthyng]

@editorialbot invite @rwegener2 as editor

[editorialbot]

Invitation to edit this submission sent!

[rwegener2]

@editorialbot add me as editor

[editorialbot]

Assigned! @rwegener2 is now the editor

[rwegener2]

👋🏻 Hi @christopheredsall and @xiaxilin, would you be willing to review this submission for JOSS? We carry out our checklist-driven reviews here in GitHub issues and follow these guidelines: https://joss.readthedocs.io/en/latest/review_criteria.html