Earth Observation path to imaging introduction tutorial - #6970
Open
annefou wants to merge 6 commits into
Open
Conversation
Reuse the same threshold -> label -> count workflow on a Sentinel-2 water-index image to count Greenland supraglacial melt ponds, mirroring the cross-discipline 'Choose Your Own Adventure' pattern of the object-tracking-using-cell-profiler and process-image-bioimageio tutorials. Adds the CYOA Bioimaging/Earth split, the EO dataset (Zenodo 10.5281/zenodo.20960690), two EO result figures, the Earth observation tag, and OSCARS funding. Validated end-to-end on usegalaxy.eu (13 major melt lakes).
Collaborator
|
Sorry it took a while, I'm looking into it now. |
kostrykin
reviewed
Aug 7, 2026
|
|
||
| > <comment-title> Counting melt ponds with a cell-counting workflow </comment-title> | ||
| > | ||
| > In the Earth observation path, we reuse *the same* segment-and-count workflow that was built for counting of stained cell nuclei to count *supraglacial melt ponds* on the Greenland ice sheet. This is a cross-discipline experiment from the [OSCARS-FIESTA](https://oscars-project.eu/projects/fair-image-analysis-across-sciences) project. Why does it work? Melt ponds have a high ice-adapted water index, so in a water-index image they appear as *bright blobs on a darker background*, which is the same characteristic that is exploited for segmenting cell nuclei. The same threshold–label–count steps that count nuclei count melt ponds; only the *index* and the *interpretation of the threshold* are domain-specific. |
Collaborator
There was a problem hiding this comment.
The same threshold–label–count steps that count nuclei count melt ponds; only the index and the interpretation of the threshold are domain-specific.
I re-phrased the text above to improve clarity, but I'm not sure myself what the last 1-2 sentences actually mean. Can you please try to phrase them more clearly?
|
|
||
| > <comment-title> How the satellite image was prepared </comment-title> | ||
| > | ||
| > The image is a single-band ice-adapted normalised-difference water index, NDWI<sub>ice</sub> = (blue − red)/(blue + red) (Williamson et al. 2018, [doi:10.5194/tc-12-3045-2018](https://doi.org/10.5194/tc-12-3045-2018)), computed from a Sentinel-2 Level-2A scene (tile T22WEV, 2019-07-23) over the south-west Greenland ablation zone and rescaled to 16-bit so that melt ponds are bright. The preprocessing notebooks, the full Galaxy run provenance, the validation against an independently published lake map, and a citable archive are in the [OSCARS-FIESTA example repository](https://github.com/annefou/fiesta-galaxy-meltponds-eo). |
Collaborator
There was a problem hiding this comment.
Can you please use the {% cite ... %} syntax for the reference?
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
|
|
||
| > <comment-title> How the satellite image was prepared </comment-title> | ||
| > | ||
| > The image is a single-band ice-adapted normalised-difference water index, NDWI<sub>ice</sub> = (blue − red)/(blue + red) (Williamson et al. 2018, [doi:10.5194/tc-12-3045-2018](https://doi.org/10.5194/tc-12-3045-2018)), computed from a Sentinel-2 Level-2A scene (tile T22WEV, 2019-07-23) over the south-west Greenland ablation zone and rescaled to 16-bit so that melt ponds are bright. The preprocessing notebooks, the full Galaxy run provenance, the validation against an independently published lake map, and a citable archive are in the [OSCARS-FIESTA example repository](https://github.com/annefou/fiesta-galaxy-meltponds-eo). |
Contributor
There was a problem hiding this comment.
This looks like a DOI which could be better served by using the built-in Citations mechanism. You can use https://doi2bib.org to convert your DOI into a .bib formatted entry, and add to your tutorial.md
Suggested change
| > The image is a single-band ice-adapted normalised-difference water index, NDWI<sub>ice</sub> = (blue − red)/(blue + red) (Williamson et al. 2018, [doi:10.5194/tc-12-3045-2018](https://doi.org/10.5194/tc-12-3045-2018)), computed from a Sentinel-2 Level-2A scene (tile T22WEV, 2019-07-23) over the south-west Greenland ablation zone and rescaled to 16-bit so that melt ponds are bright. The preprocessing notebooks, the full Galaxy run provenance, the validation against an independently published lake map, and a citable archive are in the [OSCARS-FIESTA example repository](https://github.com/annefou/fiesta-galaxy-meltponds-eo). | |
| > The image is a single-band ice-adapted normalised-difference water index, NDWI<sub>ice</sub> = (blue − red)/(blue + red) (Williamson et al. 2018{% cite ... %})), computed from a Sentinel-2 Level-2A scene (tile T22WEV, 2019-07-23) over the south-west Greenland ablation zone and rescaled to 16-bit so that melt ponds are bright. The preprocessing notebooks, the full Galaxy run provenance, the validation against an independently published lake map, and a citable archive are in the [OSCARS-FIESTA example repository](https://github.com/annefou/fiesta-galaxy-meltponds-eo). |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add Earth Observation path to the introduction to imaging. I think it can help to promote the tutorials we created for image analysis and which contain Earth Observation Path.