Interest in Automated Coastline Extraction (NDWI & Cliff Segmentation)

[lakshyadchad]

Hi mentors (@fwitmer),

My name is Lakshya, and I am a student developer interested in contributing to the Automated Coastline Extraction project.

I have a background in Python and I am currently ramping up on the geospatial stack (rasterio, geopandas). I have successfully set up the local environment and have written a simulation script to replicate the NDWI (Normalized Difference Water Index) logic mentioned in the project overview to understand how the water masking works.

You can see my NDWI reproduction script here: [https://github.com/lakshyadchad/alaska-gsoc-prep]

I am now moving on to testing the pipeline with the sample PlanetLabs imagery provided in the repo. I am particularly interested in the "Cliff Area Segmentation" challenge and will be looking for guidance on where I can be most helpful with testing or documentation in these early stages.

Looking forward to contributing!

[lakshyadchad]

Hi mentors (@fwitmer, @Rawan, and @ritika),

"Earlier, I set up a Conda environment to run this project locally and wrote a simulation script to replicate the NDWI logic.

My Initial Results: I successfully generated a water mask where the Deering airport runway is correctly classified as land. However, I noticed that the 'No Data' padding around the rotated image is currently being misclassified as water using a simple thresholding approach. I plan to implement masking for these 'No Data' regions next.

You can view my reproduction script here: https://github.com/lakshyadchad/alaska-gsoc-prep

I am particularly interested in the "Cliff Area Segmentation" challenge mentioned in the project scope. are there any specific documentation updates or small reproduction tasks that would be helpful to the team? pls give suggestion and replay for improvement

Looking forward to contributing!

[lakshyadchad]

Progress Update: Vectorization Pipeline & Border Artifact Fix

I have been working on the extraction pipeline. I successfully implemented a script that fix No data problem that "white border" artifacts (where nodata was previously being misclassified as water)
by adding the Feature: vectorizes the binary mask into Shapely polygons.

You can view my vector script here: https://github.com/lakshyadchad/alaska-gsoc-prep

thank you

[fwitmer]

@lakshyadchad Great to see your interest in our project! We were putting some finishing touches on the GSoC 2025 changes and just merged them from the dev branch to the master branch. Please take a look and hopefully the updates will be helpful in understanding the data workflow of the project.

[lakshyadchad]

Okay @fwitmer sir, I will look at them. Thank you for updating me.

[lakshyadchad]

Hi @fwitmer sir and mentors,
I want to give you an update on my current progress. I am trying to expand the dataset with more recent imagery (2020-2025), but I am facing an issue obtaining a Planet API key to gather these resources. I have already applied for one, but the approval process might take some time.

Do you have any suggestions on how to proceed or alternative options to look for?
Looking forward to your feedback.