DPIRD-DMA/OmniWaterMask
Python library for high-accuracy water segmentation in satellite and aerial imagery, combining deep learning with NDWI and vector data for robust detection across multiple sensors and resolutions.
This tool helps environmental managers, land use planners, and agricultural specialists accurately map water bodies from satellite and aerial images. You input various types of imagery, such as Sentinel-2 or PlanetScope data, and it outputs precise water masks, clearly distinguishing water from non-water areas. This is ideal for monitoring changes in water resources or assessing flood impacts across large regions.
Available on PyPI.
Use this if you need to create highly accurate maps of water bodies from diverse satellite and aerial imagery, even with varying resolutions and processing levels.
Not ideal if you lack an internet connection or don't have access to a GPU or Apple Silicon Mac, as performance may be significantly impacted.
Stars
31
Forks
7
Language
Python
License
MIT
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Dependencies
16
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DPIRD-DMA/OmniWaterMask"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
prs-eth/Popcorn
[RSE 2024] 🍿POPCORN: High-resolution Population Maps Derived from Sentinel-1 and Sentinel-2 🌍🛰️
xinluo2018/WatNetv2
A new WatNet version which further extends the data applicability from Sentinel-2 image to...
sidgan/ETCI-2021-Competition-on-Flood-Detection
Experiments on Flood Segmentation on Sentinel-1 SAR Imagery with Cyclical Pseudo Labeling and...
sei-latam/WETSAT_v2
Wetlands flooding extent and trends using SATellite data and Machine Learning v2.0
iarai/Landslide4Sense-2022
Data description and baseline code for LandSlide4Sense 2022 competition