DEA Water Observations (Sentinel-2 Near Real-Time, Provisional, Australia)

Provider
Geoscience Australia (Digital Earth Australia)
License
CC-BY-4.0 (source)
Format
JSON, JPEG (in sampled files)
Stored at
Amazon S3, s3://dea-public-data/derivative/ga_s2_wo_provisional_3 (ap-southeast-2)
Access
Free and public. No account with the data provider is needed.
DOI
10.26186/146257
Category
Earth Observation & Geospatial
Source
https://doi.org/10.26186/146257

About DEA Water Observations (Sentinel-2 Near Real-Time, Provisional, Australia)

Per-scene surface water maps for Australia from Sentinel-2A and 2B, produced by Digital Earth Australia within 24 hours of each overpass by applying the Water Observations (WOfS) classifier to Sentinel-2 near-real-time surface reflectance. Each 10 m pixel is flagged wet or dry, together with bit flags for cloud, cloud shadow, terrain shadow and sensor problems that made it unobservable. The product is provisional and not validated; it is intended for flood extent mapping and emergency management soon after an event, complementing the validated Landsat Water Observations series. The product page describes a rolling three-month window, while the DEA STAC catalogue still indexes 541,954 scenes from 2021 onward. Checked 2026-11-16: version 0-0-1 is laid out by MGRS UTM zone, tile, acquisition date and processing timestamp (e.g. 0-0-1/54/LWJ/2021/07/01/20230223T125452/), each scene holding a single-band *_nrt_water.tif bit-flag Cloud Optimised GeoTIFF (10980 x 10980 pixels), thumbnail and STAC/ODC metadata. Load with odc-stac or rioxarray and decode the bit flags as in the DEA Water Observations notebooks. Bucket region ap-southeast-2. Licensed CC BY 4.0 by Geoscience Australia, containing modified Copernicus Sentinel data; cite DEA Water Observations, doi:10.26186/146257, and Mueller et al. (2016).

How to access this dataset in Python

import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='ap-southeast-2', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='dea-public-data', Prefix='derivative/ga_s2_wo_provisional_3/', Delimiter='/')

Lists the files with anonymous access. Runs on any machine, with no cloud account.

Data structure

File types in sampled files: JSON, JPEG

Files

Example file: derivative/ga_s2_wo_provisional_3/0-0-1/49/HFA/2026/02/07/20260207T053419/ga_s2_wo_provisional_3_49HFA_2026-02-07_nrt.odc-metadata.yaml

Path pattern: {prefix}/{seg1}/{seg2}/{seg3}/{seg4}/{YYYY}/{seg6}/{seg7}/{seg8}/{filename}

Analyze this dataset without downloading it

On Scigantic, DEA Water Observations (Sentinel-2 Near Real-Time, Provisional, Australia) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Earth Observation & Geospatial datasets