# Weathering Intensity Model of Australia (Geoscience Australia)

## Facts

- Provider: Geoscience Australia (Digital Earth Australia)
- License: CC-BY-4.0 (https://pid.geoscience.gov.au/dataset/ga/123106)
- Format: TIFF (in sampled files)
- Stored at: Amazon S3, s3://dea-public-data/weathering-intensity (ap-southeast-2)
- Access: public, readable without an account
- DOI: https://doi.org/10.26186/5c6387a429914
- Category: Earth Observation & Geospatial
- Source: https://doi.org/10.26186/5c6387a429914
- Page: https://scigantic.com/archive/3f44eb47-c176-5bc7-8ba2-4cb9496d0ba6
- Keywords: Earth Observation & Geospatial, satellite imagery, TIFF, AWS Open Data

## About

A continental prediction of the degree of surface weathering across Australia, where regolith (weathered bedrock and sediments) mantles most of the land surface. Geoscience Australia trained a Random Forest model on field estimates of weathering degree against covariates from satellite imagery, terrain attributes, airborne gamma-ray radiometrics and mapped geology; 300 random tree models were generated, their mean gives the weathering intensity prediction and their standard deviation its uncertainty, with an r-squared of 0.85 under 5-fold cross-validation. The model describes surface weathering only, and its meaning differs between residual landscapes (weathered in place) and depositional landscapes (transported material). Uses include mineral exploration in weathered terrains, regolith and soil property mapping, groundwater and landscape evolution studies. The DEA STAC catalogue lists 1,470 tiles. Checked 2026-11-16: version 1.0.1 is tiled in 1-degree cells (e.g. v1.0.1/lon_126/lat_-27/WEATHER_INTENSITY_126_-27_intensity.tif), one GeoTIFF per tile. Load with rioxarray or odc-stac. Bucket region ap-southeast-2. Licensed CC BY 4.0 by Geoscience Australia; cite Wilford, Weathering Intensity Model of Australia, doi:10.26186/5c6387a429914.

## Load the data

```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='weathering-intensity/', Delimiter='/')
```

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

## Data structure

File types in sampled files: TIFF

Example file: `weathering-intensity/v1.0.1/lon_112/lat_-11/WEATHER_INTENSITY_112_-11.yaml`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/3f44eb47-c176-5bc7-8ba2-4cb9496d0ba6
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/3f44eb47-c176-5bc7-8ba2-4cb9496d0ba6
- Over MCP: `get_schema_card` with id `3f44eb47-c176-5bc7-8ba2-4cb9496d0ba6` at https://api.scigantic.com/mcp

## Related topics

- [Earth Observation & Geospatial datasets](https://scigantic.com/topics/earth-observation-and-geospatial)
- [Satellite imagery datasets](https://scigantic.com/topics/satellite-imagery)
- [TIFF datasets](https://scigantic.com/topics/tiff)
