# World Bank Global Wildfire Hazard: Fire Weather Index (FWI) Return Levels, 2, 10 and 30 year, 0.5 degree (COG)

## Facts

- Provider: World Bank / GFDRR and CSIRO; COG mirror by Portolan Mirrors
- License: CC-BY-4.0 (https://datacatalog.worldbank.org/search/dataset/0066912/global-wildfire-hazard)
- Format: JSON, TIFF, PNG (in sampled files)
- Stored at: Amazon S3, s3://us-west-2.opendata.source.coop/portolan-mirrors/wb-fwi (us-west-2)
- Access: public, readable without an account
- Category: Climate & Weather
- Source: https://datacatalog.worldbank.org/search/dataset/0066912/global-wildfire-hazard
- Page: https://scigantic.com/archive/8a9e99eb-e137-53dc-8d8e-a0bb020e32a5
- Keywords: Climate & Weather, JSON, TIFF, PNG, AWS Open Data

## About

Global wildfire hazard grids from the World Bank, computed by CSIRO for the ThinkHazard! wildfire layer: for each 0.5 degree cell, the yearly maximum Canadian Fire Weather Index (FWI) expected once in 2, 10 and 30 years, derived from daily FWI in NASA's Global Fire Weather Database (GFWED) for 1981 to 2016. One collection per return period (fwi-rp2/, fwi-rp10/, fwi-rp30/), each a single Cloud Optimized GeoTIFF such as csiro_wf_max_fwi_rp2.tif with embedded statistics, converted from the World Bank GeoTIFFs with pixel values unchanged; a STAC catalog and an agent guide describe the quirks, for example that 0 marks masked oceans and deserts as well as cells with no fire weather. Used for screening wildfire hazard in disaster risk assessments, infrastructure planning and climate risk studies. Read with rasterio or GDAL. Licensed CC BY 4.0 as listed in the World Bank Data Catalog; attribute the World Bank and CSIRO.

## Load the data

```python
import boto3
from botocore import UNSIGNED
from botocore.client import Config
s3 = boto3.client('s3', region_name='us-west-2', config=Config(signature_version=UNSIGNED))
s3.list_objects_v2(Bucket='us-west-2.opendata.source.coop', Prefix='portolan-mirrors/wb-fwi/', Delimiter='/')
```

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

## Data structure

File types in sampled files: JSON, TIFF, PNG

Example file: `portolan-mirrors/wb-fwi/fwi-rp10/AGENTS.md`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/8a9e99eb-e137-53dc-8d8e-a0bb020e32a5
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/8a9e99eb-e137-53dc-8d8e-a0bb020e32a5
- Over MCP: `get_schema_card` with id `8a9e99eb-e137-53dc-8d8e-a0bb020e32a5` at https://api.scigantic.com/mcp

## Related topics

- [JSON datasets](https://scigantic.com/topics/json)
- [TIFF datasets](https://scigantic.com/topics/tiff)
- [Climate & Weather datasets](https://scigantic.com/topics/climate-and-weather)
- [PNG datasets](https://scigantic.com/topics/png)
