How to access Spark

Spark Operational – in partnership with AFAC and the Minderoo Foundation, Spark Operational has been developed to be utilised by Australasian fire and emergency service agencies. If you work for a land or emergency management agency who is an AFAC member then please contact firepredictions@afac.com.au or your agency representative for access to Spark Operational.

Spark Research – in partnership with the ARDC and the Minderoo Foundation, Spark Wildfire platform was developed to be utilised by researchers as a testing ground for fire behaviour modelling, ensemble simulations and risk estimation. If you have an affiliation with an AAF research institution then you can access the wildfire platform using your institutions credentials. A user guide for the system can be found here. For researchers without AAF access, please contact the Spark Team.

Spark2 – to use Spark commercially, please contact the Spark Team. Note that Spark2 licensing to commercial users is expected to be available in Q4 2024.

Wildfire Simulation Toolkit

Spark is a toolkit for the end-to-end processing, simulation and analysis of wildfires. Users can design custom fire propagation models by building on Spark’s GPU-based computational fire propagation solver and incorporating various input, processing and visualisation components, each tailored for wildfire modelling. Spark can be used for many applications including planning, warning and response, and research. The Spark toolkit allows you to:

• Create powerful wildfire workflows from a huge suite of built-in operations
• Define thousands of vegetation classes, each with their own unique spread rate function
• Import all compatible GDAL and NetCDF data layers for use in pre or post-processing
• Natively conduct ensemble analyses for uncertainties in a single fire scenario or for thousands of scenarios
• Visualise and output your data with a wide range of built-in widgets and writers
• Create custom user interfaces for your wildfire workflows
• Ensure reproducibility of outputs with provenance.