Satellite data
NASA FIRMS
Near-real-time active-fire detections from NASA's satellites tell us where fires currently are - the starting point for every prediction.
How it works
Detect. Model. Map. Alert.
A deterministic pipeline that turns authoritative data into a clear picture of modelled spread and estimated time-to-impact.
How it works
From data to a decision, deterministically
Every prediction is repeatable: the same inputs produce the same output, so results can be inspected and audited.
- 01
Detect
Where fires are, right now.
Active-fire hotspots are drawn from NASA FIRMS and Digital Earth Australia on a regular cycle, giving a current national picture of where fires have been detected.
- 02
Model
Where a fire may spread, and when.
Established fire-behaviour models (McArthur) estimate spread from the detected fire, driven by weather and wind - refined over local terrain with WindNinja where terrain processing is enabled.
- 03
Map
Against the assets that matter to you.
Modelled spread and estimated time-to-impact are shown against the specific places you have registered - homes, sites, infrastructure, and land.
- 04
Alert
To the people responsible.
As risk to a registered asset changes, the people responsible for it are notified - so the right person acts on the right information in time.
Data & models
Built on authoritative Australian data + models
Fire Path AI doesn't guess. Each prediction is assembled from established, publicly accountable sources - here's what each one contributes.
Satellite data
Digital Earth Australia
Geoscience Australia's national hotspot feed adds Australian-sourced satellite coverage, cross-checking and complementing the global detections.
Weather data
Bureau of Meteorology / Open-Meteo
Temperature, humidity, and wind observations and forecasts drive both fire danger and the direction and speed a fire is likely to travel.
Model
WindNinja
Where terrain processing is enabled, broad-scale wind is re-modelled over local terrain so ridgelines and valleys shape the predicted spread; the baseline prediction uses the regional forecast wind.
Model
McArthur FFDI
The McArthur Forest Fire Danger Index turns weather and fuel conditions into a standard measure of how dangerous conditions are.
Deterministic by design
The same inputs, the same result - every time.
Predictions come from published physics and rules-based models, not opaque scoring. That makes them repeatable, inspectable, and auditable - a deliberate choice for life-safety and public-sector use.
Method & maturity. Spread modelling is physics-based (McArthur), strongest for grassland; forest and shrubland fuel-type models are being refined, and predictive accuracy is being measured rather than claimed. Fire Path AI is designed to support official decision-making, not replace it.
Request a briefing
Walk through the pipeline with us.
We can take your team from data sources to modelled spread and alerting, mapped to what you protect.