An Operational Global Probability-of-Fire (PoF) Forecast : Can we predict extreme events?

Wildfires have widespread effects on local ecosystems, communities, air quality, and global atmospheric conditions. Accurate wildfire forecasts can be used by local communities and agencies to manage and respond to wildfires effectively. As such, it is essential these predictions are not only accurate but are accessible in real-time and provide sufficient advanced notice to ensure successful actions can be taken. Existing systems typically use fire danger indices to predict landscape flammability, based on meteorological forecasts alone, often using little or no direct information on land surface or vegetation state. Here, we use a vegetation characteristic model, weather forecasts and a data-driven machine learning approach to construct a global daily ~9 km resolution Probability of Fire (PoF) model operating at multiple lead times. The PoF model outperforms existing indices, providing accurate forecasts of fire activity up to 10 days in advance, and in some cases up to 30 days and has been deployed operationally at the European Centre for Medium-Range Weather Forecasts (ECMWF). The model can also be used to investigate historical shifts in regional fire patterns. Furthermore, the underlying data driven approach allows PoF to be used for fire attribution, isolating key variables for specific fire events or for looking at the relationships between variables and fire occurrence. The 2023 Canadian wildfire season is used as a test case to assess model performance at predicting extreme wildfire events.