We propose a strategy for seasonally forecasting burned area anomalies through linking seasonal climate predictions with parsimonious empirical climate–fire models:
https://www.nature.com/articles/s41467-018-05250-0 …

Active R&D is initiated.
This includes analytical studies and laboratory studies to physically validate the analytical predictions of separate elements of the technology. Examples include components that are not yet integrated or representative.
We assess the forecasting skill of the system as it is a prototype real-time operational forecast system. This seasonal fire forecast system is based on operational dynamical climate forecast systems. In addition, all the forecasts are done by using cross-validation in order to evaluate the predictions as if they were done operationally, including the steps of the bias correction of the seasonal climate data and of the calibration of the fire-climate models. Moreover, to avoid artificial skill, the observed series are de-trended and standardized in each step of the cross-validation, avoiding using observation of the predicted year.

How does it work?

Our strategy for seasonally forecasting burned area anomalies consists in linking seasonal climate predictions with parsimonious empirical climate–fire models using the standardized precipitation index as the climate predictor for burned area.