Response time assessment in forest fire spread simulation: An integrated methodology for efficient exploitation of available prediction time

• A characterization methodology for 2-stage fire spread prediction method is proposed.
• The 2-stage method is based on evolutionary techniques, involving many simulations.
• Early detection of lengthy simulations allows us to speed up the process considerably.
• Replacement of lengthy simulations involves minimal degradation in the predictions.
• Results are based on a real case study of a large fire in Spain in the year 2012.

This work details a framework developed to shorten the time needed to perform fire spread predictions. The methodology presented relies on a two-stage prediction strategy which introduces a calibration stage in order to relieve the effects of uncertainty on simulator input parameters. Early assessment of the response time and quality of the results obtained constitute a key component in this method. This automatic and intelligent process of identification of lengthy simulations that slow down the course of the predictions presents a very high hit ratio. However, discarding certain simulations from the adjustment process (based on evolutionary algorithms) could lead to loss of accuracy in our predictions. A strong statistical study to analyze the impact of this action on our final predictions is reported. This study is based on a real fire which burnt 13,000 ha in the region of Catalonia (north-east of Spain) in the summer of 2012.