Abstract
Abstract Fire behavior prediction models can assist environmental agencies with fire prevention and control. This study aimed to adjust a fire prediction model for the state of Minas Gerais, Brazil. Using the R program and hotspots provided by the National Institute for Space Research (INPE) for 2010, prediction of the probability of fires through the Random Forest algorithm was conducted using the Bootstrapping method. The model generated a prediction map with global kappa value of 0.65. External validation was performed with hotspots in 2015. Results showed that 58% of the hotspots are in areas with ignition probability > 50%, being 24% of them in areas with 25-50% probability, and 17% in areas with < 25% probability. These results were considered satisfactory, demonstrating that the model is suitable for predicting fires.
Highlights
AND OBJECTIVESThe controlled and natural forest fires are among the main environmental problems, because in addition to the biodiversity loss, they are responsible for greenhouse gas emission
Using the R program and hotspots provided by the National Institute for Space Research (INPE) for 2010, prediction of the probability of fires through the Random Forest algorithm was conducted using the Bootstrapping method
Agility and efficiency in the detection and monitoring of forest fires is essential for the control, management, and operational costs reduction in combating fires and reducing the damages caused (Alves & Nóbrega, 2011)
Summary
The controlled and natural forest fires are among the main environmental problems, because in addition to the biodiversity loss (of both fauna and flora), they are responsible for greenhouse gas emission Depending on their intensity and frequency, they cause soil degradation through a series of modifications in its physical, chemical and biological nature (Redin et al, 2011). The categorical maps produced via simulation or statistical modeling from samples and mapped environmental variables are widely used in the definition of models (Prasad et al, 2006) The results of these analyses can be used to compare current with previous fire data and assess their temporal dynamics in a given historical series or season (months) more prone to fire occurrence, generating useful information for managers and decision-makers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
