TY - JOUR
T1 - Wildfire ignition-distribution modelling
T2 - A comparative study in the Huron-Manistee National Forest, Michigan, USA
AU - Bar Massada, Avi
AU - Syphard, Alexandra D.
AU - Stewart, Susan I.
AU - Radeloff, Volker C.
PY - 2013
Y1 - 2013
N2 - Wildfire ignition distribution models are powerful tools for predicting the probability of ignitions across broad areas, and identifying their drivers. Several approaches have been used for ignition-distribution modelling, yet the performance of different model types has not been compared. This is unfortunate, given that conceptually similar species-distribution models exhibit pronounced differences among model types. Therefore, our goal was to compare the predictive performance, variable importance and the spatial patterns of predicted ignition-probabilities of three ignition-distribution model types: one parametric, statistical model (Generalised Linear Models, GLM) and two machine-learning algorithms (Random Forests and Maximum Entropy, Maxent). We parameterised the models using 16 years of ignitions data and environmental data for the Huron-Manistee National Forest in Michigan, USA. Random Forests and Maxent had slightly better prediction accuracies than did GLM, but model fit was similar for all three. Variables related to human population and development were the best predictors of wildfire ignition locations in all models (although variable rankings differed slightly), along with elevation. However, despite similar model performance and variables, the map of ignition probabilities generated by Maxent was markedly different from those of the two other models. We thus suggest that when accurate predictions are desired, the outcomes of different model types should be compared, or alternatively combined, to produce ensemble predictions.
AB - Wildfire ignition distribution models are powerful tools for predicting the probability of ignitions across broad areas, and identifying their drivers. Several approaches have been used for ignition-distribution modelling, yet the performance of different model types has not been compared. This is unfortunate, given that conceptually similar species-distribution models exhibit pronounced differences among model types. Therefore, our goal was to compare the predictive performance, variable importance and the spatial patterns of predicted ignition-probabilities of three ignition-distribution model types: one parametric, statistical model (Generalised Linear Models, GLM) and two machine-learning algorithms (Random Forests and Maximum Entropy, Maxent). We parameterised the models using 16 years of ignitions data and environmental data for the Huron-Manistee National Forest in Michigan, USA. Random Forests and Maxent had slightly better prediction accuracies than did GLM, but model fit was similar for all three. Variables related to human population and development were the best predictors of wildfire ignition locations in all models (although variable rankings differed slightly), along with elevation. However, despite similar model performance and variables, the map of ignition probabilities generated by Maxent was markedly different from those of the two other models. We thus suggest that when accurate predictions are desired, the outcomes of different model types should be compared, or alternatively combined, to produce ensemble predictions.
KW - GLM
KW - Maxent
KW - Random Forests
UR - http://www.scopus.com/inward/record.url?scp=84875442374&partnerID=8YFLogxK
U2 - 10.1071/WF11178
DO - 10.1071/WF11178
M3 - Article
AN - SCOPUS:84875442374
SN - 1049-8001
VL - 22
SP - 174
EP - 183
JO - International Journal of Wildland Fire
JF - International Journal of Wildland Fire
IS - 2
ER -