Journal
INTERNATIONAL JOURNAL OF WILDLAND FIRE
Volume 21, Issue 4, Pages 342-356Publisher
CSIRO PUBLISHING
DOI: 10.1071/WF11088
Keywords
cross-validation; logistic model; piecewise linear model; running average; zero-truncated Poisson
Categories
Ask authors/readers for more resources
Daily records of the location and timing of human-and lightning-caused fires in British Columbia from 1981 to 2000 were used to estimate the probability of fire occurrence within 950 20 x 20-km spatial units (similar to 950 000 km(2)) using a binary logistic regression modelling framework. Explanatory variables included lightning strikes, forest cover, surface weather observations, atmospheric stability indices and fuel moisture codes of the Canadian Fire Weather Index System. Because the influence of the explanatory variables in the models varied from year to year, model coefficients were estimated for each year. The arithmetic mean of the model coefficients was used for making daily predictions in a future year. A confidence interval around the mean or a quantile was derived from the ensemble of 20 model predictions. A leave-1-year-out cross-validation procedure was used to assess model performance for random years. The daily number of lightning-caused fires was reasonably well predicted at the provincial level (R = 0.83) and slightly less well predicted for a smaller (75 000 km(2)) administrative region. The daily number of human-caused fires was less well predicted at both the provincial (R = 0.55) and the regional level. The ability to estimate confidence intervals from the ensemble of model predictions is an advantage of the year-specific approach.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available