Modeling Tree Mortality Following Wildfire in Pinus ponderosa Forests in the Central Sierra-Nevada of California

Abstract

We modeled tree mortality occurring two years following wildfire in Pinus ponderosa forests using data from 1275 trees in 25 stands burned during the 1987 Stanislaus Complex fires. We used logistic regression analysis to develop models relating the probability of wildfire-induced mortality with tree size and fire severity for Pinus ponderosa, Calocedrus decurrens, Quercus chrysolepis, and Q. kelloggii. One set of models predicts mortality probability as a function of DBH and height of stem-bark char, a second set of models uses relative char height (height of stem-bark char as a proportion of tree height) as the predictor. Probability of mortality increased with increasing height of stem-bark char and decreased with increasing tree DBH and height. Analysis of receiver operating characteristic (ROC) curves indicated that both sets of models perform well for all species, with 83 to 96 percent concordance between predicted probabilities and observed outcomes. The models can be used to predict die probability of post-wildfire mortality of four tree species common in Pinus ponderosa forests in the central Sierra Nevada of California.