Prediction of Douglas-fir fertilizer response using biogeoclimatic properties in the coastal Pacific Northwest

Fertilizer response of Douglas-fir (Pseudotsuga menziesii (Mirb.) Franco) has been related to site and soil properties in the past, but the models have explained only about half of the variation in these investigations. Fertilizer response and percent response after two years were examined, according to mapped and measured biogeoclimatic variables, for 71 Douglas-fir installations in the coastal Pacific Northwest. Paired-tree installations consisted of 12-20 pairs of Douglas-fir trees with one tree fertilized with urea at 224 kg N.ha(-1). Pearson correlation coefficients and boosted regression tree (BRT) models were used to determine the best predictor variables and models of Douglas-fir fertilizer response. The BRT models, using the combination of mapped and measured variables, performed the best for predicting fertilizer response. Basal area and volume responses were most related to high forest floor and surface soil carbon to nitrogen ratios. Basal area mean annual increment (MAI) and site index were both negatively correlated with fertilizer response. Also, low basal area MAI was the most important tree measurement for predicting fertilizer response in the BRT models. Installations with many of the predictors from the BRT models (>66% of the model criteria) were found to have a significantly greater fertilizer response than installations with only a few predictors (<33% of the model criteria). These findings support the use of these models for predicting fertilizer response of similar Douglas-fir stands in the coastal Pacific Northwest.