GENOTYPE-ASTERISK ENVIRONMENT INTERACTION - A CASE-STUDY FOR DOUGLAS-FIR IN WESTERN OREGON

Unrecognized genotype x environment interactions (g*e) can bias genetic-gain predictions and models for predicting growth dynamics or species perturbations by global climate change. This study tested six sets of families in 10 plantation sites in a 78-thousand-hectare breeding zone. Plantation differences accounted for 71 percent of sums of squares (15-year heights), replications an additional 4.4 percent, families 1.9 percent, the first principal component of interaction effects 3.5 percent, and the second principal component 1.2 percent. Results in this study and in a larger survey (87 sets in 10 breeding zones) were similar: 51 percent of sets indicated significant g*e. In 46 percent of sets, the g*e interaction-family variance ratio was greater than 1; in 35 percent, greater than 1.5; and in 10 percent, greater than 5.