Abstract:
Vertebrate diversity was modeled for the state of Oregon using a parametric approach to regression tree analysis. This exploratory data analysis effectively modeled
the non-linear relationships between vertebrate richness and phenology, terrain, and climate. Phenology was derived from time-series NOAA-AVHRR satellite imagery for
the year 1992 using two methods: principal component analysis and derivation of EROS
data center greenness metrics. These two measures of spatial and temporal vegetation
condition incorporated the critical temporal element in this analysis. The first three
principal components were shown to contain spatial and temporal information about the
landscape and discriminated phenologically distinct regions in Oregon. Principal components 2 and 3, 6 greenness metrics, elevation, slope, aspect, annual precipitation, and annual seasonal temperature difference were investigated as correlates to amphibians, birds, all vertebrates, reptiles, and mammals. Variation explained for each regression tree
by taxa were: amphibians (9 1%), birds (67%), all vertebrates (66%) reptiles (57%), and mammals (55%). Spatial statistics were used to quantify the pattern of each taxa and
assess validity of resulting predictions from regression tree models. Regression tree
analysis was relatively robust against spatial autocorrelation in the response data and graphical results indicated models were well fit to the data.
