Forestry Data Science: Reclassifying LANDFIRE's Existing Vegetation Type Variable

Presented by:
Madelon Basil (Swarthmore College)

This project is centered on exploratory data analysis and the reclassification of data products collected by the USGS LANDFIRE program. Our research involved collapsing the EVT (Existing Vegetation Type) variable used by LANDFIRE into categories that maximized homogeneity with respect to four response variables: biomass, volume, basal area, and tree count. The k-means clustering algorithm was the primary method used to determine how to best collapse EVT with regard to both statistical patterning and ecological factors. This strategy, along with creation of a "zero" cluster and flexibility in altering k values, allowed us to condense the 182 EVT categories present in the Interior West region into two different schemes (with five and ten EVT categories, respectively). Our hope is that these newly-collapsed versions of the EVT variable can effectively supplement the field data collected by the FIA (Forest Inventory and Analysis) and potentially improve estimation of forest attributes across the country.