k Nearest Neighbor
Estimating Forest Inventory Using Satellite Imagery
line
Next Page
BACKGROUND

Study Area

VIEW


  • The study area is largely located in the Minnesota’s FIA Unit 1, (Aspen-Birch Unit).
  • This unit is the most heavily forested region in the state. Lake and Cook Counties are more than 90% forested and the other counties in the unit are at least 60 percent forested. This Unit contains 44 percent of the state’s forest land.
  • Number of plots in forested land ~ 180, or about 720 subplots. Mean volume is 890 ft3/ac (62.16 m3/ha). Standard deviation of volume is 988 ft3/ac (68.99 m3/ha).
Project Design
  • The kNN estimation and classification method is a simple, but very powerful way to extend a wide range of field data to landscapes.
  • The method assigns a pixel the field data of the most similar pixel, for which actual field plot data exists. The similarity is defined in terms of the feature space (e.g., Euclidean distance between satellite image pixels).
  • kNN retains the full range of variability inherent in the sample.


VIEW
Subplot Design

VIEW


The new standard plot design consists of a series of fixed area, circular subplots tied to a cluster of four points that are spaced 120 ft (36.6 m) apart.
Next Page
line