Software and instructions for kNN applications in forest resources description and estimation.

The k-nearest neighbors (kNN) method has proven to be a very useful technique to classify and propagate forest field plot information through the landscape. This classification and estimation process reproduces the covariance structure of the observed data and retains the full range of variability inherent in the sample. The applications described here are for use with Landsat TM satellite imagery and USDA Forest Service Forest Inventory and Analysis (FIA) data for Minnesota. However, these applications can be readily adapted to other imagery and forest inventory data formats. The software provides a range of statistical and map analysis and output.Research supported by NASA, the USDA Forest Service, the National Council on Air and Stream Improvement, the University of Minnesota’s College of Natural Resources and Minnesota Agricultural Experiment Station