Estimating areal means and variances of forest attributes using the k-Nearest Neighbors technique and satellite imagery

Ronald E. McRoberts; Erkki O. Tomppo; Andrew O. Finley; Heikkinen Juha

doi:10.1016/j.rse.2007.04.002

Treesearch

Estimating areal means and variances of forest attributes using the k-Nearest Neighbors technique and satellite imagery

Formally Refereed

Authors:

Ronald E. McRoberts, Erkki O. Tomppo, Andrew O. Finley, Heikkinen Juha

Year:

2007

Type:

Scientific Journal

Station:

Northern Research Station

DOI:

https://doi.org/10.1016/j.rse.2007.04.002

Source:

Remote Sensing of Environment. 111:466-480.

Download (PDF 494 KB)

Download (PDF 494 KB): https://research.fs.usda.gov/download/treesearch/40476.pdf

Abstract

The k-Nearest Neighbor (k-NN) technique has become extremely popular for a variety of forest inventory mapping and estimation applications. Much of this popularity may be attributed to the non-parametric, multivariate features of the technique, its intuitiveness, and its ease of use. When used with satellite imagery and forest inventory plot data, the technique has been shown to produce useful estimates of many forest attributes including forest/non-forest, volume, and basal area. However, variance estimators for quantifying the uncertainty of means or sums of k-NN pixel-level predictions for areas of interest (AOI) consisting of multiple pixels have not been reported. The primary objectives of the study were to derive variance estimators for AOI estimates obtained from k-NN predictions and to compare precision estimates resulting from different approaches to k-NN prediction and different interpretations of those predictions.

Keywords

Landsat, probability-based inference, model-based inference, variance estimator

Citation

McRoberts, Ronald E.; Tomppo, Erkki O.; Finley, Andrew O.; Juha, Heikkinen. 2007. Estimating areal means and variances of forest attributes using the k-Nearest Neighbors technique and satellite imagery. Remote Sensing of Environment. 111:466-480.