Forest/non-forest mapping using inventory data and satellite imagery

Abstract

For two study areas in Minnesota, USA, one heavily forested and one sparsely forested, maps of predicted proportion forest area were created using Landsat Thematic Mapper imagery, forest inventory plot data, and two prediction techniques, logistic regression and a k-Nearest Neighbours technique. The maps were used to increase the precision of forest area estimates by using them as the basis for stratified estimation. Estimates of mean proportion forest area were similar for all estimation methods, but the variances of stratified estimates were smaller than variances under an assumption of simple random sampling by factors as great as 6.

Citation

McRoberts, Ronald E. 2002. Forest/non-forest mapping using inventory data and satellite imagery. In: Proceedings of the ForestSAT Symposium, Edinbourgh, UK: Forest Research, Forestry Commission. [City, State: Publisher Unknown]. 9 p.