Download (PDF 711 KB): https://research.fs.usda.gov/download/treesearch/23346.pdf
Abstract
The objective of this study was to develop a rule based cover type classification system for the forest and woodland vegetation in the Sky Islands of southeastern Arizona. In order to develop such system we qualitatively and quantitatively compared a hierarchical (Ward’s) and a non-hierarchical (k-means) clustering method. Ecologically, unique groups and plots dominated by multiple species were more appropriately grouped using k-means. When compared numerically using classification and regression tree (CART) model, the classification k-means required fewer nodes or decision rules. Based on these results we developed a detailed cover type classification system for the existing vegetation of the Sky Islands in southeastern Arizona. The final cover types were based on the original k-means clusters, with some minor modifications made using CART analysis to compensate for overlapping values. This allowed us to transform the CART output into a dichotomous identification key for 20 detailed cover types. The final detailed cover types were linked to a flexible three-level hierarchical framework allowing users to aggregate or segregate forest lands as needed. This framework is similar to the natural organization of ecosystems, which will aid our understanding of natural processes in these forest and woodlands.
Parent Publication
Citation
Iniguez, Jose M.; Ganey, Joseph L.; Daugherty, Peter J.;Bailey, John D. 2005. Using cluster analysis and a classification and regression tree model to developed cover types in the Sky Islands of southeastern Arizona [Abstract]. In: Gottfried, Gerald J.; Gebow, Brooke S.; Eskew, Lane G.; Edminster, Carleton B., comps. Connecting mountain islands and desert seas: biodiversity and management of the Madrean Archipelago II. Proc. RMRS-P-36. Fort Collins, CO: U.S. Department of Agriculture, Forest Service, Rocky Mountain Research Station: 583
