Return to search

Investigating Selection Criteria of Constrained Cluster Analysis: Applications in Forestry

Forest measurements are inherently spatial. Soil productivity varies spatially at fine scales and tree growth responds by changes in growth-age trajectories. Measuring spatial variability is a perquisite to more effective analysis and statistical testing.

In this study, current techniques of partial redundancy analysis and constrained cluster analysis are used to explore how spatial variables determine structure in a managed regular spaced plantation. We will test for spatial relationships in the data and then explore how those spatial relationships are manifested into spatially recognizable structures. The objectives of this research are to measure, test, and map spatial variability in simulated forest plots.

Partial redundancy analysis was found to be a good method for detecting the presence or absence of spatial relationships (~95% accuracy). We found that the Calinski-Harabasz method consistently performed better at detecting the correct number of clusters when compared to several other methods. While there is still more work that can be done we believe that constrained cluster analysis has promising applications in forestry and that the Calinski-Harabasz criterion will be most useful. / Master of Science

Identiferoai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/78176
Date16 December 2014
CreatorsCorral, Gavin Richard
ContributorsStatistics, Morgan, J. P., Du, Pang, Birch, Jeffrey B.
PublisherVirginia Tech
Source SetsVirginia Tech Theses and Dissertation
Languageen_US
Detected LanguageEnglish
TypeThesis, Text
Formatapplication/pdf
RightsIn Copyright, http://rightsstatements.org/vocab/InC/1.0/

Page generated in 0.0022 seconds