@InProceedings{Mills_ICCS_20110601,
 author		= {Richard Tran Mills and Forrest M. Hoffman and Jitendra Kumar and William W. Hargrove},
 title		= {Cluster Analysis-Based Approaches for Geospatiotemporal Data Mining of Massive Data Sets for Identification of Forest Threats},
 booktitle	= {Proceedings of the International Conference on Computational Science ({ICCS} 2011)},
 editor		= {Mitsuhisa Sato and Satoshi Matsuoka and Peter M. Sloot and G. Dick {van Albada} and Jack Dongarra},
 publisher	= {Elsevier},
 address	= {Amsterdam},
 series		= PCS,
 dates		= {1--3 June 2011},
 location	= {Nanyang Technological University, Singapore},
 volume		= 4,
 pages		= {1612--1621},
 doi		= {10.1016/j.procs.2011.04.174},
 issn		= {1877-0509},
 day		= 1,
 month		= jun,
 year		= 2011,
 abstract	= {We investigate methods for geospatiotemporal data mining of multi-year land surface phenology data (250 m$^2$ Normalized Difference Vegetation Index (NDVI) values derived from the Moderate Resolution Imaging Spectrometer (MODIS) in this study) for the conterminous United States (CONUS) as part of an early warning system for detecting threats to forest ecosystems. The approaches explored here are based on $k$-means cluster analysis of this massive data set, which provides a basis for defining the bounds of the expected or ``normal'' phenological patterns that indicate healthy vegetation at a given geographic location. We briefly describe the computational approaches we have used to make cluster analysis of such massive data sets feasible, describe approaches we have explored for distinguishing between normal and abnormal phenology, and present some examples in which we have applied these approaches to identify various forest disturbances in the CONUS.}
}