HR: 1340h
AN: B23G-0462 Poster
TI: Geospatiotemporal Data Mining of Remotely Sensed Phenology for Unsupervised Forest Threat Detection
AU: *Mills, R T
EM: rmills@ornl.gov
AF: Oak Ridge National Laboratory, Oak Ridge, TN, USA
AU: Hoffman, F M
EM: forrest@climatemodeling.org
AF: Oak Ridge National Laboratory, Oak Ridge, TN, USA
AU: Kumar, J
EM: jkumar@climate.ornl.gov
AF: Oak Ridge National Laboratory, Oak Ridge, TN, USA
AU: Vulli, S S
EM: shivakar@climatemodeling.org
AF: Oak Ridge National Laboratory, Oak Ridge, TN, USA
AU: Hargrove, W W
EM: hnw@geobabble.org
AF: USDA Forest Service, Asheville, NC, USA
AU: Spruce, J
EM: joseph.p.spruce@nasa.gov
AF: Science Systems and Applications, Inc., John C. Stennis Space Center, Bay St. Louis, MS, USA
AB: Hargrove and Hoffman have previously developed and applied a scalable geospatiotemporal data mining approach to define a set of categorical, multivariate classes or states for describing and tracking the behavior of ecosystem properties through time within a multi-dimensional phase or state space. The method employs a standard k-means cluster analysis with enhancements that reduce the number of required comparisons, dramatically accelerating iterative convergence. In support of efforts by the USDA Forest Service to develop a National Early Warning System for Forest Disturbances, we have applied this geospatiotemporal cluster analysis procedure to annual phenology patterns derived from Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) for unsupervised change detection. We will present initial results from the analysis of seven years of 250-m MODIS NDVI data for the conterminous United States. While determining what constitutes a "normal" phenological pattern for any given location is challenging due to interannual climate variability, a spatially varying climate change trend, and the relatively short record of MODIS NDVI observations, these results demonstrate the utility of the method for detecting significant mortality events, like the progressive damage from mountain pine beetle, and suggest that the technique may be successfully implemented as a key component in an early warning system for identifying forest threats from natural and anthropogenic disturbances at a continental scale.
UR: http://www.geobabble.org/FIRST
DE: [0430] BIOGEOSCIENCES / Computational methods and data processing
DE: [0480] BIOGEOSCIENCES / Remote sensing
DE: [1926] INFORMATICS / Geospatial
DE: [1932] INFORMATICS / High-performance computing
SC: Biogeosciences (B)
MN: 2010 Fall Meeting

Acknowledgements
Research partially sponsored by the Climate and Environmental Sciences Division (CESD) of the Office of Biological and Environmental Research (OBER), U.S. Department of Energy Office of Science (SC). This research used resources of the National Center for Computational Science (NCCS) at Oak Ridge National Laboratory (ORNL) which is managed by UT-Battelle, LLC, for the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.