Cluster analysis-based approaches for geospatiotemporal data mining of massive data sets for identification of forest threats

Richard Tran Mills, Forrest M. Hoffman, Jitendra Kumar, William W. Hargrove

Research output: Contribution to journalConference articlepeer-review

27 Scopus citations

Abstract

We investigate methods for geospatiotemporal data mining of multi-year land surface phenology data (250 m2 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.

Original languageEnglish
Pages (from-to)1612-1621
Number of pages10
JournalProcedia Computer Science
Volume4
DOIs
StatePublished - 2011
Event11th International Conference on Computational Science, ICCS 2011 - Singapore, Singapore
Duration: Jun 1 2011Jun 3 2011

Funding

The authors wish to thank Joseph P. Spruce at the NASA Stennis Space Center for providing quality controlled NDVI maps generated from the MODIS MOD 13 product. We thank Shivakar S. Vulli for his work on developing and testing the Bradley method sampling code during an internship at ORNL. This research was sponsored by the U.S. Department of Agriculture Forest Service, Eastern Forest Environmental Threat Assessment Center. This research used resources of the National Center for Computational Science at Oak Ridge National Laboratory, which is managed by UT-Battelle, LLC, for the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.

Keywords

  • Anomaly detection
  • Data mining
  • High performance computing
  • K-means clustering
  • MODIS
  • NDVI
  • Phenology
  • Remote sensing

Fingerprint

Dive into the research topics of 'Cluster analysis-based approaches for geospatiotemporal data mining of massive data sets for identification of forest threats'. Together they form a unique fingerprint.

Cite this