Anomalies in remotely sensed vegetation phenology using a parallel tool for principal components analysis

Richard Tran Mills; Jitendra Kumar; Forrest M. Hoffman; William W. Hargrove; Joseph P. Spruce; Steven P. Norman

doi:10.1016/j.procs.2013.05.411

Anomalies in remotely sensed vegetation phenology using a parallel tool for principal components analysis

Richard Tran Mills, Jitendra Kumar, Forrest M. Hoffman, William W. Hargrove, Joseph P. Spruce, Steven P. Norman

Research output: Contribution to journal › Conference article › peer-review

10 Scopus citations

Abstract

We investigated the use of principal components analysis (PCA) to visualize dominant patterns and identify anomalies in a multi-year land surface phenology data set (231 m × 231 m normalized difference vegetation index (NDVI) values derived from the Moderate Resolution Imaging Spectroradiometer (MODIS)) used for detecting threats to forest health in the conterminous United States (CONUS). Our goal is to find ways that PCA can be used with this massive data set to automate the process of detecting forest disturbance and attributing it to particular agents. We briefly describe the parallel computational approaches we used to make PCA feasible, and present some examples in which we have used it to visualize the seasonal vegetation phenology for the CONUS and to detect areas where anomalous NDVI traces suggest potential threats to forest health.

Original language	English
Pages (from-to)	2396-2405
Number of pages	10
Journal	Procedia Computer Science
Volume	18
DOIs	https://doi.org/10.1016/j.procs.2013.05.411
State	Published - 2013
Event	13th Annual International Conference on Computational Science, ICCS 2013 - Barcelona, Spain Duration: Jun 5 2013 → Jun 7 2013

Funding

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.

Funders	Funder number
Eastern Forest Environmental Threat Assessment Center
U.S. Department of Agriculture Forest Service
U.S. Department of Energy

Keywords

Anomaly detection
Data mining
High performance computing
MODIS
NDVI
Parallel computing
Phenology
Principal components analysis
Remote sensing
Singular value decomposition

Access to Document

10.1016/j.procs.2013.05.411

Cite this

@article{f5d7d1ae18ae4b6eb19ce02dc85dbe50,

title = "Anomalies in remotely sensed vegetation phenology using a parallel tool for principal components analysis",

abstract = "We investigated the use of principal components analysis (PCA) to visualize dominant patterns and identify anomalies in a multi-year land surface phenology data set (231 m × 231 m normalized difference vegetation index (NDVI) values derived from the Moderate Resolution Imaging Spectroradiometer (MODIS)) used for detecting threats to forest health in the conterminous United States (CONUS). Our goal is to find ways that PCA can be used with this massive data set to automate the process of detecting forest disturbance and attributing it to particular agents. We briefly describe the parallel computational approaches we used to make PCA feasible, and present some examples in which we have used it to visualize the seasonal vegetation phenology for the CONUS and to detect areas where anomalous NDVI traces suggest potential threats to forest health.",

keywords = "Anomaly detection, Data mining, High performance computing, MODIS, NDVI, Parallel computing, Phenology, Principal components analysis, Remote sensing, Singular value decomposition",

author = "Mills, {Richard Tran} and Jitendra Kumar and Hoffman, {Forrest M.} and Hargrove, {William W.} and Spruce, {Joseph P.} and Norman, {Steven P.}",

year = "2013",

doi = "10.1016/j.procs.2013.05.411",

language = "English",

volume = "18",

pages = "2396--2405",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier",

note = "13th Annual International Conference on Computational Science, ICCS 2013 ; Conference date: 05-06-2013 Through 07-06-2013",

}

TY - JOUR

T1 - Anomalies in remotely sensed vegetation phenology using a parallel tool for principal components analysis

AU - Mills, Richard Tran

AU - Kumar, Jitendra

AU - Hoffman, Forrest M.

AU - Hargrove, William W.

AU - Spruce, Joseph P.

AU - Norman, Steven P.

PY - 2013

Y1 - 2013

N2 - We investigated the use of principal components analysis (PCA) to visualize dominant patterns and identify anomalies in a multi-year land surface phenology data set (231 m × 231 m normalized difference vegetation index (NDVI) values derived from the Moderate Resolution Imaging Spectroradiometer (MODIS)) used for detecting threats to forest health in the conterminous United States (CONUS). Our goal is to find ways that PCA can be used with this massive data set to automate the process of detecting forest disturbance and attributing it to particular agents. We briefly describe the parallel computational approaches we used to make PCA feasible, and present some examples in which we have used it to visualize the seasonal vegetation phenology for the CONUS and to detect areas where anomalous NDVI traces suggest potential threats to forest health.

AB - We investigated the use of principal components analysis (PCA) to visualize dominant patterns and identify anomalies in a multi-year land surface phenology data set (231 m × 231 m normalized difference vegetation index (NDVI) values derived from the Moderate Resolution Imaging Spectroradiometer (MODIS)) used for detecting threats to forest health in the conterminous United States (CONUS). Our goal is to find ways that PCA can be used with this massive data set to automate the process of detecting forest disturbance and attributing it to particular agents. We briefly describe the parallel computational approaches we used to make PCA feasible, and present some examples in which we have used it to visualize the seasonal vegetation phenology for the CONUS and to detect areas where anomalous NDVI traces suggest potential threats to forest health.

KW - Anomaly detection

KW - Data mining

KW - High performance computing

KW - MODIS

KW - NDVI

KW - Parallel computing

KW - Phenology

KW - Principal components analysis

KW - Remote sensing

KW - Singular value decomposition

UR - http://www.scopus.com/inward/record.url?scp=84897011105&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2013.05.411

DO - 10.1016/j.procs.2013.05.411

M3 - Conference article

AN - SCOPUS:84897011105

SN - 1877-0509

VL - 18

SP - 2396

EP - 2405

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 13th Annual International Conference on Computational Science, ICCS 2013

Y2 - 5 June 2013 through 7 June 2013

ER -

Anomalies in remotely sensed vegetation phenology using a parallel tool for principal components analysis

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this