Cluster analysis of structural stage classes to map wildland fuels in a Madrean ecosystem

Jay D. Miller, Shelley R. Danzer, Joseph M. Watts, Sheridan Stone, Stephen Yool

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Geospatial information technology is changing the nature of fire mapping science and management. Geographic information systems (GIS) and global positioning system technology coupled with remotely sensed data provide powerful tools for mapping, assessing, and understanding the complex spatial phenomena of wildland fuels and fire hazard. The effectiveness of these technologies for fire management still depends on good baseline fuels data since techniques have yet to be developed to directly interrogate understory fuels with remotely sensed data. We couple field data collections with GIS, remote sensing, and hierarchical clustering to characterize and map the variability of wildland fuels within and across vegetation types. One hundred fifty six fuel plots were sampled in eight vegetation types ranging in elevation from 1150 to 2600 m surrounding a Madrean 'sky island' mountain range in the southwestern US. Fuel plots within individual vegetation types were divided into classes representing various stages of structural development with unique fuel load characteristics using a hierarchical clustering method. Two Landsat satellite images were then classified into vegetation/fuel classes using a hybrid unsupervised/supervised approach. A back-classification accuracy assessment, which uses the same pixels to test as used to train the classifier, produced an overall Kappa of 50% for the vegetation/fuels map. The map with fuel classes within vegetation type collapsed into single classes was verified with an independent dataset, yielding an overall Kappa of 80%.

Original languageEnglish (US)
Pages (from-to)239-252
Number of pages14
JournalJournal of Environmental Management
Volume68
Issue number3
DOIs
StatePublished - Jul 1 2003

Fingerprint

Cluster analysis
Ecosystems
cluster analysis
ecosystem
vegetation type
Geographic information systems
Fires
Fire hazards
fire management
accuracy assessment
vegetation
information technology
understory
train
Landsat
Information technology
Global positioning system
Remote sensing
pixel
Classifiers

Keywords

  • Hierarchal cluster analysis
  • Mandrean vegetation
  • Remote sensing
  • Southwestern US
  • Structural stage
  • Wildland fuels

ASJC Scopus subject areas

  • Environmental Science(all)
  • Management, Monitoring, Policy and Law

Cite this

Cluster analysis of structural stage classes to map wildland fuels in a Madrean ecosystem. / Miller, Jay D.; Danzer, Shelley R.; Watts, Joseph M.; Stone, Sheridan; Yool, Stephen.

In: Journal of Environmental Management, Vol. 68, No. 3, 01.07.2003, p. 239-252.

Research output: Contribution to journalArticle

Miller, Jay D. ; Danzer, Shelley R. ; Watts, Joseph M. ; Stone, Sheridan ; Yool, Stephen. / Cluster analysis of structural stage classes to map wildland fuels in a Madrean ecosystem. In: Journal of Environmental Management. 2003 ; Vol. 68, No. 3. pp. 239-252.
@article{c0d97905dec84f51a750a65139c009c1,
title = "Cluster analysis of structural stage classes to map wildland fuels in a Madrean ecosystem",
abstract = "Geospatial information technology is changing the nature of fire mapping science and management. Geographic information systems (GIS) and global positioning system technology coupled with remotely sensed data provide powerful tools for mapping, assessing, and understanding the complex spatial phenomena of wildland fuels and fire hazard. The effectiveness of these technologies for fire management still depends on good baseline fuels data since techniques have yet to be developed to directly interrogate understory fuels with remotely sensed data. We couple field data collections with GIS, remote sensing, and hierarchical clustering to characterize and map the variability of wildland fuels within and across vegetation types. One hundred fifty six fuel plots were sampled in eight vegetation types ranging in elevation from 1150 to 2600 m surrounding a Madrean 'sky island' mountain range in the southwestern US. Fuel plots within individual vegetation types were divided into classes representing various stages of structural development with unique fuel load characteristics using a hierarchical clustering method. Two Landsat satellite images were then classified into vegetation/fuel classes using a hybrid unsupervised/supervised approach. A back-classification accuracy assessment, which uses the same pixels to test as used to train the classifier, produced an overall Kappa of 50{\%} for the vegetation/fuels map. The map with fuel classes within vegetation type collapsed into single classes was verified with an independent dataset, yielding an overall Kappa of 80{\%}.",
keywords = "Hierarchal cluster analysis, Mandrean vegetation, Remote sensing, Southwestern US, Structural stage, Wildland fuels",
author = "Miller, {Jay D.} and Danzer, {Shelley R.} and Watts, {Joseph M.} and Sheridan Stone and Stephen Yool",
year = "2003",
month = "7",
day = "1",
doi = "10.1016/S0301-4797(03)00062-8",
language = "English (US)",
volume = "68",
pages = "239--252",
journal = "Journal of Environmental Management",
issn = "0301-4797",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - Cluster analysis of structural stage classes to map wildland fuels in a Madrean ecosystem

AU - Miller, Jay D.

AU - Danzer, Shelley R.

AU - Watts, Joseph M.

AU - Stone, Sheridan

AU - Yool, Stephen

PY - 2003/7/1

Y1 - 2003/7/1

N2 - Geospatial information technology is changing the nature of fire mapping science and management. Geographic information systems (GIS) and global positioning system technology coupled with remotely sensed data provide powerful tools for mapping, assessing, and understanding the complex spatial phenomena of wildland fuels and fire hazard. The effectiveness of these technologies for fire management still depends on good baseline fuels data since techniques have yet to be developed to directly interrogate understory fuels with remotely sensed data. We couple field data collections with GIS, remote sensing, and hierarchical clustering to characterize and map the variability of wildland fuels within and across vegetation types. One hundred fifty six fuel plots were sampled in eight vegetation types ranging in elevation from 1150 to 2600 m surrounding a Madrean 'sky island' mountain range in the southwestern US. Fuel plots within individual vegetation types were divided into classes representing various stages of structural development with unique fuel load characteristics using a hierarchical clustering method. Two Landsat satellite images were then classified into vegetation/fuel classes using a hybrid unsupervised/supervised approach. A back-classification accuracy assessment, which uses the same pixels to test as used to train the classifier, produced an overall Kappa of 50% for the vegetation/fuels map. The map with fuel classes within vegetation type collapsed into single classes was verified with an independent dataset, yielding an overall Kappa of 80%.

AB - Geospatial information technology is changing the nature of fire mapping science and management. Geographic information systems (GIS) and global positioning system technology coupled with remotely sensed data provide powerful tools for mapping, assessing, and understanding the complex spatial phenomena of wildland fuels and fire hazard. The effectiveness of these technologies for fire management still depends on good baseline fuels data since techniques have yet to be developed to directly interrogate understory fuels with remotely sensed data. We couple field data collections with GIS, remote sensing, and hierarchical clustering to characterize and map the variability of wildland fuels within and across vegetation types. One hundred fifty six fuel plots were sampled in eight vegetation types ranging in elevation from 1150 to 2600 m surrounding a Madrean 'sky island' mountain range in the southwestern US. Fuel plots within individual vegetation types were divided into classes representing various stages of structural development with unique fuel load characteristics using a hierarchical clustering method. Two Landsat satellite images were then classified into vegetation/fuel classes using a hybrid unsupervised/supervised approach. A back-classification accuracy assessment, which uses the same pixels to test as used to train the classifier, produced an overall Kappa of 50% for the vegetation/fuels map. The map with fuel classes within vegetation type collapsed into single classes was verified with an independent dataset, yielding an overall Kappa of 80%.

KW - Hierarchal cluster analysis

KW - Mandrean vegetation

KW - Remote sensing

KW - Southwestern US

KW - Structural stage

KW - Wildland fuels

UR - http://www.scopus.com/inward/record.url?scp=0038268764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038268764&partnerID=8YFLogxK

U2 - 10.1016/S0301-4797(03)00062-8

DO - 10.1016/S0301-4797(03)00062-8

M3 - Article

C2 - 12837253

AN - SCOPUS:0038268764

VL - 68

SP - 239

EP - 252

JO - Journal of Environmental Management

JF - Journal of Environmental Management

SN - 0301-4797

IS - 3

ER -