A comparison of methods for monitoring multitemporal vegetation change using thematic mapper imagery

John Rogan, Janet Franklin, Dar A. Roberts

Research output: Contribution to journalArticle

256 Citations (Scopus)

Abstract

Forested ecosystems in California are undergoing accelerated change due to natural and anthropogenic disturbances. Change detection is a remote sensing technique used to monitor and map landcover change between two or more time periods and is now an essential tool in forest management activities. We compared the ability of two linear change enhancement techniques, the Multitemporal Kauth Thomas (MKT) and Multitemporal Spectral Mixture Analysis (MSMA), and two classification techniques, maximum likelihood (ML) and decision tree (DT), to accurately identify changes in vegetation cover in a southern California study area between 1990 and 1996. Supervised classification accuracy results were high (>70% correct classification for four vegetation change classes and one no-change class) and showed that (1) the DT classification approach outperformed the ML classification approach by ∼ 10%, regardless of the enhancement technique used, and (2) using DT classification, MSMA change fractions [i.e., green vegetation (GV), nonphotosynthetic vegetation (NPV), shade, and soil] outperformed MKT change features (i.e., change in brightness, greenness, and wetness) by ∼ 5%.

Original languageEnglish (US)
Pages (from-to)143-156
Number of pages14
JournalRemote Sensing of Environment
Volume80
Issue number1
DOIs
StatePublished - 2002
Externally publishedYes

Fingerprint

imagery
taxonomy
vegetation
Monitoring
monitoring
Decision trees
Maximum likelihood
methodology
image classification
Forestry
vegetation cover
forest management
land cover
Ecosystems
anthropogenic activities
remote sensing
method
comparison
Luminance
Remote sensing

Keywords

  • Decision tree classification
  • Remote sensing
  • Spectral mixture analysis
  • Vegetation change

ASJC Scopus subject areas

  • Computers in Earth Sciences
  • Earth-Surface Processes
  • Environmental Science(all)
  • Management, Monitoring, Policy and Law

Cite this

A comparison of methods for monitoring multitemporal vegetation change using thematic mapper imagery. / Rogan, John; Franklin, Janet; Roberts, Dar A.

In: Remote Sensing of Environment, Vol. 80, No. 1, 2002, p. 143-156.

Research output: Contribution to journalArticle

Rogan, John ; Franklin, Janet ; Roberts, Dar A. / A comparison of methods for monitoring multitemporal vegetation change using thematic mapper imagery. In: Remote Sensing of Environment. 2002 ; Vol. 80, No. 1. pp. 143-156.
@article{f0a53b15a07a49448f2574be997aab38,
title = "A comparison of methods for monitoring multitemporal vegetation change using thematic mapper imagery",
abstract = "Forested ecosystems in California are undergoing accelerated change due to natural and anthropogenic disturbances. Change detection is a remote sensing technique used to monitor and map landcover change between two or more time periods and is now an essential tool in forest management activities. We compared the ability of two linear change enhancement techniques, the Multitemporal Kauth Thomas (MKT) and Multitemporal Spectral Mixture Analysis (MSMA), and two classification techniques, maximum likelihood (ML) and decision tree (DT), to accurately identify changes in vegetation cover in a southern California study area between 1990 and 1996. Supervised classification accuracy results were high (>70{\%} correct classification for four vegetation change classes and one no-change class) and showed that (1) the DT classification approach outperformed the ML classification approach by ∼ 10{\%}, regardless of the enhancement technique used, and (2) using DT classification, MSMA change fractions [i.e., green vegetation (GV), nonphotosynthetic vegetation (NPV), shade, and soil] outperformed MKT change features (i.e., change in brightness, greenness, and wetness) by ∼ 5{\%}.",
keywords = "Decision tree classification, Remote sensing, Spectral mixture analysis, Vegetation change",
author = "John Rogan and Janet Franklin and Roberts, {Dar A.}",
year = "2002",
doi = "10.1016/S0034-4257(01)00296-6",
language = "English (US)",
volume = "80",
pages = "143--156",
journal = "Remote Sensing of Environment",
issn = "0034-4257",
publisher = "Elsevier Inc.",
number = "1",

}

TY - JOUR

T1 - A comparison of methods for monitoring multitemporal vegetation change using thematic mapper imagery

AU - Rogan, John

AU - Franklin, Janet

AU - Roberts, Dar A.

PY - 2002

Y1 - 2002

N2 - Forested ecosystems in California are undergoing accelerated change due to natural and anthropogenic disturbances. Change detection is a remote sensing technique used to monitor and map landcover change between two or more time periods and is now an essential tool in forest management activities. We compared the ability of two linear change enhancement techniques, the Multitemporal Kauth Thomas (MKT) and Multitemporal Spectral Mixture Analysis (MSMA), and two classification techniques, maximum likelihood (ML) and decision tree (DT), to accurately identify changes in vegetation cover in a southern California study area between 1990 and 1996. Supervised classification accuracy results were high (>70% correct classification for four vegetation change classes and one no-change class) and showed that (1) the DT classification approach outperformed the ML classification approach by ∼ 10%, regardless of the enhancement technique used, and (2) using DT classification, MSMA change fractions [i.e., green vegetation (GV), nonphotosynthetic vegetation (NPV), shade, and soil] outperformed MKT change features (i.e., change in brightness, greenness, and wetness) by ∼ 5%.

AB - Forested ecosystems in California are undergoing accelerated change due to natural and anthropogenic disturbances. Change detection is a remote sensing technique used to monitor and map landcover change between two or more time periods and is now an essential tool in forest management activities. We compared the ability of two linear change enhancement techniques, the Multitemporal Kauth Thomas (MKT) and Multitemporal Spectral Mixture Analysis (MSMA), and two classification techniques, maximum likelihood (ML) and decision tree (DT), to accurately identify changes in vegetation cover in a southern California study area between 1990 and 1996. Supervised classification accuracy results were high (>70% correct classification for four vegetation change classes and one no-change class) and showed that (1) the DT classification approach outperformed the ML classification approach by ∼ 10%, regardless of the enhancement technique used, and (2) using DT classification, MSMA change fractions [i.e., green vegetation (GV), nonphotosynthetic vegetation (NPV), shade, and soil] outperformed MKT change features (i.e., change in brightness, greenness, and wetness) by ∼ 5%.

KW - Decision tree classification

KW - Remote sensing

KW - Spectral mixture analysis

KW - Vegetation change

UR - http://www.scopus.com/inward/record.url?scp=0036221284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036221284&partnerID=8YFLogxK

U2 - 10.1016/S0034-4257(01)00296-6

DO - 10.1016/S0034-4257(01)00296-6

M3 - Article

VL - 80

SP - 143

EP - 156

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

IS - 1

ER -