Clustering versus regression trees for determining ecological land units in the southern California mountains and foothills

Janet Franklin

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

A landscape stratification was required for simulation modeling of fire disturbance and succession in the mountains and foothills region of the Peninsular Ranges within San Diego County, California. Two quantitative approaches to mapping ecological land units (ELUs) were compared for a 3,878 km2 study area. These were: (a) clustering of climate overlain with key terrain variables; and (b) regression tree modeling of climate, geology, and terrain variables using a normalized difference vegetation index (NDVI), derived from a Landsat Thematic Mapper image, as the dependent variable. Terrain variables derived from a digital elevation model included slope gradient, cosine transformed slope aspect, potential solar insolation, and a topographic moisture index. For the simulation model ELUs were required that would stratify the landscape according to biomass (fuel) accumulation dynamics, related to site productivity, and probabilities of plant species establishment. Therefore, ELUs were defined using abiotic variables, and the resulting stratifications were evaluated by their ability to reduce within-class variance in the NDVI (as an index of biological productivity), and by comparing them to a map of existing vegetation. While the regression tree method resulted in classes that explained more variance in NDVI than classes resulting from unsupervised clustering, the difference was not large. In contrast, the unsupervised approach resulted in ecological land classes that were more strongly related to existing vegetation patterns.

Original languageEnglish (US)
Pages (from-to)354-368
Number of pages15
JournalForest Science
Volume49
Issue number3
StatePublished - Jun 2003
Externally publishedYes

Fingerprint

mountains
NDVI
mountain
stratification
climate
productivity
vegetation
digital elevation models
Landsat
geology
insolation
biofuels
Landsat thematic mapper
modeling
digital elevation model
simulation
simulation models
solar radiation
moisture
disturbance

Keywords

  • Digital terrain model
  • Ecological land classification
  • Landsat Thematic Mapper
  • NDVI
  • Peninsular Ranges

ASJC Scopus subject areas

  • Forestry
  • Plant Science

Cite this

Clustering versus regression trees for determining ecological land units in the southern California mountains and foothills. / Franklin, Janet.

In: Forest Science, Vol. 49, No. 3, 06.2003, p. 354-368.

Research output: Contribution to journalArticle

@article{2a56de3cef544226b62e36b43b5040b8,
title = "Clustering versus regression trees for determining ecological land units in the southern California mountains and foothills",
abstract = "A landscape stratification was required for simulation modeling of fire disturbance and succession in the mountains and foothills region of the Peninsular Ranges within San Diego County, California. Two quantitative approaches to mapping ecological land units (ELUs) were compared for a 3,878 km2 study area. These were: (a) clustering of climate overlain with key terrain variables; and (b) regression tree modeling of climate, geology, and terrain variables using a normalized difference vegetation index (NDVI), derived from a Landsat Thematic Mapper image, as the dependent variable. Terrain variables derived from a digital elevation model included slope gradient, cosine transformed slope aspect, potential solar insolation, and a topographic moisture index. For the simulation model ELUs were required that would stratify the landscape according to biomass (fuel) accumulation dynamics, related to site productivity, and probabilities of plant species establishment. Therefore, ELUs were defined using abiotic variables, and the resulting stratifications were evaluated by their ability to reduce within-class variance in the NDVI (as an index of biological productivity), and by comparing them to a map of existing vegetation. While the regression tree method resulted in classes that explained more variance in NDVI than classes resulting from unsupervised clustering, the difference was not large. In contrast, the unsupervised approach resulted in ecological land classes that were more strongly related to existing vegetation patterns.",
keywords = "Digital terrain model, Ecological land classification, Landsat Thematic Mapper, NDVI, Peninsular Ranges",
author = "Janet Franklin",
year = "2003",
month = "6",
language = "English (US)",
volume = "49",
pages = "354--368",
journal = "Forest Science",
issn = "0015-749X",
publisher = "Society of American Foresters",
number = "3",

}

TY - JOUR

T1 - Clustering versus regression trees for determining ecological land units in the southern California mountains and foothills

AU - Franklin, Janet

PY - 2003/6

Y1 - 2003/6

N2 - A landscape stratification was required for simulation modeling of fire disturbance and succession in the mountains and foothills region of the Peninsular Ranges within San Diego County, California. Two quantitative approaches to mapping ecological land units (ELUs) were compared for a 3,878 km2 study area. These were: (a) clustering of climate overlain with key terrain variables; and (b) regression tree modeling of climate, geology, and terrain variables using a normalized difference vegetation index (NDVI), derived from a Landsat Thematic Mapper image, as the dependent variable. Terrain variables derived from a digital elevation model included slope gradient, cosine transformed slope aspect, potential solar insolation, and a topographic moisture index. For the simulation model ELUs were required that would stratify the landscape according to biomass (fuel) accumulation dynamics, related to site productivity, and probabilities of plant species establishment. Therefore, ELUs were defined using abiotic variables, and the resulting stratifications were evaluated by their ability to reduce within-class variance in the NDVI (as an index of biological productivity), and by comparing them to a map of existing vegetation. While the regression tree method resulted in classes that explained more variance in NDVI than classes resulting from unsupervised clustering, the difference was not large. In contrast, the unsupervised approach resulted in ecological land classes that were more strongly related to existing vegetation patterns.

AB - A landscape stratification was required for simulation modeling of fire disturbance and succession in the mountains and foothills region of the Peninsular Ranges within San Diego County, California. Two quantitative approaches to mapping ecological land units (ELUs) were compared for a 3,878 km2 study area. These were: (a) clustering of climate overlain with key terrain variables; and (b) regression tree modeling of climate, geology, and terrain variables using a normalized difference vegetation index (NDVI), derived from a Landsat Thematic Mapper image, as the dependent variable. Terrain variables derived from a digital elevation model included slope gradient, cosine transformed slope aspect, potential solar insolation, and a topographic moisture index. For the simulation model ELUs were required that would stratify the landscape according to biomass (fuel) accumulation dynamics, related to site productivity, and probabilities of plant species establishment. Therefore, ELUs were defined using abiotic variables, and the resulting stratifications were evaluated by their ability to reduce within-class variance in the NDVI (as an index of biological productivity), and by comparing them to a map of existing vegetation. While the regression tree method resulted in classes that explained more variance in NDVI than classes resulting from unsupervised clustering, the difference was not large. In contrast, the unsupervised approach resulted in ecological land classes that were more strongly related to existing vegetation patterns.

KW - Digital terrain model

KW - Ecological land classification

KW - Landsat Thematic Mapper

KW - NDVI

KW - Peninsular Ranges

UR - http://www.scopus.com/inward/record.url?scp=0037533733&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037533733&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0037533733

VL - 49

SP - 354

EP - 368

JO - Forest Science

JF - Forest Science

SN - 0015-749X

IS - 3

ER -