A comparison of Nebraska reservoir classes estimated from watershed-based classification models and ecoregions

H. N.N. Bulley, D. B. Marx, J. W. Merchant, J. C. Holz, C. P. Derksen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Regulatory agencies have been investigating a number of alternatives for classifying lakes into hydogeologically and ecologically similar assemblages that will facilitate establishment of attainable water quality standards. Concerns over the ability of traditional statistical classifiers to effectively classify environmental data have led to increasing interest in machine (predictive) learning classification tools such as decision trees. This paper compares the performance (classification strength) of a classification tree-based watershed classification model of Nebraska reservoirs to a discriminant analysis (DA)-based watershed classification system and reservoir classes derived from Omernik's Level IV Ecoregions. The performance of classification tree and DA-based watershed classification methods were also compared with respect to their cross-validation prediction errors. The results suggest that both watershed-based classification approaches (classification tree and DA) were more effective than Omernik's Level IV ecoregions in accounting for observed variations in water quality characteristics of Nebraska reservoirs. Moreover, this study demonstrates the utility of a classification tree algorithm, either as a supplement or alternative to DA, in handling the complexities of watershed variables and classifying Nebraska reservoirs for the purpose of water quality management. The classification tree also provides water resource managers with a useful interpretive classification interface.

Original languageEnglish (US)
Pages (from-to)90-102
Number of pages13
JournalJournal of Environmental Informatics
Volume11
Issue number2
DOIs
StatePublished - Jun 1 2008

Fingerprint

ecoregion
Watersheds
watershed
Discriminant analysis
discriminant analysis
Water quality
comparison
Watershed
water quality
Quality management
Decision trees
Water resources
Lakes
Managers
Classifiers
water resource

Keywords

  • Classification tree
  • Discriminant analysis
  • Ecoregions
  • Reservoirs
  • Water quality
  • Watershed

ASJC Scopus subject areas

  • Decision Sciences(all)
  • Environmental Science(all)
  • Computer Science Applications

Cite this

A comparison of Nebraska reservoir classes estimated from watershed-based classification models and ecoregions. / Bulley, H. N.N.; Marx, D. B.; Merchant, J. W.; Holz, J. C.; Derksen, C. P.

In: Journal of Environmental Informatics, Vol. 11, No. 2, 01.06.2008, p. 90-102.

Research output: Contribution to journalArticle

Bulley, H. N.N. ; Marx, D. B. ; Merchant, J. W. ; Holz, J. C. ; Derksen, C. P. / A comparison of Nebraska reservoir classes estimated from watershed-based classification models and ecoregions. In: Journal of Environmental Informatics. 2008 ; Vol. 11, No. 2. pp. 90-102.
@article{653f00b77b87433bab92952340f54130,
title = "A comparison of Nebraska reservoir classes estimated from watershed-based classification models and ecoregions",
abstract = "Regulatory agencies have been investigating a number of alternatives for classifying lakes into hydogeologically and ecologically similar assemblages that will facilitate establishment of attainable water quality standards. Concerns over the ability of traditional statistical classifiers to effectively classify environmental data have led to increasing interest in machine (predictive) learning classification tools such as decision trees. This paper compares the performance (classification strength) of a classification tree-based watershed classification model of Nebraska reservoirs to a discriminant analysis (DA)-based watershed classification system and reservoir classes derived from Omernik's Level IV Ecoregions. The performance of classification tree and DA-based watershed classification methods were also compared with respect to their cross-validation prediction errors. The results suggest that both watershed-based classification approaches (classification tree and DA) were more effective than Omernik's Level IV ecoregions in accounting for observed variations in water quality characteristics of Nebraska reservoirs. Moreover, this study demonstrates the utility of a classification tree algorithm, either as a supplement or alternative to DA, in handling the complexities of watershed variables and classifying Nebraska reservoirs for the purpose of water quality management. The classification tree also provides water resource managers with a useful interpretive classification interface.",
keywords = "Classification tree, Discriminant analysis, Ecoregions, Reservoirs, Water quality, Watershed",
author = "Bulley, {H. N.N.} and Marx, {D. B.} and Merchant, {J. W.} and Holz, {J. C.} and Derksen, {C. P.}",
year = "2008",
month = "6",
day = "1",
doi = "10.3808/jei.200800114",
language = "English (US)",
volume = "11",
pages = "90--102",
journal = "Journal of Environmental Informatics",
issn = "1726-2135",
publisher = "International Society for Environmental Information Sciences",
number = "2",

}

TY - JOUR

T1 - A comparison of Nebraska reservoir classes estimated from watershed-based classification models and ecoregions

AU - Bulley, H. N.N.

AU - Marx, D. B.

AU - Merchant, J. W.

AU - Holz, J. C.

AU - Derksen, C. P.

PY - 2008/6/1

Y1 - 2008/6/1

N2 - Regulatory agencies have been investigating a number of alternatives for classifying lakes into hydogeologically and ecologically similar assemblages that will facilitate establishment of attainable water quality standards. Concerns over the ability of traditional statistical classifiers to effectively classify environmental data have led to increasing interest in machine (predictive) learning classification tools such as decision trees. This paper compares the performance (classification strength) of a classification tree-based watershed classification model of Nebraska reservoirs to a discriminant analysis (DA)-based watershed classification system and reservoir classes derived from Omernik's Level IV Ecoregions. The performance of classification tree and DA-based watershed classification methods were also compared with respect to their cross-validation prediction errors. The results suggest that both watershed-based classification approaches (classification tree and DA) were more effective than Omernik's Level IV ecoregions in accounting for observed variations in water quality characteristics of Nebraska reservoirs. Moreover, this study demonstrates the utility of a classification tree algorithm, either as a supplement or alternative to DA, in handling the complexities of watershed variables and classifying Nebraska reservoirs for the purpose of water quality management. The classification tree also provides water resource managers with a useful interpretive classification interface.

AB - Regulatory agencies have been investigating a number of alternatives for classifying lakes into hydogeologically and ecologically similar assemblages that will facilitate establishment of attainable water quality standards. Concerns over the ability of traditional statistical classifiers to effectively classify environmental data have led to increasing interest in machine (predictive) learning classification tools such as decision trees. This paper compares the performance (classification strength) of a classification tree-based watershed classification model of Nebraska reservoirs to a discriminant analysis (DA)-based watershed classification system and reservoir classes derived from Omernik's Level IV Ecoregions. The performance of classification tree and DA-based watershed classification methods were also compared with respect to their cross-validation prediction errors. The results suggest that both watershed-based classification approaches (classification tree and DA) were more effective than Omernik's Level IV ecoregions in accounting for observed variations in water quality characteristics of Nebraska reservoirs. Moreover, this study demonstrates the utility of a classification tree algorithm, either as a supplement or alternative to DA, in handling the complexities of watershed variables and classifying Nebraska reservoirs for the purpose of water quality management. The classification tree also provides water resource managers with a useful interpretive classification interface.

KW - Classification tree

KW - Discriminant analysis

KW - Ecoregions

KW - Reservoirs

KW - Water quality

KW - Watershed

UR - http://www.scopus.com/inward/record.url?scp=45549095466&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=45549095466&partnerID=8YFLogxK

U2 - 10.3808/jei.200800114

DO - 10.3808/jei.200800114

M3 - Article

AN - SCOPUS:45549095466

VL - 11

SP - 90

EP - 102

JO - Journal of Environmental Informatics

JF - Journal of Environmental Informatics

SN - 1726-2135

IS - 2

ER -