Land cover classification in rugged areas using simulated moderate-resolution remote sensor data and an artificial neural network

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Rugged land cover classification accuracies produced by an artificial neural network (ANN) using simulated moderate-resolution remote sensor data exceed overall accuracies produced using the maximum likelihood rule (MLR). Land cover in spatially-complex areas and at broad spatial scales may be difficult to monitor due to ambiguities in spectral reflectance information produced from cloud-related and topographic effects, or from sampling constraints. Such ambiguities may produce inconsistent estimates of changes in vegetation status, surface energy balance, run-off yields, or other land cover characteristics. By use of a 'back-classification' protocol, which uses the same pixels for testing as for training the classifier, tests of ANN versus MLR-based classifiers demonstrated the ANN-based classifier equalled or exceeded classification accuracies produced by the MLR-based classifier in five of six land cover classes evaluated.

Original languageEnglish (US)
Pages (from-to)85-96
Number of pages12
JournalInternational Journal of Remote Sensing
Volume19
Issue number1
StatePublished - 1998

Fingerprint

artificial neural network
land cover
Classifiers
Maximum likelihood
sensor
Neural networks
Sensors
topographic effect
spectral reflectance
surface energy
Energy balance
Interfacial energy
energy balance
pixel
Pixels
runoff
Sampling
vegetation
sampling
Testing

ASJC Scopus subject areas

  • Computers in Earth Sciences

Cite this

@article{1366bf975fb545818063156990cfb879,
title = "Land cover classification in rugged areas using simulated moderate-resolution remote sensor data and an artificial neural network",
abstract = "Rugged land cover classification accuracies produced by an artificial neural network (ANN) using simulated moderate-resolution remote sensor data exceed overall accuracies produced using the maximum likelihood rule (MLR). Land cover in spatially-complex areas and at broad spatial scales may be difficult to monitor due to ambiguities in spectral reflectance information produced from cloud-related and topographic effects, or from sampling constraints. Such ambiguities may produce inconsistent estimates of changes in vegetation status, surface energy balance, run-off yields, or other land cover characteristics. By use of a 'back-classification' protocol, which uses the same pixels for testing as for training the classifier, tests of ANN versus MLR-based classifiers demonstrated the ANN-based classifier equalled or exceeded classification accuracies produced by the MLR-based classifier in five of six land cover classes evaluated.",
author = "Stephen Yool",
year = "1998",
language = "English (US)",
volume = "19",
pages = "85--96",
journal = "International Joural of Remote Sensing",
issn = "0143-1161",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

TY - JOUR

T1 - Land cover classification in rugged areas using simulated moderate-resolution remote sensor data and an artificial neural network

AU - Yool, Stephen

PY - 1998

Y1 - 1998

N2 - Rugged land cover classification accuracies produced by an artificial neural network (ANN) using simulated moderate-resolution remote sensor data exceed overall accuracies produced using the maximum likelihood rule (MLR). Land cover in spatially-complex areas and at broad spatial scales may be difficult to monitor due to ambiguities in spectral reflectance information produced from cloud-related and topographic effects, or from sampling constraints. Such ambiguities may produce inconsistent estimates of changes in vegetation status, surface energy balance, run-off yields, or other land cover characteristics. By use of a 'back-classification' protocol, which uses the same pixels for testing as for training the classifier, tests of ANN versus MLR-based classifiers demonstrated the ANN-based classifier equalled or exceeded classification accuracies produced by the MLR-based classifier in five of six land cover classes evaluated.

AB - Rugged land cover classification accuracies produced by an artificial neural network (ANN) using simulated moderate-resolution remote sensor data exceed overall accuracies produced using the maximum likelihood rule (MLR). Land cover in spatially-complex areas and at broad spatial scales may be difficult to monitor due to ambiguities in spectral reflectance information produced from cloud-related and topographic effects, or from sampling constraints. Such ambiguities may produce inconsistent estimates of changes in vegetation status, surface energy balance, run-off yields, or other land cover characteristics. By use of a 'back-classification' protocol, which uses the same pixels for testing as for training the classifier, tests of ANN versus MLR-based classifiers demonstrated the ANN-based classifier equalled or exceeded classification accuracies produced by the MLR-based classifier in five of six land cover classes evaluated.

UR - http://www.scopus.com/inward/record.url?scp=0031923921&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031923921&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031923921

VL - 19

SP - 85

EP - 96

JO - International Joural of Remote Sensing

JF - International Joural of Remote Sensing

SN - 0143-1161

IS - 1

ER -