Contemporary and historical classification of crop types in Arizona

Kyle A. Hartfield, Stuart Marsh, Christa D. Kirk, Yves Carriere

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

This research compares three different classification algorithms for mapping crops in Pinal County, Arizona, using both present and historical image data. The study area lacked past crop maps, and farmers were dealing with the risk of evolution of resistance to insecticides in the whitefly, a global pest of cotton, fruits, and vegetables. The ability to create historical crop maps without concurrent training data is an invaluable tool for historical integrated pest management research. Comparison of maximum likelihood, object-oriented, and regression tree classifiers was done with Landsat Thematic Mapper imagery and high quality crop maps. Classification outputs for the three years in this research all achieved overall accuracies above the traditional benchmark of 85%. Comparison of the classification results shows that the classification and regression tree technique clearly outperformed the other classifiers. Using training data from one year and applying that data to another year for classification purposes demonstrated that overall accuracies from 71% to 83% are achievable, although accuracies were consistently greater than 85% for some crops.

Original languageEnglish (US)
Pages (from-to)6024-6036
Number of pages13
JournalInternational Journal of Remote Sensing
Volume34
Issue number17
DOIs
StatePublished - 2013

Fingerprint

crop
whitefly
integrated pest management
Landsat thematic mapper
vegetable
insecticide
cotton
imagery
fruit
comparison

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)

Cite this

Contemporary and historical classification of crop types in Arizona. / Hartfield, Kyle A.; Marsh, Stuart; Kirk, Christa D.; Carriere, Yves.

In: International Journal of Remote Sensing, Vol. 34, No. 17, 2013, p. 6024-6036.

Research output: Contribution to journalArticle

@article{a826053037b24b49a11b148e6a1e1528,
title = "Contemporary and historical classification of crop types in Arizona",
abstract = "This research compares three different classification algorithms for mapping crops in Pinal County, Arizona, using both present and historical image data. The study area lacked past crop maps, and farmers were dealing with the risk of evolution of resistance to insecticides in the whitefly, a global pest of cotton, fruits, and vegetables. The ability to create historical crop maps without concurrent training data is an invaluable tool for historical integrated pest management research. Comparison of maximum likelihood, object-oriented, and regression tree classifiers was done with Landsat Thematic Mapper imagery and high quality crop maps. Classification outputs for the three years in this research all achieved overall accuracies above the traditional benchmark of 85{\%}. Comparison of the classification results shows that the classification and regression tree technique clearly outperformed the other classifiers. Using training data from one year and applying that data to another year for classification purposes demonstrated that overall accuracies from 71{\%} to 83{\%} are achievable, although accuracies were consistently greater than 85{\%} for some crops.",
author = "Hartfield, {Kyle A.} and Stuart Marsh and Kirk, {Christa D.} and Yves Carriere",
year = "2013",
doi = "10.1080/01431161.2013.793861",
language = "English (US)",
volume = "34",
pages = "6024--6036",
journal = "International Joural of Remote Sensing",
issn = "0143-1161",
publisher = "Taylor and Francis Ltd.",
number = "17",

}

TY - JOUR

T1 - Contemporary and historical classification of crop types in Arizona

AU - Hartfield, Kyle A.

AU - Marsh, Stuart

AU - Kirk, Christa D.

AU - Carriere, Yves

PY - 2013

Y1 - 2013

N2 - This research compares three different classification algorithms for mapping crops in Pinal County, Arizona, using both present and historical image data. The study area lacked past crop maps, and farmers were dealing with the risk of evolution of resistance to insecticides in the whitefly, a global pest of cotton, fruits, and vegetables. The ability to create historical crop maps without concurrent training data is an invaluable tool for historical integrated pest management research. Comparison of maximum likelihood, object-oriented, and regression tree classifiers was done with Landsat Thematic Mapper imagery and high quality crop maps. Classification outputs for the three years in this research all achieved overall accuracies above the traditional benchmark of 85%. Comparison of the classification results shows that the classification and regression tree technique clearly outperformed the other classifiers. Using training data from one year and applying that data to another year for classification purposes demonstrated that overall accuracies from 71% to 83% are achievable, although accuracies were consistently greater than 85% for some crops.

AB - This research compares three different classification algorithms for mapping crops in Pinal County, Arizona, using both present and historical image data. The study area lacked past crop maps, and farmers were dealing with the risk of evolution of resistance to insecticides in the whitefly, a global pest of cotton, fruits, and vegetables. The ability to create historical crop maps without concurrent training data is an invaluable tool for historical integrated pest management research. Comparison of maximum likelihood, object-oriented, and regression tree classifiers was done with Landsat Thematic Mapper imagery and high quality crop maps. Classification outputs for the three years in this research all achieved overall accuracies above the traditional benchmark of 85%. Comparison of the classification results shows that the classification and regression tree technique clearly outperformed the other classifiers. Using training data from one year and applying that data to another year for classification purposes demonstrated that overall accuracies from 71% to 83% are achievable, although accuracies were consistently greater than 85% for some crops.

UR - http://www.scopus.com/inward/record.url?scp=84879520844&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879520844&partnerID=8YFLogxK

U2 - 10.1080/01431161.2013.793861

DO - 10.1080/01431161.2013.793861

M3 - Article

AN - SCOPUS:84879520844

VL - 34

SP - 6024

EP - 6036

JO - International Joural of Remote Sensing

JF - International Joural of Remote Sensing

SN - 0143-1161

IS - 17

ER -