Delineation of forest/nonforest land use classes using nearest neighbor methods

Reija Haapanen; Alan R. Ek; Marvin E. Bauer; Andrew O. Finley

doi:10.1016/j.rse.2003.10.002

Delineation of forest/nonforest land use classes using nearest neighbor methods

Reija Haapanen, Alan R. Ek, Marvin E. Bauer, Andrew O. Finley

Forest Resources

Research output: Contribution to journal › Article › peer-review

86 Scopus citations

Abstract

The k-Nearest Neighbor (kNN) method of forest attribute estimation and mapping has become an integral part of national forest inventory methods in Finland in the last decade. This success of kNN method in facilitating multi-source inventory has encouraged trials of the method in the Great Lakes Region of the United States. Here we present results from applying the method to Landsat TM and ETM+ data and land cover data collected by the USDA Forest Service's Forest Inventory and Analysis (FIA) program. In 1999, the FIA program in the state of Minnesota moved to a new annual inventory design to reach its targeted full sampling intensity over a 5-year period. This inventory design also utilizes a new 4-subplot cluster plot configuration. Using this new plot design together with 1 year of field plot observations, the kNN classification of forest/nonforest/water achieved overall accuracies ranging from 87% to 91%. Our analysis revealed several important behavioral features associated with kNN classification using the new FIA sample plot design. Results demonstrate the simplicity and utility of using kNN to produce FIA defined forest/nonforest/ water classifications.

Original language	English (US)
Pages (from-to)	265-271
Number of pages	7
Journal	Remote Sensing of Environment
Volume	89
Issue number	3
DOIs	https://doi.org/10.1016/j.rse.2003.10.002
State	Published - Feb 15 2004

Bibliographical note

Funding Information:
This research was supported by the College of Natural Resources and the Minnesota Agricultural Experiment Station, University of Minnesota, St. Paul, the McIntire-Stennis Cooperative Forest Research Program, the USDA Forest Service, NCASI, and NASA. The authors gratefully acknowledge the assistance of the staff of the USDA North Central Research Station FIA unit, especially Dr. Mark H. Hansen and Dr. Ronald E. McRoberts. Additionally, we thank Dr. Erkki Tomppo of the Finnish Forest Research Institute, Helsinki, Finland for several helpful suggestions in support of this work.

Keywords

FIA
Forest/nonforest
kNN

Access

10.1016/j.rse.2003.10.002

OpenUrl availability

Full text

Cite this

@article{e574c5be6fbc4c2f86884b5e0f4d96af,

title = "Delineation of forest/nonforest land use classes using nearest neighbor methods",

abstract = "The k-Nearest Neighbor (kNN) method of forest attribute estimation and mapping has become an integral part of national forest inventory methods in Finland in the last decade. This success of kNN method in facilitating multi-source inventory has encouraged trials of the method in the Great Lakes Region of the United States. Here we present results from applying the method to Landsat TM and ETM+ data and land cover data collected by the USDA Forest Service's Forest Inventory and Analysis (FIA) program. In 1999, the FIA program in the state of Minnesota moved to a new annual inventory design to reach its targeted full sampling intensity over a 5-year period. This inventory design also utilizes a new 4-subplot cluster plot configuration. Using this new plot design together with 1 year of field plot observations, the kNN classification of forest/nonforest/water achieved overall accuracies ranging from 87% to 91%. Our analysis revealed several important behavioral features associated with kNN classification using the new FIA sample plot design. Results demonstrate the simplicity and utility of using kNN to produce FIA defined forest/nonforest/ water classifications.",

keywords = "FIA, Forest/nonforest, kNN",

author = "Reija Haapanen and Ek, {Alan R.} and Bauer, {Marvin E.} and Finley, {Andrew O.}",

note = "Funding Information: This research was supported by the College of Natural Resources and the Minnesota Agricultural Experiment Station, University of Minnesota, St. Paul, the McIntire-Stennis Cooperative Forest Research Program, the USDA Forest Service, NCASI, and NASA. The authors gratefully acknowledge the assistance of the staff of the USDA North Central Research Station FIA unit, especially Dr. Mark H. Hansen and Dr. Ronald E. McRoberts. Additionally, we thank Dr. Erkki Tomppo of the Finnish Forest Research Institute, Helsinki, Finland for several helpful suggestions in support of this work.",

year = "2004",

month = feb,

day = "15",

doi = "10.1016/j.rse.2003.10.002",

language = "English (US)",

volume = "89",

pages = "265--271",

journal = "Remote Sensing of Environment",

issn = "0034-4257",

publisher = "Elsevier",

number = "3",

}

TY - JOUR

T1 - Delineation of forest/nonforest land use classes using nearest neighbor methods

AU - Haapanen, Reija

AU - Ek, Alan R.

AU - Bauer, Marvin E.

AU - Finley, Andrew O.

N1 - Funding Information: This research was supported by the College of Natural Resources and the Minnesota Agricultural Experiment Station, University of Minnesota, St. Paul, the McIntire-Stennis Cooperative Forest Research Program, the USDA Forest Service, NCASI, and NASA. The authors gratefully acknowledge the assistance of the staff of the USDA North Central Research Station FIA unit, especially Dr. Mark H. Hansen and Dr. Ronald E. McRoberts. Additionally, we thank Dr. Erkki Tomppo of the Finnish Forest Research Institute, Helsinki, Finland for several helpful suggestions in support of this work.

PY - 2004/2/15

Y1 - 2004/2/15

N2 - The k-Nearest Neighbor (kNN) method of forest attribute estimation and mapping has become an integral part of national forest inventory methods in Finland in the last decade. This success of kNN method in facilitating multi-source inventory has encouraged trials of the method in the Great Lakes Region of the United States. Here we present results from applying the method to Landsat TM and ETM+ data and land cover data collected by the USDA Forest Service's Forest Inventory and Analysis (FIA) program. In 1999, the FIA program in the state of Minnesota moved to a new annual inventory design to reach its targeted full sampling intensity over a 5-year period. This inventory design also utilizes a new 4-subplot cluster plot configuration. Using this new plot design together with 1 year of field plot observations, the kNN classification of forest/nonforest/water achieved overall accuracies ranging from 87% to 91%. Our analysis revealed several important behavioral features associated with kNN classification using the new FIA sample plot design. Results demonstrate the simplicity and utility of using kNN to produce FIA defined forest/nonforest/ water classifications.

AB - The k-Nearest Neighbor (kNN) method of forest attribute estimation and mapping has become an integral part of national forest inventory methods in Finland in the last decade. This success of kNN method in facilitating multi-source inventory has encouraged trials of the method in the Great Lakes Region of the United States. Here we present results from applying the method to Landsat TM and ETM+ data and land cover data collected by the USDA Forest Service's Forest Inventory and Analysis (FIA) program. In 1999, the FIA program in the state of Minnesota moved to a new annual inventory design to reach its targeted full sampling intensity over a 5-year period. This inventory design also utilizes a new 4-subplot cluster plot configuration. Using this new plot design together with 1 year of field plot observations, the kNN classification of forest/nonforest/water achieved overall accuracies ranging from 87% to 91%. Our analysis revealed several important behavioral features associated with kNN classification using the new FIA sample plot design. Results demonstrate the simplicity and utility of using kNN to produce FIA defined forest/nonforest/ water classifications.

KW - FIA

KW - Forest/nonforest

KW - kNN

UR - http://www.scopus.com/inward/record.url?scp=0842327896&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0842327896&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2003.10.002

DO - 10.1016/j.rse.2003.10.002

M3 - Article

AN - SCOPUS:0842327896

SN - 0034-4257

VL - 89

SP - 265

EP - 271

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

IS - 3

ER -

Delineation of forest/nonforest land use classes using nearest neighbor methods

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this