Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method

Hector Franco-Lopez; Alan R. Ek; Marvin E. Bauer

doi:10.1016/S0034-4257(01)00209-7

Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method

Hector Franco-Lopez
, Alan R. Ek
, Marvin E. Bauer

Forest Resources

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

411 Scopus citations

Abstract

Mapping forest variables and associated characteristics is fundamental for forest planning and management. Considerable effort has been made in Northern Europe to develop techniques for wall-to-wall mapping of forest variables. Following that work, we describe the k-nearest neighbors (kNN) method for improving estimation and to produce wall-to-wall basal area, volume, and cover type maps, in the context of the USDA Forest Service's Forest Inventory and Analysis (FIA) monitoring system. Several variations within the kNN were tested, including: distance metric, weighting function, feature weighting parameters, and number of neighbors. Specific procedures to incorporate ancillary information and image enhancement techniques were also tested. Using the nearest neighbor (k = 1), Euclidean distance, a three date 18-band composite image, and feature weighting parameters, maps were constructed for basal area, volume, and cover type. The empirical, bootstrap based, 95% confidence interval for the basal area root mean square error (MSE) is (8.21, 9.02) m²/ha and for volume (48.68, 54.58) m³/ha. For the 13 FIA forest cover type classes, results indicated useful map accuracy and the choice of k = 1 retained the full range of forest types present in the region. The 95% confidence interval, obtained using the bootstrap 0.632+ technique, for the overall accuracy (OA) in the 13 cover type classification was (0.4952, 0.5459). Recommendations for applying the kNN method for mapping and regional estimation are provided.

Original language	English (US)
Pages (from-to)	251-274
Number of pages	24
Journal	Remote Sensing of Environment
Volume	77
Issue number	3
DOIs	https://doi.org/10.1016/S0034-4257(01)00209-7
State	Published - 2001

Bibliographical note

Funding Information:
Our research was supported by the College of Natural Resources and the Minnesota Agricultural Experiment Station, University of Minnesota, St. Paul, and the McIntire-Stennis Cooperative Forest Research Program. Published as MAES Paper No. 994420020 of the Minnesota Agricultural Experiment Station. The authors gratefully acknowledge the assistance of the staff of the USDA North Central Research Station FIA unit, especially Dr. Mark H. Hansen, and the Minnesota Department of Natural Resources in providing access to and interpretation of the data used in this project. Additionally, we thank Dr. Erkki Tomppo of the Finnish Forest Research Institute, Helsinki, Finland for numerous helpful suggestions in support of this work. We also thank Ms. Reija Haapanen of the University of Minnesota Department of Forest Resources for helpful suggestions with analysis and refining the manuscript for publication.

Copyright:
Copyright 2007 Elsevier B.V., All rights reserved.

Keywords

Estimation
Forest inventory
k-nearest neighbors

Publisher link

10.1016/S0034-4257(01)00209-7

Find It

Find It at U of M Libraries

Cite this

@article{dcad1af3a8be483cb9f3b4430de5ee31,

title = "Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method",

abstract = "Mapping forest variables and associated characteristics is fundamental for forest planning and management. Considerable effort has been made in Northern Europe to develop techniques for wall-to-wall mapping of forest variables. Following that work, we describe the k-nearest neighbors (kNN) method for improving estimation and to produce wall-to-wall basal area, volume, and cover type maps, in the context of the USDA Forest Service's Forest Inventory and Analysis (FIA) monitoring system. Several variations within the kNN were tested, including: distance metric, weighting function, feature weighting parameters, and number of neighbors. Specific procedures to incorporate ancillary information and image enhancement techniques were also tested. Using the nearest neighbor (k = 1), Euclidean distance, a three date 18-band composite image, and feature weighting parameters, maps were constructed for basal area, volume, and cover type. The empirical, bootstrap based, 95\% confidence interval for the basal area root mean square error (MSE) is (8.21, 9.02) m2/ha and for volume (48.68, 54.58) m3/ha. For the 13 FIA forest cover type classes, results indicated useful map accuracy and the choice of k = 1 retained the full range of forest types present in the region. The 95\% confidence interval, obtained using the bootstrap 0.632+ technique, for the overall accuracy (OA) in the 13 cover type classification was (0.4952, 0.5459). Recommendations for applying the kNN method for mapping and regional estimation are provided.",

keywords = "Estimation, Forest inventory, k-nearest neighbors",

author = "Hector Franco-Lopez and Ek, \{Alan R.\} and Bauer, \{Marvin E.\}",

note = "Funding Information: Our research was supported by the College of Natural Resources and the Minnesota Agricultural Experiment Station, University of Minnesota, St. Paul, and the McIntire-Stennis Cooperative Forest Research Program. Published as MAES Paper No. 994420020 of the Minnesota Agricultural Experiment Station. The authors gratefully acknowledge the assistance of the staff of the USDA North Central Research Station FIA unit, especially Dr. Mark H. Hansen, and the Minnesota Department of Natural Resources in providing access to and interpretation of the data used in this project. Additionally, we thank Dr. Erkki Tomppo of the Finnish Forest Research Institute, Helsinki, Finland for numerous helpful suggestions in support of this work. We also thank Ms. Reija Haapanen of the University of Minnesota Department of Forest Resources for helpful suggestions with analysis and refining the manuscript for publication. Copyright: Copyright 2007 Elsevier B.V., All rights reserved.",

year = "2001",

doi = "10.1016/S0034-4257(01)00209-7",

language = "English (US)",

volume = "77",

pages = "251--274",

journal = "Remote Sensing of Environment",

issn = "0034-4257",

publisher = "Elsevier Inc.",

number = "3",

}

TY - JOUR

T1 - Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method

AU - Franco-Lopez, Hector

AU - Ek, Alan R.

AU - Bauer, Marvin E.

N1 - Funding Information: Our research was supported by the College of Natural Resources and the Minnesota Agricultural Experiment Station, University of Minnesota, St. Paul, and the McIntire-Stennis Cooperative Forest Research Program. Published as MAES Paper No. 994420020 of the Minnesota Agricultural Experiment Station. The authors gratefully acknowledge the assistance of the staff of the USDA North Central Research Station FIA unit, especially Dr. Mark H. Hansen, and the Minnesota Department of Natural Resources in providing access to and interpretation of the data used in this project. Additionally, we thank Dr. Erkki Tomppo of the Finnish Forest Research Institute, Helsinki, Finland for numerous helpful suggestions in support of this work. We also thank Ms. Reija Haapanen of the University of Minnesota Department of Forest Resources for helpful suggestions with analysis and refining the manuscript for publication. Copyright: Copyright 2007 Elsevier B.V., All rights reserved.

PY - 2001

Y1 - 2001

N2 - Mapping forest variables and associated characteristics is fundamental for forest planning and management. Considerable effort has been made in Northern Europe to develop techniques for wall-to-wall mapping of forest variables. Following that work, we describe the k-nearest neighbors (kNN) method for improving estimation and to produce wall-to-wall basal area, volume, and cover type maps, in the context of the USDA Forest Service's Forest Inventory and Analysis (FIA) monitoring system. Several variations within the kNN were tested, including: distance metric, weighting function, feature weighting parameters, and number of neighbors. Specific procedures to incorporate ancillary information and image enhancement techniques were also tested. Using the nearest neighbor (k = 1), Euclidean distance, a three date 18-band composite image, and feature weighting parameters, maps were constructed for basal area, volume, and cover type. The empirical, bootstrap based, 95% confidence interval for the basal area root mean square error (MSE) is (8.21, 9.02) m2/ha and for volume (48.68, 54.58) m3/ha. For the 13 FIA forest cover type classes, results indicated useful map accuracy and the choice of k = 1 retained the full range of forest types present in the region. The 95% confidence interval, obtained using the bootstrap 0.632+ technique, for the overall accuracy (OA) in the 13 cover type classification was (0.4952, 0.5459). Recommendations for applying the kNN method for mapping and regional estimation are provided.

AB - Mapping forest variables and associated characteristics is fundamental for forest planning and management. Considerable effort has been made in Northern Europe to develop techniques for wall-to-wall mapping of forest variables. Following that work, we describe the k-nearest neighbors (kNN) method for improving estimation and to produce wall-to-wall basal area, volume, and cover type maps, in the context of the USDA Forest Service's Forest Inventory and Analysis (FIA) monitoring system. Several variations within the kNN were tested, including: distance metric, weighting function, feature weighting parameters, and number of neighbors. Specific procedures to incorporate ancillary information and image enhancement techniques were also tested. Using the nearest neighbor (k = 1), Euclidean distance, a three date 18-band composite image, and feature weighting parameters, maps were constructed for basal area, volume, and cover type. The empirical, bootstrap based, 95% confidence interval for the basal area root mean square error (MSE) is (8.21, 9.02) m2/ha and for volume (48.68, 54.58) m3/ha. For the 13 FIA forest cover type classes, results indicated useful map accuracy and the choice of k = 1 retained the full range of forest types present in the region. The 95% confidence interval, obtained using the bootstrap 0.632+ technique, for the overall accuracy (OA) in the 13 cover type classification was (0.4952, 0.5459). Recommendations for applying the kNN method for mapping and regional estimation are provided.

KW - Estimation

KW - Forest inventory

KW - k-nearest neighbors

UR - https://www.scopus.com/pages/publications/0034814349

UR - https://www.scopus.com/pages/publications/0034814349#tab=citedBy

U2 - 10.1016/S0034-4257(01)00209-7

DO - 10.1016/S0034-4257(01)00209-7

M3 - Article

AN - SCOPUS:0034814349

SN - 0034-4257

VL - 77

SP - 251

EP - 274

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

IS - 3

ER -

Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this