A spectral three-dimensional color space model of tree crown health

Protecting the future of forests in the United States and other countries depends in part on our ability to monitor and map forest health conditions in a timely fashion to facilitate management of emerging threats and disturbances over a multitude of spatial scales. Remote sensing data and technolog...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:PLoS ONE 2022, Vol.17 (10), p.e0272360
Hauptverfasser: Monahan, William B, Arnspiger, Colton E, Bhatt, Parth, An, Zhongming, Krist, Frank J, Liu, Tao, Richard, Robert P, Edson, Cu, Froese, Robert E, Steffenson, John, Lammers, Tony C, Frosh, Randy
Format: Report
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 10
container_start_page e0272360
container_title PLoS ONE
container_volume 17
creator Monahan, William B
Arnspiger, Colton E
Bhatt, Parth
An, Zhongming
Krist, Frank J
Liu, Tao
Richard, Robert P
Edson, Cu
Froese, Robert E
Steffenson, John
Lammers, Tony C
Frosh, Randy
description Protecting the future of forests in the United States and other countries depends in part on our ability to monitor and map forest health conditions in a timely fashion to facilitate management of emerging threats and disturbances over a multitude of spatial scales. Remote sensing data and technologies have contributed to our ability to meet these needs, but existing methods relying on supervised classification are often limited to specific areas by the availability of imagery or training data, as well as model transferability. Scaling up and operationalizing these methods for general broadscale monitoring and mapping may be promoted by using simple models that are easily trained and projected across space and time with widely available imagery. Here, we describe a new model that classifies high resolution (~1 m.sup.2) 3-band red, green, blue (RGB) imagery from a single point in time into one of four color classes corresponding to tree crown condition or health: green healthy crowns, red damaged or dying crowns, gray damaged or dead crowns, and shadowed crowns where the condition status is unknown. These Tree Crown Health (TCH) models trained on data from the United States (US) Department of Agriculture, National Agriculture Imagery Program (NAIP), for all 48 States in the contiguous US and spanning years 2012 to 2019, exhibited high measures of model performance and transferability when evaluated using randomly withheld testing data (n = 122 NAIP state x year combinations; median overall accuracy 0.89-0.90; median Kappa 0.85-0.86). We present examples of how TCH models can detect and map individual tree mortality resulting from a variety of nationally significant native and invasive forest insects and diseases in the US. We conclude with discussion of opportunities and challenges for extending and implementing TCH models in support of broadscale monitoring and mapping of forest health.
doi_str_mv 10.1371/journal.pone.0272360
format Report
fullrecord <record><control><sourceid>gale</sourceid><recordid>TN_cdi_gale_infotracacademiconefile_A721050703</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A721050703</galeid><sourcerecordid>A721050703</sourcerecordid><originalsourceid>FETCH-gale_infotracacademiconefile_A7210507033</originalsourceid><addsrcrecordid>eNqVTksKwjAUDKLg9wYucoHWl4S2uiyieAD3EtJXm5LmlaTi9c3ChVuZxQzDzDCM7QXkQlXi0NMreO3ykTzmICupSpixlTgpmZUS1PxHL9k6xh6gUMeyXLFzzeOIZgra8akLiFljB_TRUhrkhhyFFNAG-UANOk4tn1KKm0BvzzvUbuq2bNFqF3H35Q3Lr5f7-ZY9tcOH9S2leZPQ4GBN-tja5NeVFFBABUr9XfgAAEtLig</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>report</recordtype></control><display><type>report</type><title>A spectral three-dimensional color space model of tree crown health</title><source>Public Library of Science (PLoS) Journals Open Access</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><source>Free Full-Text Journals in Chemistry</source><creator>Monahan, William B ; Arnspiger, Colton E ; Bhatt, Parth ; An, Zhongming ; Krist, Frank J ; Liu, Tao ; Richard, Robert P ; Edson, Cu ; Froese, Robert E ; Steffenson, John ; Lammers, Tony C ; Frosh, Randy</creator><creatorcontrib>Monahan, William B ; Arnspiger, Colton E ; Bhatt, Parth ; An, Zhongming ; Krist, Frank J ; Liu, Tao ; Richard, Robert P ; Edson, Cu ; Froese, Robert E ; Steffenson, John ; Lammers, Tony C ; Frosh, Randy</creatorcontrib><description>Protecting the future of forests in the United States and other countries depends in part on our ability to monitor and map forest health conditions in a timely fashion to facilitate management of emerging threats and disturbances over a multitude of spatial scales. Remote sensing data and technologies have contributed to our ability to meet these needs, but existing methods relying on supervised classification are often limited to specific areas by the availability of imagery or training data, as well as model transferability. Scaling up and operationalizing these methods for general broadscale monitoring and mapping may be promoted by using simple models that are easily trained and projected across space and time with widely available imagery. Here, we describe a new model that classifies high resolution (~1 m.sup.2) 3-band red, green, blue (RGB) imagery from a single point in time into one of four color classes corresponding to tree crown condition or health: green healthy crowns, red damaged or dying crowns, gray damaged or dead crowns, and shadowed crowns where the condition status is unknown. These Tree Crown Health (TCH) models trained on data from the United States (US) Department of Agriculture, National Agriculture Imagery Program (NAIP), for all 48 States in the contiguous US and spanning years 2012 to 2019, exhibited high measures of model performance and transferability when evaluated using randomly withheld testing data (n = 122 NAIP state x year combinations; median overall accuracy 0.89-0.90; median Kappa 0.85-0.86). We present examples of how TCH models can detect and map individual tree mortality resulting from a variety of nationally significant native and invasive forest insects and diseases in the US. We conclude with discussion of opportunities and challenges for extending and implementing TCH models in support of broadscale monitoring and mapping of forest health.</description><identifier>ISSN: 1932-6203</identifier><identifier>EISSN: 1932-6203</identifier><identifier>DOI: 10.1371/journal.pone.0272360</identifier><language>eng</language><publisher>Public Library of Science</publisher><subject>Forest conservation ; Methods ; Remote sensing ; Trees, Care of ; United States</subject><ispartof>PLoS ONE, 2022, Vol.17 (10), p.e0272360</ispartof><rights>COPYRIGHT 2022 Public Library of Science</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780,860,4476,27902</link.rule.ids></links><search><creatorcontrib>Monahan, William B</creatorcontrib><creatorcontrib>Arnspiger, Colton E</creatorcontrib><creatorcontrib>Bhatt, Parth</creatorcontrib><creatorcontrib>An, Zhongming</creatorcontrib><creatorcontrib>Krist, Frank J</creatorcontrib><creatorcontrib>Liu, Tao</creatorcontrib><creatorcontrib>Richard, Robert P</creatorcontrib><creatorcontrib>Edson, Cu</creatorcontrib><creatorcontrib>Froese, Robert E</creatorcontrib><creatorcontrib>Steffenson, John</creatorcontrib><creatorcontrib>Lammers, Tony C</creatorcontrib><creatorcontrib>Frosh, Randy</creatorcontrib><title>A spectral three-dimensional color space model of tree crown health</title><title>PLoS ONE</title><description>Protecting the future of forests in the United States and other countries depends in part on our ability to monitor and map forest health conditions in a timely fashion to facilitate management of emerging threats and disturbances over a multitude of spatial scales. Remote sensing data and technologies have contributed to our ability to meet these needs, but existing methods relying on supervised classification are often limited to specific areas by the availability of imagery or training data, as well as model transferability. Scaling up and operationalizing these methods for general broadscale monitoring and mapping may be promoted by using simple models that are easily trained and projected across space and time with widely available imagery. Here, we describe a new model that classifies high resolution (~1 m.sup.2) 3-band red, green, blue (RGB) imagery from a single point in time into one of four color classes corresponding to tree crown condition or health: green healthy crowns, red damaged or dying crowns, gray damaged or dead crowns, and shadowed crowns where the condition status is unknown. These Tree Crown Health (TCH) models trained on data from the United States (US) Department of Agriculture, National Agriculture Imagery Program (NAIP), for all 48 States in the contiguous US and spanning years 2012 to 2019, exhibited high measures of model performance and transferability when evaluated using randomly withheld testing data (n = 122 NAIP state x year combinations; median overall accuracy 0.89-0.90; median Kappa 0.85-0.86). We present examples of how TCH models can detect and map individual tree mortality resulting from a variety of nationally significant native and invasive forest insects and diseases in the US. We conclude with discussion of opportunities and challenges for extending and implementing TCH models in support of broadscale monitoring and mapping of forest health.</description><subject>Forest conservation</subject><subject>Methods</subject><subject>Remote sensing</subject><subject>Trees, Care of</subject><subject>United States</subject><issn>1932-6203</issn><issn>1932-6203</issn><fulltext>true</fulltext><rsrctype>report</rsrctype><creationdate>2022</creationdate><recordtype>report</recordtype><sourceid/><recordid>eNqVTksKwjAUDKLg9wYucoHWl4S2uiyieAD3EtJXm5LmlaTi9c3ChVuZxQzDzDCM7QXkQlXi0NMreO3ykTzmICupSpixlTgpmZUS1PxHL9k6xh6gUMeyXLFzzeOIZgra8akLiFljB_TRUhrkhhyFFNAG-UANOk4tn1KKm0BvzzvUbuq2bNFqF3H35Q3Lr5f7-ZY9tcOH9S2leZPQ4GBN-tja5NeVFFBABUr9XfgAAEtLig</recordid><startdate>20221005</startdate><enddate>20221005</enddate><creator>Monahan, William B</creator><creator>Arnspiger, Colton E</creator><creator>Bhatt, Parth</creator><creator>An, Zhongming</creator><creator>Krist, Frank J</creator><creator>Liu, Tao</creator><creator>Richard, Robert P</creator><creator>Edson, Cu</creator><creator>Froese, Robert E</creator><creator>Steffenson, John</creator><creator>Lammers, Tony C</creator><creator>Frosh, Randy</creator><general>Public Library of Science</general><scope/></search><sort><creationdate>20221005</creationdate><title>A spectral three-dimensional color space model of tree crown health</title><author>Monahan, William B ; Arnspiger, Colton E ; Bhatt, Parth ; An, Zhongming ; Krist, Frank J ; Liu, Tao ; Richard, Robert P ; Edson, Cu ; Froese, Robert E ; Steffenson, John ; Lammers, Tony C ; Frosh, Randy</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-gale_infotracacademiconefile_A7210507033</frbrgroupid><rsrctype>reports</rsrctype><prefilter>reports</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Forest conservation</topic><topic>Methods</topic><topic>Remote sensing</topic><topic>Trees, Care of</topic><topic>United States</topic><toplevel>online_resources</toplevel><creatorcontrib>Monahan, William B</creatorcontrib><creatorcontrib>Arnspiger, Colton E</creatorcontrib><creatorcontrib>Bhatt, Parth</creatorcontrib><creatorcontrib>An, Zhongming</creatorcontrib><creatorcontrib>Krist, Frank J</creatorcontrib><creatorcontrib>Liu, Tao</creatorcontrib><creatorcontrib>Richard, Robert P</creatorcontrib><creatorcontrib>Edson, Cu</creatorcontrib><creatorcontrib>Froese, Robert E</creatorcontrib><creatorcontrib>Steffenson, John</creatorcontrib><creatorcontrib>Lammers, Tony C</creatorcontrib><creatorcontrib>Frosh, Randy</creatorcontrib></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Monahan, William B</au><au>Arnspiger, Colton E</au><au>Bhatt, Parth</au><au>An, Zhongming</au><au>Krist, Frank J</au><au>Liu, Tao</au><au>Richard, Robert P</au><au>Edson, Cu</au><au>Froese, Robert E</au><au>Steffenson, John</au><au>Lammers, Tony C</au><au>Frosh, Randy</au><format>book</format><genre>unknown</genre><ristype>RPRT</ristype><atitle>A spectral three-dimensional color space model of tree crown health</atitle><jtitle>PLoS ONE</jtitle><date>2022-10-05</date><risdate>2022</risdate><volume>17</volume><issue>10</issue><spage>e0272360</spage><pages>e0272360-</pages><issn>1932-6203</issn><eissn>1932-6203</eissn><abstract>Protecting the future of forests in the United States and other countries depends in part on our ability to monitor and map forest health conditions in a timely fashion to facilitate management of emerging threats and disturbances over a multitude of spatial scales. Remote sensing data and technologies have contributed to our ability to meet these needs, but existing methods relying on supervised classification are often limited to specific areas by the availability of imagery or training data, as well as model transferability. Scaling up and operationalizing these methods for general broadscale monitoring and mapping may be promoted by using simple models that are easily trained and projected across space and time with widely available imagery. Here, we describe a new model that classifies high resolution (~1 m.sup.2) 3-band red, green, blue (RGB) imagery from a single point in time into one of four color classes corresponding to tree crown condition or health: green healthy crowns, red damaged or dying crowns, gray damaged or dead crowns, and shadowed crowns where the condition status is unknown. These Tree Crown Health (TCH) models trained on data from the United States (US) Department of Agriculture, National Agriculture Imagery Program (NAIP), for all 48 States in the contiguous US and spanning years 2012 to 2019, exhibited high measures of model performance and transferability when evaluated using randomly withheld testing data (n = 122 NAIP state x year combinations; median overall accuracy 0.89-0.90; median Kappa 0.85-0.86). We present examples of how TCH models can detect and map individual tree mortality resulting from a variety of nationally significant native and invasive forest insects and diseases in the US. We conclude with discussion of opportunities and challenges for extending and implementing TCH models in support of broadscale monitoring and mapping of forest health.</abstract><pub>Public Library of Science</pub><doi>10.1371/journal.pone.0272360</doi></addata></record>
fulltext fulltext
identifier ISSN: 1932-6203
ispartof PLoS ONE, 2022, Vol.17 (10), p.e0272360
issn 1932-6203
1932-6203
language eng
recordid cdi_gale_infotracacademiconefile_A721050703
source Public Library of Science (PLoS) Journals Open Access; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central; Free Full-Text Journals in Chemistry
subjects Forest conservation
Methods
Remote sensing
Trees, Care of
United States
title A spectral three-dimensional color space model of tree crown health
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T23%3A07%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=unknown&rft.atitle=A%20spectral%20three-dimensional%20color%20space%20model%20of%20tree%20crown%20health&rft.jtitle=PLoS%20ONE&rft.au=Monahan,%20William%20B&rft.date=2022-10-05&rft.volume=17&rft.issue=10&rft.spage=e0272360&rft.pages=e0272360-&rft.issn=1932-6203&rft.eissn=1932-6203&rft_id=info:doi/10.1371/journal.pone.0272360&rft_dat=%3Cgale%3EA721050703%3C/gale%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_galeid=A721050703&rfr_iscdi=true