Integrating Neighborhood Effect and Supervised Machine Learning Techniques to Model and Simulate Forest Insect Outbreaks in British Columbia, Canada

Background and Objectives: Modelling and simulation of forest land cover change due to epidemic insect outbreaks are powerful tools that can be used in planning and preparing strategies for forest management. In this study, we propose an integrative approach to model land cover changes at a provinci...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Forests 2020-11, Vol.11 (11), p.1215
Hauptverfasser: Harati, Saeed, Perez, Liliana, Molowny-Horas, Roberto
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 11
container_start_page 1215
container_title Forests
container_volume 11
creator Harati, Saeed
Perez, Liliana
Molowny-Horas, Roberto
description Background and Objectives: Modelling and simulation of forest land cover change due to epidemic insect outbreaks are powerful tools that can be used in planning and preparing strategies for forest management. In this study, we propose an integrative approach to model land cover changes at a provincial level, using as a study case the simulation of the spatiotemporal dynamics of mountain pine beetle (MPB) infestation over the lodgepole pine forest of British Columbia (BC), Canada. This paper aims to simulate land cover change by applying supervised machine learning techniques to maps of MPB-driven deforestation. Materials and Methods: We used a 16-year series (1999–2014) of spatial information on annual mortality of pine trees due to MPB attacks, provided by the BC Ministry of Forests. We used elevation, aspect, slope, ruggedness, and weighted neighborhood of infestation as predictors. We implemented (a) generalized linear regression (GLM), and (b) random forest (RF) algorithms to simulate forestland cover changes due to MPB between 2005 and 2014. To optimize the ability of our models to predict MPB infestation in 2020, a cross-validation procedure was implemented. Results: Simulating infestations from 2008 to 2014, RF algorithms produced less error than GLM. Our simulations for the year 2020 confirmed the predictions from the BC Ministry of Forest by forecasting a slower rate of spread in future MPB infestations in the province. Conclusions: Integrating neighborhood effects as variables in model calibration allows spatiotemporal complexities to be simulated.
doi_str_mv 10.3390/f11111215
format Article
fullrecord <record><control><sourceid>gale_cross</sourceid><recordid>TN_cdi_gale_infotracmisc_A645157047</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A645157047</galeid><sourcerecordid>A645157047</sourcerecordid><originalsourceid>FETCH-LOGICAL-c292t-1a28034d20ffc209f7a7b771896fa889426d17c242962ee32ee36f24efa1bbb63</originalsourceid><addsrcrecordid>eNpNUMFKAzEUXETBoj34BwFPgtUku91sjrW0WmjtwXpe3mZfutFtUpOs4H_4wXapiAPDzGFmDpMkV4zepamk95r14Gx8kgyYlHKUSSpO__nzZBjCGz1gLArJs0HyvbARtx6isVvyjGbbVM43ztVkpjWqSMDW5KXbo_80AWuyAtUYi2SJ4G3f2aBqrPnoMJDoyMrV2B47Zte1EJHMnccQycKGfm7dxcojvAdiLHnwJprQkKlru11l4JZMwUINl8mZhjbg8Fcvktf5bDN9Gi3Xj4vpZDlSXPI4YsALmmY1p1orTqUWICohWCFzDUUhM57XTCiecZlzxLRnrnmGGlhVVXl6kVwfd7fQYmmsdtGD2pmgykmejdlY0EwcUjfHlPIuBI-63HuzA_9VMlr2v5d_v6c_-6l1rQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Integrating Neighborhood Effect and Supervised Machine Learning Techniques to Model and Simulate Forest Insect Outbreaks in British Columbia, Canada</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Harati, Saeed ; Perez, Liliana ; Molowny-Horas, Roberto</creator><creatorcontrib>Harati, Saeed ; Perez, Liliana ; Molowny-Horas, Roberto</creatorcontrib><description>Background and Objectives: Modelling and simulation of forest land cover change due to epidemic insect outbreaks are powerful tools that can be used in planning and preparing strategies for forest management. In this study, we propose an integrative approach to model land cover changes at a provincial level, using as a study case the simulation of the spatiotemporal dynamics of mountain pine beetle (MPB) infestation over the lodgepole pine forest of British Columbia (BC), Canada. This paper aims to simulate land cover change by applying supervised machine learning techniques to maps of MPB-driven deforestation. Materials and Methods: We used a 16-year series (1999–2014) of spatial information on annual mortality of pine trees due to MPB attacks, provided by the BC Ministry of Forests. We used elevation, aspect, slope, ruggedness, and weighted neighborhood of infestation as predictors. We implemented (a) generalized linear regression (GLM), and (b) random forest (RF) algorithms to simulate forestland cover changes due to MPB between 2005 and 2014. To optimize the ability of our models to predict MPB infestation in 2020, a cross-validation procedure was implemented. Results: Simulating infestations from 2008 to 2014, RF algorithms produced less error than GLM. Our simulations for the year 2020 confirmed the predictions from the BC Ministry of Forest by forecasting a slower rate of spread in future MPB infestations in the province. Conclusions: Integrating neighborhood effects as variables in model calibration allows spatiotemporal complexities to be simulated.</description><identifier>ISSN: 1999-4907</identifier><identifier>EISSN: 1999-4907</identifier><identifier>DOI: 10.3390/f11111215</identifier><language>eng</language><publisher>MDPI AG</publisher><subject>Analysis ; Beetles ; Canada ; Deforestation ; Distribution ; Environmental protection ; Forest management ; Insect pests ; Land cover ; Machine learning ; Methods ; Sustainable forestry</subject><ispartof>Forests, 2020-11, Vol.11 (11), p.1215</ispartof><rights>COPYRIGHT 2020 MDPI AG</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c292t-1a28034d20ffc209f7a7b771896fa889426d17c242962ee32ee36f24efa1bbb63</citedby><cites>FETCH-LOGICAL-c292t-1a28034d20ffc209f7a7b771896fa889426d17c242962ee32ee36f24efa1bbb63</cites><orcidid>0000-0003-2626-6379 ; 0000-0002-6599-9893 ; 0000-0003-2318-9259</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Harati, Saeed</creatorcontrib><creatorcontrib>Perez, Liliana</creatorcontrib><creatorcontrib>Molowny-Horas, Roberto</creatorcontrib><title>Integrating Neighborhood Effect and Supervised Machine Learning Techniques to Model and Simulate Forest Insect Outbreaks in British Columbia, Canada</title><title>Forests</title><description>Background and Objectives: Modelling and simulation of forest land cover change due to epidemic insect outbreaks are powerful tools that can be used in planning and preparing strategies for forest management. In this study, we propose an integrative approach to model land cover changes at a provincial level, using as a study case the simulation of the spatiotemporal dynamics of mountain pine beetle (MPB) infestation over the lodgepole pine forest of British Columbia (BC), Canada. This paper aims to simulate land cover change by applying supervised machine learning techniques to maps of MPB-driven deforestation. Materials and Methods: We used a 16-year series (1999–2014) of spatial information on annual mortality of pine trees due to MPB attacks, provided by the BC Ministry of Forests. We used elevation, aspect, slope, ruggedness, and weighted neighborhood of infestation as predictors. We implemented (a) generalized linear regression (GLM), and (b) random forest (RF) algorithms to simulate forestland cover changes due to MPB between 2005 and 2014. To optimize the ability of our models to predict MPB infestation in 2020, a cross-validation procedure was implemented. Results: Simulating infestations from 2008 to 2014, RF algorithms produced less error than GLM. Our simulations for the year 2020 confirmed the predictions from the BC Ministry of Forest by forecasting a slower rate of spread in future MPB infestations in the province. Conclusions: Integrating neighborhood effects as variables in model calibration allows spatiotemporal complexities to be simulated.</description><subject>Analysis</subject><subject>Beetles</subject><subject>Canada</subject><subject>Deforestation</subject><subject>Distribution</subject><subject>Environmental protection</subject><subject>Forest management</subject><subject>Insect pests</subject><subject>Land cover</subject><subject>Machine learning</subject><subject>Methods</subject><subject>Sustainable forestry</subject><issn>1999-4907</issn><issn>1999-4907</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNpNUMFKAzEUXETBoj34BwFPgtUku91sjrW0WmjtwXpe3mZfutFtUpOs4H_4wXapiAPDzGFmDpMkV4zepamk95r14Gx8kgyYlHKUSSpO__nzZBjCGz1gLArJs0HyvbARtx6isVvyjGbbVM43ztVkpjWqSMDW5KXbo_80AWuyAtUYi2SJ4G3f2aBqrPnoMJDoyMrV2B47Zte1EJHMnccQycKGfm7dxcojvAdiLHnwJprQkKlru11l4JZMwUINl8mZhjbg8Fcvktf5bDN9Gi3Xj4vpZDlSXPI4YsALmmY1p1orTqUWICohWCFzDUUhM57XTCiecZlzxLRnrnmGGlhVVXl6kVwfd7fQYmmsdtGD2pmgykmejdlY0EwcUjfHlPIuBI-63HuzA_9VMlr2v5d_v6c_-6l1rQ</recordid><startdate>20201101</startdate><enddate>20201101</enddate><creator>Harati, Saeed</creator><creator>Perez, Liliana</creator><creator>Molowny-Horas, Roberto</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-2626-6379</orcidid><orcidid>https://orcid.org/0000-0002-6599-9893</orcidid><orcidid>https://orcid.org/0000-0003-2318-9259</orcidid></search><sort><creationdate>20201101</creationdate><title>Integrating Neighborhood Effect and Supervised Machine Learning Techniques to Model and Simulate Forest Insect Outbreaks in British Columbia, Canada</title><author>Harati, Saeed ; Perez, Liliana ; Molowny-Horas, Roberto</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c292t-1a28034d20ffc209f7a7b771896fa889426d17c242962ee32ee36f24efa1bbb63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Analysis</topic><topic>Beetles</topic><topic>Canada</topic><topic>Deforestation</topic><topic>Distribution</topic><topic>Environmental protection</topic><topic>Forest management</topic><topic>Insect pests</topic><topic>Land cover</topic><topic>Machine learning</topic><topic>Methods</topic><topic>Sustainable forestry</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Harati, Saeed</creatorcontrib><creatorcontrib>Perez, Liliana</creatorcontrib><creatorcontrib>Molowny-Horas, Roberto</creatorcontrib><collection>CrossRef</collection><jtitle>Forests</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Harati, Saeed</au><au>Perez, Liliana</au><au>Molowny-Horas, Roberto</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Integrating Neighborhood Effect and Supervised Machine Learning Techniques to Model and Simulate Forest Insect Outbreaks in British Columbia, Canada</atitle><jtitle>Forests</jtitle><date>2020-11-01</date><risdate>2020</risdate><volume>11</volume><issue>11</issue><spage>1215</spage><pages>1215-</pages><issn>1999-4907</issn><eissn>1999-4907</eissn><abstract>Background and Objectives: Modelling and simulation of forest land cover change due to epidemic insect outbreaks are powerful tools that can be used in planning and preparing strategies for forest management. In this study, we propose an integrative approach to model land cover changes at a provincial level, using as a study case the simulation of the spatiotemporal dynamics of mountain pine beetle (MPB) infestation over the lodgepole pine forest of British Columbia (BC), Canada. This paper aims to simulate land cover change by applying supervised machine learning techniques to maps of MPB-driven deforestation. Materials and Methods: We used a 16-year series (1999–2014) of spatial information on annual mortality of pine trees due to MPB attacks, provided by the BC Ministry of Forests. We used elevation, aspect, slope, ruggedness, and weighted neighborhood of infestation as predictors. We implemented (a) generalized linear regression (GLM), and (b) random forest (RF) algorithms to simulate forestland cover changes due to MPB between 2005 and 2014. To optimize the ability of our models to predict MPB infestation in 2020, a cross-validation procedure was implemented. Results: Simulating infestations from 2008 to 2014, RF algorithms produced less error than GLM. Our simulations for the year 2020 confirmed the predictions from the BC Ministry of Forest by forecasting a slower rate of spread in future MPB infestations in the province. Conclusions: Integrating neighborhood effects as variables in model calibration allows spatiotemporal complexities to be simulated.</abstract><pub>MDPI AG</pub><doi>10.3390/f11111215</doi><orcidid>https://orcid.org/0000-0003-2626-6379</orcidid><orcidid>https://orcid.org/0000-0002-6599-9893</orcidid><orcidid>https://orcid.org/0000-0003-2318-9259</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1999-4907
ispartof Forests, 2020-11, Vol.11 (11), p.1215
issn 1999-4907
1999-4907
language eng
recordid cdi_gale_infotracmisc_A645157047
source MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals
subjects Analysis
Beetles
Canada
Deforestation
Distribution
Environmental protection
Forest management
Insect pests
Land cover
Machine learning
Methods
Sustainable forestry
title Integrating Neighborhood Effect and Supervised Machine Learning Techniques to Model and Simulate Forest Insect Outbreaks in British Columbia, Canada
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T08%3A20%3A33IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Integrating%20Neighborhood%20Effect%20and%20Supervised%20Machine%20Learning%20Techniques%20to%20Model%20and%20Simulate%20Forest%20Insect%20Outbreaks%20in%20British%20Columbia,%20Canada&rft.jtitle=Forests&rft.au=Harati,%20Saeed&rft.date=2020-11-01&rft.volume=11&rft.issue=11&rft.spage=1215&rft.pages=1215-&rft.issn=1999-4907&rft.eissn=1999-4907&rft_id=info:doi/10.3390/f11111215&rft_dat=%3Cgale_cross%3EA645157047%3C/gale_cross%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=A645157047&rfr_iscdi=true