Loading…

Reconstructing palaeoclimatic variables from fossil pollen using boosted regression trees: comparison and synthesis with other quantitative reconstruction methods

We test and analyse a new calibration method, boosted regression trees (BRTs) in palaeoclimatic reconstructions based on fossil pollen assemblages. We apply BRTs to multiple Holocene and Lateglacial pollen sequences from northern Europe, and compare their performance with two commonly-used calibrati...

Full description

Saved in:
Bibliographic Details
Published in:Quaternary science reviews 2014-03, Vol.88, p.69-81
Main Authors: Salonen, J. Sakari, Luoto, Miska, Alenius, Teija, Heikkilä, Maija, Seppä, Heikki, Telford, Richard J., Birks, H. John B.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-a371t-895a1ea812a4c373f417210341f7d4ba01b113aa3d01f28569b0796b2fb54ed63
cites cdi_FETCH-LOGICAL-a371t-895a1ea812a4c373f417210341f7d4ba01b113aa3d01f28569b0796b2fb54ed63
container_end_page 81
container_issue
container_start_page 69
container_title Quaternary science reviews
container_volume 88
creator Salonen, J. Sakari
Luoto, Miska
Alenius, Teija
Heikkilä, Maija
Seppä, Heikki
Telford, Richard J.
Birks, H. John B.
description We test and analyse a new calibration method, boosted regression trees (BRTs) in palaeoclimatic reconstructions based on fossil pollen assemblages. We apply BRTs to multiple Holocene and Lateglacial pollen sequences from northern Europe, and compare their performance with two commonly-used calibration methods: weighted averaging regression (WA) and the modern-analogue technique (MAT). Using these calibration methods and fossil pollen data, we present synthetic reconstructions of Holocene summer temperature, winter temperature, and water balance changes in northern Europe. Highly consistent trends are found for summer temperature, with a distinct Holocene thermal maximum at ca 8000–4000 cal. a BP, with a mean Tjja anomaly of ca +0.7 °C at 6 ka compared to 0.5 ka. We were unable to reconstruct reliably winter temperature or water balance, due to the confounding effects of summer temperature and the great between-reconstruction variability. We find BRTs to be a promising tool for quantitative reconstructions from palaeoenvironmental proxy data. BRTs show good performance in cross-validations compared with WA and MAT, can model a variety of taxon response types, find relevant predictors and incorporate interactions between predictors, and show some robustness with non-analogue fossil assemblages. •Boosted regression trees (BRTs) tested as a palaeoclimatic reconstruction method.•BRTs tested in reconstructions based on northern European fossil pollen sequences.•BRTs compared with two commonly-used reconstruction methods (WA and MAT).•BRTs fare a promising reconstruction method with major theoretical strengths.•Synthesis reconstructions of Holocene palaeoclimate of northern Europe are presented.
doi_str_mv 10.1016/j.quascirev.2014.01.011
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1529913669</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0277379114000183</els_id><sourcerecordid>1529913669</sourcerecordid><originalsourceid>FETCH-LOGICAL-a371t-895a1ea812a4c373f417210341f7d4ba01b113aa3d01f28569b0796b2fb54ed63</originalsourceid><addsrcrecordid>eNqFkd-K1DAUxoMoOK4-g7n0pmNO0jatd8viP1hYWBS8C2l6upMhbbo56ci-jk9qhhG9FA6EJN_vy8n5GHsLYg8C2vfH_eNmyfmEp70UUO8FlIJnbAedVlXd6B_P2U5IrSule3jJXhEdhRCN7OSO_bpHFxfKaXPZLw98tcFidMHPNnvHTzZ5OwQkPqU48ykS-cDXGAIufKMzMcRIGUee8CFhuY4LzwmRPnAX57XwVE7sMnJ6WvIByRP_6fOBx7JJvPS-ZJ_LYycsFv96KdCM-RBHes1eTDYQvvmzXrHvnz5-u_lS3d59_npzfVtZpSFXXd9YQNuBtLVTWk01aAlC1TDpsR6sgAFAWatGAZPsmrYfhO7bQU5DU-PYqiv27uK7pvi4IWUze3IYgl0wbmSgkX0Pqm37ItUXqUtlIgkns6YysfRkQJhzKuZo_qZizqkYAaWgkNcXEstPTh6TKSJcHI5F6rIZo_-vx2_fe6Cq</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1529913669</pqid></control><display><type>article</type><title>Reconstructing palaeoclimatic variables from fossil pollen using boosted regression trees: comparison and synthesis with other quantitative reconstruction methods</title><source>Elsevier</source><creator>Salonen, J. Sakari ; Luoto, Miska ; Alenius, Teija ; Heikkilä, Maija ; Seppä, Heikki ; Telford, Richard J. ; Birks, H. John B.</creator><creatorcontrib>Salonen, J. Sakari ; Luoto, Miska ; Alenius, Teija ; Heikkilä, Maija ; Seppä, Heikki ; Telford, Richard J. ; Birks, H. John B.</creatorcontrib><description>We test and analyse a new calibration method, boosted regression trees (BRTs) in palaeoclimatic reconstructions based on fossil pollen assemblages. We apply BRTs to multiple Holocene and Lateglacial pollen sequences from northern Europe, and compare their performance with two commonly-used calibration methods: weighted averaging regression (WA) and the modern-analogue technique (MAT). Using these calibration methods and fossil pollen data, we present synthetic reconstructions of Holocene summer temperature, winter temperature, and water balance changes in northern Europe. Highly consistent trends are found for summer temperature, with a distinct Holocene thermal maximum at ca 8000–4000 cal. a BP, with a mean Tjja anomaly of ca +0.7 °C at 6 ka compared to 0.5 ka. We were unable to reconstruct reliably winter temperature or water balance, due to the confounding effects of summer temperature and the great between-reconstruction variability. We find BRTs to be a promising tool for quantitative reconstructions from palaeoenvironmental proxy data. BRTs show good performance in cross-validations compared with WA and MAT, can model a variety of taxon response types, find relevant predictors and incorporate interactions between predictors, and show some robustness with non-analogue fossil assemblages. •Boosted regression trees (BRTs) tested as a palaeoclimatic reconstruction method.•BRTs tested in reconstructions based on northern European fossil pollen sequences.•BRTs compared with two commonly-used reconstruction methods (WA and MAT).•BRTs fare a promising reconstruction method with major theoretical strengths.•Synthesis reconstructions of Holocene palaeoclimate of northern Europe are presented.</description><identifier>ISSN: 0277-3791</identifier><identifier>EISSN: 1873-457X</identifier><identifier>DOI: 10.1016/j.quascirev.2014.01.011</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Holocene ; Lateglacial ; Modern-analogue technique ; Northern Europe ; Weighted averaging</subject><ispartof>Quaternary science reviews, 2014-03, Vol.88, p.69-81</ispartof><rights>2014 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a371t-895a1ea812a4c373f417210341f7d4ba01b113aa3d01f28569b0796b2fb54ed63</citedby><cites>FETCH-LOGICAL-a371t-895a1ea812a4c373f417210341f7d4ba01b113aa3d01f28569b0796b2fb54ed63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Salonen, J. Sakari</creatorcontrib><creatorcontrib>Luoto, Miska</creatorcontrib><creatorcontrib>Alenius, Teija</creatorcontrib><creatorcontrib>Heikkilä, Maija</creatorcontrib><creatorcontrib>Seppä, Heikki</creatorcontrib><creatorcontrib>Telford, Richard J.</creatorcontrib><creatorcontrib>Birks, H. John B.</creatorcontrib><title>Reconstructing palaeoclimatic variables from fossil pollen using boosted regression trees: comparison and synthesis with other quantitative reconstruction methods</title><title>Quaternary science reviews</title><description>We test and analyse a new calibration method, boosted regression trees (BRTs) in palaeoclimatic reconstructions based on fossil pollen assemblages. We apply BRTs to multiple Holocene and Lateglacial pollen sequences from northern Europe, and compare their performance with two commonly-used calibration methods: weighted averaging regression (WA) and the modern-analogue technique (MAT). Using these calibration methods and fossil pollen data, we present synthetic reconstructions of Holocene summer temperature, winter temperature, and water balance changes in northern Europe. Highly consistent trends are found for summer temperature, with a distinct Holocene thermal maximum at ca 8000–4000 cal. a BP, with a mean Tjja anomaly of ca +0.7 °C at 6 ka compared to 0.5 ka. We were unable to reconstruct reliably winter temperature or water balance, due to the confounding effects of summer temperature and the great between-reconstruction variability. We find BRTs to be a promising tool for quantitative reconstructions from palaeoenvironmental proxy data. BRTs show good performance in cross-validations compared with WA and MAT, can model a variety of taxon response types, find relevant predictors and incorporate interactions between predictors, and show some robustness with non-analogue fossil assemblages. •Boosted regression trees (BRTs) tested as a palaeoclimatic reconstruction method.•BRTs tested in reconstructions based on northern European fossil pollen sequences.•BRTs compared with two commonly-used reconstruction methods (WA and MAT).•BRTs fare a promising reconstruction method with major theoretical strengths.•Synthesis reconstructions of Holocene palaeoclimate of northern Europe are presented.</description><subject>Holocene</subject><subject>Lateglacial</subject><subject>Modern-analogue technique</subject><subject>Northern Europe</subject><subject>Weighted averaging</subject><issn>0277-3791</issn><issn>1873-457X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><recordid>eNqFkd-K1DAUxoMoOK4-g7n0pmNO0jatd8viP1hYWBS8C2l6upMhbbo56ci-jk9qhhG9FA6EJN_vy8n5GHsLYg8C2vfH_eNmyfmEp70UUO8FlIJnbAedVlXd6B_P2U5IrSule3jJXhEdhRCN7OSO_bpHFxfKaXPZLw98tcFidMHPNnvHTzZ5OwQkPqU48ykS-cDXGAIufKMzMcRIGUee8CFhuY4LzwmRPnAX57XwVE7sMnJ6WvIByRP_6fOBx7JJvPS-ZJ_LYycsFv96KdCM-RBHes1eTDYQvvmzXrHvnz5-u_lS3d59_npzfVtZpSFXXd9YQNuBtLVTWk01aAlC1TDpsR6sgAFAWatGAZPsmrYfhO7bQU5DU-PYqiv27uK7pvi4IWUze3IYgl0wbmSgkX0Pqm37ItUXqUtlIgkns6YysfRkQJhzKuZo_qZizqkYAaWgkNcXEstPTh6TKSJcHI5F6rIZo_-vx2_fe6Cq</recordid><startdate>20140315</startdate><enddate>20140315</enddate><creator>Salonen, J. Sakari</creator><creator>Luoto, Miska</creator><creator>Alenius, Teija</creator><creator>Heikkilä, Maija</creator><creator>Seppä, Heikki</creator><creator>Telford, Richard J.</creator><creator>Birks, H. John B.</creator><general>Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7TG</scope><scope>7UA</scope><scope>C1K</scope><scope>F1W</scope><scope>H96</scope><scope>KL.</scope><scope>L.G</scope></search><sort><creationdate>20140315</creationdate><title>Reconstructing palaeoclimatic variables from fossil pollen using boosted regression trees: comparison and synthesis with other quantitative reconstruction methods</title><author>Salonen, J. Sakari ; Luoto, Miska ; Alenius, Teija ; Heikkilä, Maija ; Seppä, Heikki ; Telford, Richard J. ; Birks, H. John B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a371t-895a1ea812a4c373f417210341f7d4ba01b113aa3d01f28569b0796b2fb54ed63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Holocene</topic><topic>Lateglacial</topic><topic>Modern-analogue technique</topic><topic>Northern Europe</topic><topic>Weighted averaging</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Salonen, J. Sakari</creatorcontrib><creatorcontrib>Luoto, Miska</creatorcontrib><creatorcontrib>Alenius, Teija</creatorcontrib><creatorcontrib>Heikkilä, Maija</creatorcontrib><creatorcontrib>Seppä, Heikki</creatorcontrib><creatorcontrib>Telford, Richard J.</creatorcontrib><creatorcontrib>Birks, H. John B.</creatorcontrib><collection>CrossRef</collection><collection>Meteorological &amp; Geoastrophysical Abstracts</collection><collection>Water Resources Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Meteorological &amp; Geoastrophysical Abstracts - Academic</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><jtitle>Quaternary science reviews</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Salonen, J. Sakari</au><au>Luoto, Miska</au><au>Alenius, Teija</au><au>Heikkilä, Maija</au><au>Seppä, Heikki</au><au>Telford, Richard J.</au><au>Birks, H. John B.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Reconstructing palaeoclimatic variables from fossil pollen using boosted regression trees: comparison and synthesis with other quantitative reconstruction methods</atitle><jtitle>Quaternary science reviews</jtitle><date>2014-03-15</date><risdate>2014</risdate><volume>88</volume><spage>69</spage><epage>81</epage><pages>69-81</pages><issn>0277-3791</issn><eissn>1873-457X</eissn><abstract>We test and analyse a new calibration method, boosted regression trees (BRTs) in palaeoclimatic reconstructions based on fossil pollen assemblages. We apply BRTs to multiple Holocene and Lateglacial pollen sequences from northern Europe, and compare their performance with two commonly-used calibration methods: weighted averaging regression (WA) and the modern-analogue technique (MAT). Using these calibration methods and fossil pollen data, we present synthetic reconstructions of Holocene summer temperature, winter temperature, and water balance changes in northern Europe. Highly consistent trends are found for summer temperature, with a distinct Holocene thermal maximum at ca 8000–4000 cal. a BP, with a mean Tjja anomaly of ca +0.7 °C at 6 ka compared to 0.5 ka. We were unable to reconstruct reliably winter temperature or water balance, due to the confounding effects of summer temperature and the great between-reconstruction variability. We find BRTs to be a promising tool for quantitative reconstructions from palaeoenvironmental proxy data. BRTs show good performance in cross-validations compared with WA and MAT, can model a variety of taxon response types, find relevant predictors and incorporate interactions between predictors, and show some robustness with non-analogue fossil assemblages. •Boosted regression trees (BRTs) tested as a palaeoclimatic reconstruction method.•BRTs tested in reconstructions based on northern European fossil pollen sequences.•BRTs compared with two commonly-used reconstruction methods (WA and MAT).•BRTs fare a promising reconstruction method with major theoretical strengths.•Synthesis reconstructions of Holocene palaeoclimate of northern Europe are presented.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.quascirev.2014.01.011</doi><tpages>13</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0277-3791
ispartof Quaternary science reviews, 2014-03, Vol.88, p.69-81
issn 0277-3791
1873-457X
language eng
recordid cdi_proquest_miscellaneous_1529913669
source Elsevier
subjects Holocene
Lateglacial
Modern-analogue technique
Northern Europe
Weighted averaging
title Reconstructing palaeoclimatic variables from fossil pollen using boosted regression trees: comparison and synthesis with other quantitative reconstruction methods
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T22%3A05%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Reconstructing%20palaeoclimatic%20variables%20from%20fossil%20pollen%20using%20boosted%20regression%20trees:%20comparison%20and%20synthesis%20with%20other%20quantitative%20reconstruction%20methods&rft.jtitle=Quaternary%20science%20reviews&rft.au=Salonen,%20J.%20Sakari&rft.date=2014-03-15&rft.volume=88&rft.spage=69&rft.epage=81&rft.pages=69-81&rft.issn=0277-3791&rft.eissn=1873-457X&rft_id=info:doi/10.1016/j.quascirev.2014.01.011&rft_dat=%3Cproquest_cross%3E1529913669%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a371t-895a1ea812a4c373f417210341f7d4ba01b113aa3d01f28569b0796b2fb54ed63%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1529913669&rft_id=info:pmid/&rfr_iscdi=true