Machine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data

Abstract We test several quantitative algorithms as palaeoclimate reconstruction tools for North American and European fossil pollen data, using both classical methods and newer machine-learning approaches based on regression tree ensembles and artificial neural networks. We focus on the reconstruct...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: J. Sakari Salonen, Mikko Korpela, John W. Williams, Miska Luoto
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2019
Materias:
R
Q
Acceso en línea:https://doaj.org/article/b8548e10953e4fd095bb0a622c57d84b
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:b8548e10953e4fd095bb0a622c57d84b
record_format dspace
spelling oai:doaj.org-article:b8548e10953e4fd095bb0a622c57d84b2021-12-02T15:09:28ZMachine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data10.1038/s41598-019-52293-42045-2322https://doaj.org/article/b8548e10953e4fd095bb0a622c57d84b2019-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-019-52293-4https://doaj.org/toc/2045-2322Abstract We test several quantitative algorithms as palaeoclimate reconstruction tools for North American and European fossil pollen data, using both classical methods and newer machine-learning approaches based on regression tree ensembles and artificial neural networks. We focus on the reconstruction of secondary climate variables (here, January temperature and annual water balance), as their comparatively small ecological influence compared to the primary variable (July temperature) presents special challenges to palaeo-reconstructions. We test the pollen–climate models using a novel and comprehensive cross-validation approach, running a series of h-block cross-validations using h values of 100–1500 km. Our study illustrates major benefits of this variable h-block cross-validation scheme, as the effect of spatial autocorrelation is minimized, while the cross-validations with increasing h values can reveal instabilities in the calibration model and approximate challenges faced in palaeo-reconstructions with poor modern analogues. We achieve well-performing calibration models for both primary and secondary climate variables, with boosted regression trees providing the overall most robust performance, while the palaeoclimate reconstructions from fossil datasets show major independent features for the primary and secondary variables. Our results suggest that with careful variable selection and consideration of ecological processes, robust reconstruction of both primary and secondary climate variables is possible.J. Sakari SalonenMikko KorpelaJohn W. WilliamsMiska LuotoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 9, Iss 1, Pp 1-13 (2019)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
J. Sakari Salonen
Mikko Korpela
John W. Williams
Miska Luoto
Machine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data
description Abstract We test several quantitative algorithms as palaeoclimate reconstruction tools for North American and European fossil pollen data, using both classical methods and newer machine-learning approaches based on regression tree ensembles and artificial neural networks. We focus on the reconstruction of secondary climate variables (here, January temperature and annual water balance), as their comparatively small ecological influence compared to the primary variable (July temperature) presents special challenges to palaeo-reconstructions. We test the pollen–climate models using a novel and comprehensive cross-validation approach, running a series of h-block cross-validations using h values of 100–1500 km. Our study illustrates major benefits of this variable h-block cross-validation scheme, as the effect of spatial autocorrelation is minimized, while the cross-validations with increasing h values can reveal instabilities in the calibration model and approximate challenges faced in palaeo-reconstructions with poor modern analogues. We achieve well-performing calibration models for both primary and secondary climate variables, with boosted regression trees providing the overall most robust performance, while the palaeoclimate reconstructions from fossil datasets show major independent features for the primary and secondary variables. Our results suggest that with careful variable selection and consideration of ecological processes, robust reconstruction of both primary and secondary climate variables is possible.
format article
author J. Sakari Salonen
Mikko Korpela
John W. Williams
Miska Luoto
author_facet J. Sakari Salonen
Mikko Korpela
John W. Williams
Miska Luoto
author_sort J. Sakari Salonen
title Machine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data
title_short Machine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data
title_full Machine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data
title_fullStr Machine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data
title_full_unstemmed Machine-learning based reconstructions of primary and secondary climate variables from North American and European fossil pollen data
title_sort machine-learning based reconstructions of primary and secondary climate variables from north american and european fossil pollen data
publisher Nature Portfolio
publishDate 2019
url https://doaj.org/article/b8548e10953e4fd095bb0a622c57d84b
work_keys_str_mv AT jsakarisalonen machinelearningbasedreconstructionsofprimaryandsecondaryclimatevariablesfromnorthamericanandeuropeanfossilpollendata
AT mikkokorpela machinelearningbasedreconstructionsofprimaryandsecondaryclimatevariablesfromnorthamericanandeuropeanfossilpollendata
AT johnwwilliams machinelearningbasedreconstructionsofprimaryandsecondaryclimatevariablesfromnorthamericanandeuropeanfossilpollendata
AT miskaluoto machinelearningbasedreconstructionsofprimaryandsecondaryclimatevariablesfromnorthamericanandeuropeanfossilpollendata
_version_ 1718387834694402048