Predicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithms

Simple item page
cg.contributor.affiliationETH Zürichen
cg.contributor.affiliationFriedrich Schiller University Jenaen
cg.contributor.affiliationInternational Livestock Research Instituteen
cg.contributor.affiliationJapan Agency for Marine-Earth Science and Technologyen
cg.contributor.affiliationJoint Research Centre, Ispra, Italyen
cg.contributor.affiliationMax Planck Institute for Biogeochemistryen
cg.contributor.affiliationMcMaster Universityen
cg.contributor.affiliationNational Institute for Environmental Studiesen
cg.contributor.affiliationSapientia Hungarian University of Transylvaniaen
cg.contributor.affiliationTuscia Universityen
cg.contributor.affiliationUniversity College Corken
cg.contributor.affiliationUniversity of Granadaen
cg.contributor.affiliationUniversity of Valenciaen
cg.contributor.affiliationWoodwell Climate Research Centeren
cg.contributor.donorEuropean Unionen
cg.contributor.donorEuropean Research Councilen
cg.contributor.donorLawrence Berkeley National Laboratoryen
cg.contributor.donorMax Planck Societyen
cg.contributor.donorMicrosoften
cg.contributor.donorMinistry of Economy, Industry and Competitivenessen
cg.contributor.donorMinistry of the Environment, Japanen
cg.contributor.donorNational Aeronautics and Space Administration, United Statesen
cg.contributor.donorNational Science Foundation, United Statesen
cg.contributor.donorNatural Resources Canadaen
cg.contributor.donorNatural Sciences and Engineering Research Councilen
cg.contributor.donorOak Ridge National Laboratoryen
cg.contributor.donorOffice of Biological and Environmental Researchen
cg.contributor.donorUnited Nationsen
cg.creator.identifierLutz Merbold: 0000-0003-4974-170X
cg.identifier.doihttps://doi.org/10.5194/bg-13-4291-2016en
cg.issn1726-4189en
cg.issue14en
cg.journalBiogeosciencesen
cg.subject.ilriGHG EMISSIONSen
cg.volume13en
dc.contributor.authorTramontana, Gianlucaen
dc.contributor.authorJung, Martinen
dc.contributor.authorSchwalm, Christopher R.en
dc.contributor.authorIchii, Kazuhitoen
dc.contributor.authorCamps-Valls, Gustauen
dc.contributor.authorRáduly, Botonden
dc.contributor.authorReichstein, Markusen
dc.contributor.authorArain, M. Altafen
dc.contributor.authorCescatti, Alessandroen
dc.contributor.authorKiely, Gerarden
dc.contributor.authorMerbold, Lutzen
dc.contributor.authorSerrano-Ortiz, Penelopeen
dc.contributor.authorSickert, Svenen
dc.contributor.authorWolf, Sebastianen
dc.contributor.authorPapale, Darioen
dc.date.accessioned2023-03-10T14:34:29Zen
dc.date.available2023-03-10T14:34:29Zen
dc.identifier.urihttps://hdl.handle.net/10568/129400
dc.titlePredicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithmsen
dcterms.abstractAbstract. Spatio-temporal fields of land–atmosphere fluxes derived from data-driven models can complement simulations by process-based land surface models. While a number of strategies for empirical models with eddy-covariance flux data have been applied, a systematic intercomparison of these methods has been missing so far. In this study, we performed a cross-validation experiment for predicting carbon dioxide, latent heat, sensible heat and net radiation fluxes across different ecosystem types with 11 machine learning (ML) methods from four different classes (kernel methods, neural networks, tree methods, and regression splines). We applied two complementary setups: (1) 8-day average fluxes based on remotely sensed data and (2) daily mean fluxes based on meteorological data and a mean seasonal cycle of remotely sensed variables. The patterns of predictions from different ML and experimental setups were highly consistent. There were systematic differences in performance among the fluxes, with the following ascending order: net ecosystem exchange (R2 < 0.5), ecosystem respiration (R2 > 0.6), gross primary production (R2> 0.7), latent heat (R2 > 0.7), sensible heat (R2 > 0.7), and net radiation (R2 > 0.8). The ML methods predicted the across-site variability and the mean seasonal cycle of the observed fluxes very well (R2 > 0.7), while the 8-day deviations from the mean seasonal cycle were not well predicted (R2 < 0.5). Fluxes were better predicted at forested and temperate climate sites than at sites in extreme climates or less represented by training data (e.g., the tropics). The evaluated large ensemble of ML-based models will be the basis of new global flux products.en
dcterms.accessRightsOpen Access
dcterms.available2016-07-29
dcterms.bibliographicCitationTramontana, Gianluca; Jung, Martin; Schwalm, Christopher R.; Ichii, Kazuhito; Camps-Valls, Gustau; Ráduly, Botond; Reichstein, Markus; Arain, M. Altaf; Cescatti, Alessandro; Kiely, Gerard; Merbold, Lutz; Serrano-Ortiz, Penelope; Sickert, Sven; Wolf, Sebastian; Papale, Dario. 2016. Predicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithms. Biogeosciences 13: 4291-4313en
dcterms.extentp. 4291-4313en
dcterms.issued2016-07-29
dcterms.languageen
dcterms.licenseCC-BY-3.0
dcterms.publisherCopernicus GmbHen
dcterms.subjectcarbonen
dcterms.subjectenergyen
dcterms.subjectcarbon dioxideen
dcterms.subjectalgorithmsen
dcterms.typeJournal Article

Files

Collections

ILRI articles in journals