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

Simple item page
cg.contributor.affiliationETH Zürich
cg.contributor.affiliationFriedrich Schiller University Jena
cg.contributor.affiliationInternational Livestock Research Institute
cg.contributor.affiliationJapan Agency for Marine-Earth Science and Technology
cg.contributor.affiliationJoint Research Centre, Ispra, Italy
cg.contributor.affiliationMax Planck Institute for Biogeochemistry
cg.contributor.affiliationMcMaster University
cg.contributor.affiliationNational Institute for Environmental Studies
cg.contributor.affiliationSapientia Hungarian University of Transylvania
cg.contributor.affiliationTuscia University
cg.contributor.affiliationUniversity College Cork
cg.contributor.affiliationUniversity of Granada
cg.contributor.affiliationUniversity of Valencia
cg.contributor.affiliationWoodwell Climate Research Center
cg.contributor.donorEuropean Union
cg.contributor.donorEuropean Research Council
cg.contributor.donorLawrence Berkeley National Laboratory
cg.contributor.donorMax Planck Society
cg.contributor.donorMicrosoft
cg.contributor.donorMinistry of Economy, Industry and Competitiveness
cg.contributor.donorMinistry of the Environment, Japan
cg.contributor.donorNational Aeronautics and Space Administration, United States
cg.contributor.donorNational Science Foundation, United States
cg.contributor.donorNatural Resources Canada
cg.contributor.donorNatural Sciences and Engineering Research Council
cg.contributor.donorOak Ridge National Laboratory
cg.contributor.donorOffice of Biological and Environmental Research
cg.contributor.donorUnited Nations
cg.creator.identifierLutz Merbold: 0000-0003-4974-170X
cg.identifier.doihttps://doi.org/10.5194/bg-13-4291-2016
cg.issn1726-4189
cg.issue14
cg.journalBiogeosciences
cg.subject.ilriGHG EMISSIONS
cg.volume13
dc.contributor.authorTramontana, Gianluca
dc.contributor.authorJung, Martin
dc.contributor.authorSchwalm, Christopher R.
dc.contributor.authorIchii, Kazuhito
dc.contributor.authorCamps-Valls, Gustau
dc.contributor.authorRáduly, Botond
dc.contributor.authorReichstein, Markus
dc.contributor.authorArain, M. Altaf
dc.contributor.authorCescatti, Alessandro
dc.contributor.authorKiely, Gerard
dc.contributor.authorMerbold, Lutz
dc.contributor.authorSerrano-Ortiz, Penelope
dc.contributor.authorSickert, Sven
dc.contributor.authorWolf, Sebastian
dc.contributor.authorPapale, Dario
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. 4291-4313
dcterms.issued2016-07-29
dcterms.languageen
dcterms.licenseCC-BY-3.0
dcterms.publisherCopernicus GmbH
dcterms.subjectcarbonen
dcterms.subjectenergyen
dcterms.subjectcarbon dioxideen
dcterms.subjectalgorithmsen
dcterms.typeJournal Article

Files

Collections

ILRI articles in journals