Show simple item record

dc.contributor.author
Tramontana, Gianluca
dc.contributor.author
Jung, Martin
dc.contributor.author
Camps-Valls, Gustau
dc.contributor.author
Ichii, Kazuhito
dc.contributor.author
Ráduly, Botond
dc.contributor.author
Reichstein, Markus
dc.contributor.author
Schwalm, Christopher R.
dc.contributor.author
Arain, M. Altaf
dc.contributor.author
Cescatti, Alessandro
dc.contributor.author
Kiely, Gerard
dc.contributor.author
Merbold, Lutz
dc.contributor.author
Serrano-Ortiz, Penelope
dc.contributor.author
Sickert, Sven
dc.contributor.author
Wolf, Sebastian
dc.contributor.author
Papale, Dario
dc.date.accessioned
2018-11-06T17:36:22Z
dc.date.available
2017-06-12T09:16:19Z
dc.date.available
2018-11-06T17:36:22Z
dc.date.issued
2016
dc.identifier.issn
1810-6277
dc.identifier.issn
1810-6285
dc.identifier.other
10.5194/bg-2015-661
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/118483
dc.identifier.doi
10.3929/ethz-b-000118483
dc.description.abstract
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_US
dc.language.iso
en
en_US
dc.publisher
Copernicus
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/3.0/
dc.subject
Machine learning
en_US
dc.subject
Carbon fluxes
en_US
dc.subject
Energy fluxes
en_US
dc.subject
FLUXNET
en_US
dc.subject
Remote sensing
en_US
dc.subject
FLUXCOM
en_US
dc.title
Predicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithms
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 3.0 Unported
dc.date.published
2016-03-07
ethz.journal.title
Biogeosciences Discussions
ethz.journal.abbreviated
Biogeosci. discuss.
ethz.size
33 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.identifier.nebis
010153508
ethz.publication.place
Goettingen
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02350 - Dep. Umweltsystemwissenschaften / Dep. of Environmental Systems Science::02703 - Institut für Agrarwissenschaften / Institute of Agricultural Sciences::03648 - Buchmann, Nina / Buchmann, Nina
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02350 - Dep. Umweltsystemwissenschaften / Dep. of Environmental Systems Science::02703 - Institut für Agrarwissenschaften / Institute of Agricultural Sciences::03648 - Buchmann, Nina / Buchmann, Nina
ethz.relation.isPreviousVersionOf
10.5194/bg-13-4291-2016
ethz.date.deposited
2017-06-12T09:18:02Z
ethz.source
ECIT
ethz.identifier.importid
imp5936548dd628b65111
ethz.ecitpid
pub:180441
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2017-07-13T06:46:48Z
ethz.rosetta.lastUpdated
2018-11-06T17:36:54Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&amp;rft_val_fmt=info:ofi/fmt:kev:mtx:journal&amp;rft.atitle=Predicting%20carbon%20dioxide%20and%20energy%20fluxes%20across%20global%20FLUXNET%20sites%20with%20regression%20algorithms&amp;rft.jtitle=Biogeosciences%20Discussions&amp;rft.date=2016&amp;rft.issn=1810-6277&amp;1810-6285&amp;rft.au=Tramontana,%20Gianluca&amp;Jung,%20Martin&amp;Camps-Valls,%20Gustau&amp;Ichii,%20Kazuhito&amp;R%C3%A1duly,%20Botond&amp;rft.genre=article&amp;
 Search via SFX

Files in this item

Thumbnail

Publication type

Show simple item record