Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/25804
Full metadata record
DC FieldValueLanguage
dc.contributor.authorIlie, Iuliaen_UK
dc.contributor.authorDittrich, Peteren_UK
dc.contributor.authorCarvalhais, Nunoen_UK
dc.contributor.authorJung, Martinen_UK
dc.contributor.authorHeinemeyer, Andreasen_UK
dc.contributor.authorMigliavacca, Mircoen_UK
dc.contributor.authorMorison, James I Len_UK
dc.contributor.authorSippel, Sebastianen_UK
dc.contributor.authorSubke, Jens-Arneen_UK
dc.contributor.authorWilkinson, Matthewen_UK
dc.contributor.authorMahecha, Miguel Den_UK
dc.date.accessioned2017-12-21T01:12:37Z-
dc.date.available2017-12-21T01:12:37Z-
dc.date.issued2017-09-25en_UK
dc.identifier.urihttp://hdl.handle.net/1893/25804-
dc.description.abstractAccurate model representation of land-atmosphere carbon fluxes is essential for climate projections. However, the exact responses of carbon cycle processes to climatic drivers often remain uncertain. Presently, knowledge derived from experiments, complemented with a steadily evolving body of mechanistic theory provides the main basis for developing such models. The strongly increasing availability of measurements may facilitate new ways of identifying suitable model structures using machine learning. Here, we explore the potential of gene expression programming (GEP) to derive relevant model formulations based solely on the signals present in data by automatically applying various mathematical transformations to potential predictors and repeatedly evolving the resulting model structures. In contrast to most other machine learning regression techniques, the GEP approach generates "readable" models that allow for prediction and possibly for interpretation. Our study is based on two cases: artificially generated data and real observations. Simulations based on artificial data show that GEP is successful in identifying prescribed functions with the prediction capacity of the models comparable to four state-of-the-art machine learning methods (Random Forests, Support Vector Machines, Artificial Neural Networks, and Kernel Ridge Regressions). Based on real observations we explore the responses of the different components of terrestrial respiration at an oak forest in south-east England. We find that the GEP retrieved models are often better in prediction than some established respiration models. Based on their structures, we find previously unconsidered exponential dependencies of respiration on seasonal ecosystem carbon assimilation and water dynamics. We noticed that the GEP models are only partly portable across respiration components; the identification of a "general" terrestrial respiration model possibly prevented by equifinality issues. Overall, GEP is a promising tool for uncovering new model structures for terrestrial ecology in the data rich era, complementing more traditional modelling approaches.en_UK
dc.language.isoenen_UK
dc.publisherEuropean Geosciences Union (EGU)en_UK
dc.relationIlie I, Dittrich P, Carvalhais N, Jung M, Heinemeyer A, Migliavacca M, Morison JIL, Sippel S, Subke J, Wilkinson M & Mahecha MD (2017) Reverse engineering model structures for soil and ecosystem respiration: the potential of gene expression programming. Geoscientific Model Development, 10, pp. 3519-3545. https://doi.org/10.5194/gmd-10-3519-2017en_UK
dc.rights© Author(s) 2017. This work is distributed under the Creative Commons Attribution 3.0 License.en_UK
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en_UK
dc.titleReverse engineering model structures for soil and ecosystem respiration: the potential of gene expression programmingen_UK
dc.typeJournal Articleen_UK
dc.identifier.doi10.5194/gmd-10-3519-2017en_UK
dc.citation.jtitleGeoscientific Model Developmenten_UK
dc.citation.issn1991-9603en_UK
dc.citation.issn1991-959Xen_UK
dc.citation.volume10en_UK
dc.citation.spage3519en_UK
dc.citation.epage3545en_UK
dc.citation.publicationstatusPublisheden_UK
dc.citation.peerreviewedRefereeden_UK
dc.type.statusVoR - Version of Recorden_UK
dc.citation.date25/09/2017en_UK
dc.contributor.affiliationMax-Planck-Institute for Biogeochemistry, Germanyen_UK
dc.contributor.affiliationFriedrich Schiller University of Jenaen_UK
dc.contributor.affiliationMax-Planck-Institute for Biogeochemistry, Germanyen_UK
dc.contributor.affiliationMax-Planck-Institute for Biogeochemistry, Germanyen_UK
dc.contributor.affiliationStockholm Environment Instituteen_UK
dc.contributor.affiliationMax-Planck-Institute for Biogeochemistry, Germanyen_UK
dc.contributor.affiliationForest Researchen_UK
dc.contributor.affiliationMax-Planck-Institute for Biogeochemistry, Germanyen_UK
dc.contributor.affiliationBiological and Environmental Sciencesen_UK
dc.contributor.affiliationForest Researchen_UK
dc.contributor.affiliationMax-Planck-Institute for Biogeochemistry, Germanyen_UK
dc.identifier.isiWOS:000411598200001en_UK
dc.identifier.scopusid2-s2.0-85029939270en_UK
dc.identifier.wtid521104en_UK
dc.contributor.orcid0000-0001-9244-639Xen_UK
dc.date.accepted2017-08-21en_UK
dcterms.dateAccepted2017-08-21en_UK
dc.date.filedepositdate2017-08-29en_UK
rioxxterms.apcnot requireden_UK
rioxxterms.typeJournal Article/Reviewen_UK
rioxxterms.versionVoRen_UK
local.rioxx.authorIlie, Iulia|en_UK
local.rioxx.authorDittrich, Peter|en_UK
local.rioxx.authorCarvalhais, Nuno|en_UK
local.rioxx.authorJung, Martin|en_UK
local.rioxx.authorHeinemeyer, Andreas|en_UK
local.rioxx.authorMigliavacca, Mirco|en_UK
local.rioxx.authorMorison, James I L|en_UK
local.rioxx.authorSippel, Sebastian|en_UK
local.rioxx.authorSubke, Jens-Arne|0000-0001-9244-639Xen_UK
local.rioxx.authorWilkinson, Matthew|en_UK
local.rioxx.authorMahecha, Miguel D|en_UK
local.rioxx.projectInternal Project|University of Stirling|https://isni.org/isni/0000000122484331en_UK
local.rioxx.freetoreaddate2017-09-25en_UK
local.rioxx.licencehttp://www.rioxx.net/licenses/under-embargo-all-rights-reserved||2017-09-25en_UK
local.rioxx.licencehttp://creativecommons.org/licenses/by/4.0/|2017-09-25|en_UK
local.rioxx.filenamegmd-10-3519-2017.pdfen_UK
local.rioxx.filecount1en_UK
local.rioxx.source1991-959Xen_UK
Appears in Collections:Biological and Environmental Sciences Journal Articles

Files in This Item:
File Description SizeFormat 
gmd-10-3519-2017.pdfFulltext - Published Version10.01 MBAdobe PDFView/Open


This item is protected by original copyright



A file in this item is licensed under a Creative Commons License Creative Commons

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.