001006966 001__ 1006966
001006966 005__ 20231027114402.0
001006966 0247_ $$2doi$$a10.5194/gmd-16-2149-2023
001006966 0247_ $$2ISSN$$a1991-959X
001006966 0247_ $$2ISSN$$a1991-9603
001006966 0247_ $$2Handle$$a2128/34378
001006966 0247_ $$2WOS$$aWOS:000972780500001
001006966 037__ $$aFZJ-2023-01917
001006966 082__ $$a550
001006966 1001_ $$0P:(DE-Juel1)178989$$aTesch, Tobias$$b0$$eCorresponding author
001006966 245__ $$aCausal deep learning models for studying the Earth system
001006966 260__ $$aKatlenburg-Lindau$$bCopernicus$$c2023
001006966 3367_ $$2DRIVER$$aarticle
001006966 3367_ $$2DataCite$$aOutput Types/Journal article
001006966 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1683536339_19928
001006966 3367_ $$2BibTeX$$aARTICLE
001006966 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001006966 3367_ $$00$$2EndNote$$aJournal Article
001006966 520__ $$aEarth is a complex non-linear dynamical system. Despite decades of research and considerable scientific and methodological progress, many processes and relations between Earth system variables remain poorly understood. Current approaches for studying relations in the Earth system rely either on numerical simulations or statistical approaches. However, there are several inherent limitations to existing approaches, including high computational costs, uncertainties in numerical models, strong assumptions about linearity or locality, and the fallacy of correlation and causality. Here, we propose a novel methodology combining deep learning (DL) and principles of causality research in an attempt to overcome these limitations. On the one hand, we employ the recent idea of training and analyzing DL models to gain new scientific insights into relations between input and target variables. On the other hand, we use the fact that a statistical model learns the causal effect of an input variable on a target variable if suitable additional input variables are included. As an illustrative example, we apply the methodology to study soil-moisture–precipitation coupling in ERA5 climate reanalysis data across Europe. We demonstrate that, harnessing the great power and flexibility of DL models, the proposed methodology may yield new scientific insights into complex non-linear and non-local coupling mechanisms in the Earth system.
001006966 536__ $$0G:(DE-HGF)POF4-2173$$a2173 - Agro-biogeosystems: controls, feedbacks and impact (POF4-217)$$cPOF4-217$$fPOF IV$$x0
001006966 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001006966 7001_ $$0P:(DE-Juel1)151405$$aKollet, Stefan$$b1$$ufzj
001006966 7001_ $$0P:(DE-HGF)0$$aGarcke, Jochen$$b2
001006966 773__ $$0PERI:(DE-600)2456725-5$$a10.5194/gmd-16-2149-2023$$gVol. 16, no. 8, p. 2149 - 2166$$n8$$p2149 - 2166$$tGeoscientific model development$$v16$$x1991-959X$$y2023
001006966 8564_ $$uhttps://juser.fz-juelich.de/record/1006966/files/Invoice_Helmholtz-PUC-2023-44.pdf
001006966 8564_ $$uhttps://juser.fz-juelich.de/record/1006966/files/gmd-16-2149-2023.pdf$$yOpenAccess
001006966 8767_ $$8Helmholtz-PUC-2023-44$$92023-04-21$$a1200192708$$d2023-05-03$$eAPC$$jZahlung erfolgt
001006966 909CO $$ooai:juser.fz-juelich.de:1006966$$pdnbdelivery$$popenCost$$pVDB$$pdriver$$pOpenAPC$$popen_access$$popenaire
001006966 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178989$$aForschungszentrum Jülich$$b0$$kFZJ
001006966 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)151405$$aForschungszentrum Jülich$$b1$$kFZJ
001006966 9131_ $$0G:(DE-HGF)POF4-217$$1G:(DE-HGF)POF4-210$$2G:(DE-HGF)POF4-200$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-2173$$aDE-HGF$$bForschungsbereich Erde und Umwelt$$lErde im Wandel – Unsere Zukunft nachhaltig gestalten$$vFür eine nachhaltige Bio-Ökonomie – von Ressourcen zu Produkten$$x0
001006966 9141_ $$y2023
001006966 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
001006966 915pc $$0PC:(DE-HGF)0001$$2APC$$aLocal Funding
001006966 915pc $$0PC:(DE-HGF)0002$$2APC$$aDFG OA Publikationskosten
001006966 915pc $$0PC:(DE-HGF)0003$$2APC$$aDOAJ Journal
001006966 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-25
001006966 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001006966 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-25
001006966 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2022-11-25
001006966 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001006966 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2022-11-25
001006966 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2022-12-20T09:29:04Z
001006966 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2022-12-20T09:29:04Z
001006966 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Open peer review$$d2022-12-20T09:29:04Z
001006966 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-10-25
001006966 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-10-25
001006966 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-10-25
001006966 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2023-10-25
001006966 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bGEOSCI MODEL DEV : 2022$$d2023-10-25
001006966 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-10-25
001006966 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2023-10-25
001006966 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2023-10-25
001006966 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bGEOSCI MODEL DEV : 2022$$d2023-10-25
001006966 9201_ $$0I:(DE-Juel1)IBG-3-20101118$$kIBG-3$$lAgrosphäre$$x0
001006966 980__ $$ajournal
001006966 980__ $$aVDB
001006966 980__ $$aUNRESTRICTED
001006966 980__ $$aI:(DE-Juel1)IBG-3-20101118
001006966 980__ $$aAPC
001006966 9801_ $$aAPC
001006966 9801_ $$aFullTexts