001037646 001__ 1037646
001037646 005__ 20250203124512.0
001037646 0247_ $$2doi$$a10.5194/gmd-16-1467-2023
001037646 0247_ $$2ISSN$$a1991-959X
001037646 0247_ $$2ISSN$$a1991-9603
001037646 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-00811
001037646 0247_ $$2WOS$$aWOS:000945377600001
001037646 037__ $$aFZJ-2025-00811
001037646 082__ $$a550
001037646 1001_ $$0P:(DE-HGF)0$$aRojas-Campos, Adrian$$b0$$eCorresponding author
001037646 245__ $$aDeep learning models for generation of precipitation maps based on numerical weather prediction
001037646 260__ $$aKatlenburg-Lindau$$bCopernicus$$c2023
001037646 3367_ $$2DRIVER$$aarticle
001037646 3367_ $$2DataCite$$aOutput Types/Journal article
001037646 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1737459980_23861
001037646 3367_ $$2BibTeX$$aARTICLE
001037646 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001037646 3367_ $$00$$2EndNote$$aJournal Article
001037646 520__ $$aNumerical weather prediction (NWP) models are atmospheric simulations that imitate the dynamics of the atmosphere and provide high-quality forecasts. One of the most significant limitations of NWP is the elevated amount of computational resources required for its functioning, which limits the spatial and temporal resolution of the outputs. Traditional meteorological techniques to increase the resolution are uniquely based on information from a limited group of interest variables. In this study, we offer an alternative approach to the task where we generate precipitation maps based on the complete set of variables of the NWP to generate high-resolution and short-time precipitation predictions. To achieve this, five different deep learning models were trained and evaluated: a baseline, U-Net, two deconvolution networks and one conditional generative model (Conditional Generative Adversarial Network; CGAN). A total of 20 independent random initializations were performed for each of the models. The predictions were evaluated using skill scores based on mean absolute error (MAE) and linear error in probability space (LEPS), equitable threat score (ETS), critical success index (CSI) and frequency bias after applying several thresholds. The models showed a significant improvement in predicting precipitation, showing the benefits of including the complete information from the NWP. The algorithms doubled the resolution of the predictions and corrected an over-forecast bias from the input information. However, some new models presented new types of bias: U-Net tended to mid-range precipitation events, and the deconvolution models favored low rain events and generated some spatial smoothing. The CGAN offered the highest-quality precipitation forecast, generating realistic outputs and indicating possible future research paths.
001037646 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001037646 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x1
001037646 536__ $$0G:(BMBF)01IS18047A$$aVerbundprojekt DeepRain: Effiziente Lokale Niederschlagsvorhersage durch Maschinelles Lernen (01IS18047A)$$c01IS18047A$$x2
001037646 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001037646 7001_ $$0P:(DE-Juel1)180790$$aLangguth, Michael$$b1
001037646 7001_ $$0P:(DE-HGF)0$$aWittenbrink, Martin$$b2
001037646 7001_ $$0P:(DE-HGF)0$$aPipa, Gordon$$b3
001037646 773__ $$0PERI:(DE-600)2456725-5$$a10.5194/gmd-16-1467-2023$$gVol. 16, no. 5, p. 1467 - 1480$$n5$$p1467 - 1480$$tGeoscientific model development$$v16$$x1991-959X$$y2023
001037646 8564_ $$uhttps://juser.fz-juelich.de/record/1037646/files/gmd-16-1467-2023.pdf$$yOpenAccess
001037646 909CO $$ooai:juser.fz-juelich.de:1037646$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
001037646 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180790$$aForschungszentrum Jülich$$b1$$kFZJ
001037646 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001037646 9141_ $$y2024
001037646 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-21
001037646 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001037646 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2022-12-20T09:29:04Z
001037646 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2022-12-20T09:29:04Z
001037646 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001037646 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-21
001037646 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-21
001037646 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001037646 9801_ $$aFullTexts
001037646 980__ $$ajournal
001037646 980__ $$aVDB
001037646 980__ $$aUNRESTRICTED
001037646 980__ $$aI:(DE-Juel1)JSC-20090406