000917525 001__ 917525
000917525 005__ 20230224084240.0
000917525 0247_ $$2doi$$a10.5194/gmd-15-8931-2022
000917525 0247_ $$2ISSN$$a1991-959X
000917525 0247_ $$2ISSN$$a1991-9603
000917525 0247_ $$2Handle$$a2128/33637
000917525 0247_ $$2WOS$$aWOS:000898541700001
000917525 037__ $$aFZJ-2023-00738
000917525 082__ $$a550
000917525 1001_ $$0P:(DE-Juel1)177767$$aGong, Bing$$b0$$eCorresponding author
000917525 245__ $$aTemperature forecasting by deep learning methods
000917525 260__ $$aKatlenburg-Lindau$$bCopernicus$$c2022
000917525 3367_ $$2DRIVER$$aarticle
000917525 3367_ $$2DataCite$$aOutput Types/Journal article
000917525 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1673943515_27886
000917525 3367_ $$2BibTeX$$aARTICLE
000917525 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000917525 3367_ $$00$$2EndNote$$aJournal Article
000917525 520__ $$aNumerical weather prediction (NWP) models solve a system of partial differential equations based on physical laws to forecast the future state of the atmosphere. These models are deployed operationally, but they are computationally very expensive. Recently, the potential of deep neural networks to generate bespoke weather forecasts has been explored in a couple of scientific studies inspired by the success of video frame prediction models in computer vision. In this study, a simple recurrent neural network with convolutional filters, called ConvLSTM, and an advanced generative network, the Stochastic Adversarial Video Prediction (SAVP) model, are applied to create hourly forecasts of the 2 m temperature for the next 12 h over Europe. We make use of 13 years of data from the ERA5 reanalysis, of which 11 years are utilized for training and 1 year each is used for validating and testing. We choose the 2 m temperature, total cloud cover, and the 850 hPa temperature as predictors and show that both models attain predictive skill by outperforming persistence forecasts. SAVP is superior to ConvLSTM in terms of several evaluation metrics, confirming previous results from computer vision that larger, more complex networks are better suited to learn complex features and to generate better predictions. The 12 h forecasts of SAVP attain a mean squared error (MSE) of about 2.3 K2, an anomaly correlation coefficient (ACC) larger than 0.85, a structural similarity index (SSIM) of around 0.72, and a gradient ratio (rG) of about 0.82. The ConvLSTM yields a higher MSE (3.6 K2), a smaller ACC (0.80) and SSIM (0.65), and a slightly larger rG (0.84). The superior performance of SAVP in terms of MSE, ACC, and SSIM can be largely attributed to the generator. A sensitivity study shows that a larger weight of the generative adversarial network (GAN) component in the SAVP loss leads to even better preservation of spatial variability at the cost of a somewhat increased MSE (2.5 K2). Including the 850 hPa temperature as an additional predictor enhances the forecast quality, and the model also benefits from a larger spatial domain. By contrast, adding the total cloud cover as predictor or reducing the amount of training data to 8 years has only small effects. Although the temperature forecasts obtained in this way are still less powerful than contemporary NWP models, this study demonstrates that sophisticated deep neural networks may achieve considerable forecast quality beyond the nowcasting range in a purely data-driven way.
000917525 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
000917525 536__ $$0G:(EU-Grant)955513$$aMAELSTROM - MAchinE Learning for Scalable meTeoROlogy and cliMate (955513)$$c955513$$fH2020-JTI-EuroHPC-2019-1$$x1
000917525 536__ $$0G:(EU-Grant)787576$$aIntelliAQ - Artificial Intelligence for Air Quality (787576)$$c787576$$fERC-2017-ADG$$x2
000917525 536__ $$0G:(DE-Juel-1)ESDE$$aEarth System Data Exploration (ESDE)$$cESDE$$x3
000917525 588__ $$aDataset connected to DataCite
000917525 7001_ $$0P:(DE-Juel1)180790$$aLangguth, Michael$$b1
000917525 7001_ $$0P:(DE-Juel1)187069$$aJi, Yan$$b2
000917525 7001_ $$0P:(DE-Juel1)166264$$aMozaffari, Amirpasha$$b3
000917525 7001_ $$0P:(DE-Juel1)180752$$aStadtler, Scarlet$$b4$$ufzj
000917525 7001_ $$0P:(DE-Juel1)187076$$aMache, Karim$$b5$$ufzj
000917525 7001_ $$0P:(DE-Juel1)6952$$aSchultz, Martin G.$$b6
000917525 773__ $$0PERI:(DE-600)2456725-5$$a10.5194/gmd-15-8931-2022$$gVol. 15, no. 23, p. 8931 - 8956$$n23$$p8931 - 8956$$tGeoscientific model development$$v15$$x1991-959X$$y2022
000917525 8564_ $$uhttps://juser.fz-juelich.de/record/917525/files/gmd-15-8931-2022.pdf$$yOpenAccess
000917525 909CO $$ooai:juser.fz-juelich.de:917525$$pdnbdelivery$$pec_fundedresources$$pVDB$$pdriver$$popen_access$$popenaire
000917525 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177767$$aForschungszentrum Jülich$$b0$$kFZJ
000917525 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180790$$aForschungszentrum Jülich$$b1$$kFZJ
000917525 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187069$$aForschungszentrum Jülich$$b2$$kFZJ
000917525 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)166264$$aForschungszentrum Jülich$$b3$$kFZJ
000917525 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180752$$aForschungszentrum Jülich$$b4$$kFZJ
000917525 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187076$$aForschungszentrum Jülich$$b5$$kFZJ
000917525 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)6952$$aForschungszentrum Jülich$$b6$$kFZJ
000917525 9131_ $$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
000917525 9141_ $$y2022
000917525 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2022-11-25
000917525 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
000917525 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bGEOSCI MODEL DEV : 2021$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-01-16T18:00:10Z
000917525 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-01-16T18:00:10Z
000917525 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000917525 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bGEOSCI MODEL DEV : 2021$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-25
000917525 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Peer review$$d2021-01-16T18:00:10Z
000917525 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000917525 9801_ $$aFullTexts
000917525 980__ $$ajournal
000917525 980__ $$aVDB
000917525 980__ $$aUNRESTRICTED
000917525 980__ $$aI:(DE-Juel1)JSC-20090406