FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220797251> ?p ?o ?g. }

• W4220797251 abstract "&lt;p&gt;The 29 circulation types by Hess &amp; Brezowsky, called &amp;#8220;Gro&amp;#223;wetterlagen&amp;#8221;, are one of the most established classification schemes of the large-scale atmospheric circulation patterns influencing Europe. They are widely used in order to assess linkages between atmospheric forcing and surface conditions e.g. extreme events like floods or heat waves. Because of the connection between driving circulation type and extreme event, it is of high interest to understand future changes in the occurrence of circulation types in the context of climate change. Even though the &amp;#8220;Gro&amp;#223;wetterlagen&amp;#8221; have been commonly used in conjunction with historic data, only very few studies examine future trends in the frequency distribution of these circulation types using climate models. Among the potential limitations for the application of &amp;#8220;Gro&amp;#223;wetterlagen&amp;#8221; to climate models are the lack of an open-source classification method and the high range of internal variability. Due to the dynamic nature of the large-scale atmospheric circulation in the mid-latitudes, it is highly relevant to consider the range of internal variability when studying future changes in circulation patterns and to separate the climate change signal from noise.&lt;/p&gt;&lt;p&gt;We have therefore developed an open-source, automated method for the classification of the &amp;#8220;Gro&amp;#223;wetterlagen&amp;#8221; using deep learning and we apply this method to the SMHI-LENS, an initial-condition single-model large ensemble of the CMIP6 generation with 50 members on a daily resolution. A convolutional neural network has been trained to classify the circulation patterns using the atmospheric variables sea level pressure and geopotential height at 500 hPa at 5&amp;#176; resolution. The convolutional neural network is trained for this supervised classification task with a long-term historic record of the &amp;#8220;Gro&amp;#223;wetterlagen&amp;#8221;, which covers the 20&lt;sup&gt;th&lt;/sup&gt; century. It is derived from a subjective catalog of the German Weather Service with daily class affiliations and atmospheric variables from ECMWFs&amp;#8217; reanalysis dataset of the 20th century, ERA-20C.&lt;/p&gt;&lt;p&gt;We present the challenges of the deep learning based classification of subjectively defined circulation types and quantify the uncertainty range intrinsic to deep neural networks using deep ensembles. We furthermore demonstrate the benefits of this automated classification of &amp;#8220;Gro&amp;#223;wetterlagen&amp;#8221; with respect to the application to large datasets of climate model ensembles. Our results show the ensemble-averaged future trends in the occurrence of &amp;#8220;Gro&amp;#223;wetterlagen&amp;#8221; and the range of internal variability, including the signal-to-noise ratio, for the CMIP6 SMHI-LENS under the SSP37.0 scenario.&lt;/p&gt;" @default.
• W4220797251 created "2022-04-03" @default.
• W4220797251 creator A5007624977 @default.
• W4220797251 creator A5022012759 @default.
• W4220797251 creator A5035969125 @default.
• W4220797251 creator A5039086570 @default.
• W4220797251 date "2022-03-28" @default.
• W4220797251 modified "2023-09-24" @default.
• W4220797251 title "Classification of atmospheric circulation types over Europe in a CMIP6 Large Ensemble using Deep Learning" @default.
• W4220797251 doi "https://doi.org/10.5194/egusphere-egu22-10421" @default.
• W4220797251 hasPublicationYear "2022" @default.
• W4220797251 type Work @default.
• W4220797251 citedByCount "2" @default.
• W4220797251 countsByYear W42207972512023 @default.
• W4220797251 crossrefType "posted-content" @default.
• W4220797251 hasAuthorship W4220797251A5007624977 @default.
• W4220797251 hasAuthorship W4220797251A5022012759 @default.
• W4220797251 hasAuthorship W4220797251A5035969125 @default.
• W4220797251 hasAuthorship W4220797251A5039086570 @default.
• W4220797251 hasConcept C11111821 @default.
• W4220797251 hasConcept C111368507 @default.
• W4220797251 hasConcept C121332964 @default.
• W4220797251 hasConcept C122523270 @default.
• W4220797251 hasConcept C127313418 @default.
• W4220797251 hasConcept C132651083 @default.
• W4220797251 hasConcept C13280743 @default.
• W4220797251 hasConcept C150284090 @default.
• W4220797251 hasConcept C151730666 @default.
• W4220797251 hasConcept C2779343474 @default.
• W4220797251 hasConcept C39432304 @default.
• W4220797251 hasConcept C49204034 @default.
• W4220797251 hasConcept C91586092 @default.
• W4220797251 hasConcept C97355855 @default.
• W4220797251 hasConceptScore W4220797251C11111821 @default.
• W4220797251 hasConceptScore W4220797251C111368507 @default.
• W4220797251 hasConceptScore W4220797251C121332964 @default.
• W4220797251 hasConceptScore W4220797251C122523270 @default.
• W4220797251 hasConceptScore W4220797251C127313418 @default.
• W4220797251 hasConceptScore W4220797251C132651083 @default.
• W4220797251 hasConceptScore W4220797251C13280743 @default.
• W4220797251 hasConceptScore W4220797251C150284090 @default.
• W4220797251 hasConceptScore W4220797251C151730666 @default.
• W4220797251 hasConceptScore W4220797251C2779343474 @default.
• W4220797251 hasConceptScore W4220797251C39432304 @default.
• W4220797251 hasConceptScore W4220797251C49204034 @default.
• W4220797251 hasConceptScore W4220797251C91586092 @default.
• W4220797251 hasConceptScore W4220797251C97355855 @default.
• W4220797251 hasLocation W42207972511 @default.
• W4220797251 hasOpenAccess W4220797251 @default.
• W4220797251 hasPrimaryLocation W42207972511 @default.
• W4220797251 hasRelatedWork W1894540399 @default.
• W4220797251 hasRelatedWork W1999928813 @default.
• W4220797251 hasRelatedWork W2018657082 @default.
• W4220797251 hasRelatedWork W2065184876 @default.
• W4220797251 hasRelatedWork W2083574888 @default.
• W4220797251 hasRelatedWork W2087710575 @default.
• W4220797251 hasRelatedWork W2131222486 @default.
• W4220797251 hasRelatedWork W2153070978 @default.
• W4220797251 hasRelatedWork W2988499099 @default.
• W4220797251 hasRelatedWork W2183531311 @default.
• W4220797251 isParatext "false" @default.
• W4220797251 isRetracted "false" @default.
• W4220797251 workType "article" @default.