10.60507/FK2/RD9E33Shams Eddin, Mohamad HakamMohamad HakamShams Eddin0000-0003-3136-4619University of BonnGall, JuergenJuergenGall0000-0002-9447-3399University of Bonnbonndata2024Agricultural SciencesComputer and Information ScienceEarth and Environmental SciencesPhysicsShams Eddin, Mohamad HakamMohamad HakamShams EddinUniversity of BonnShams Eddin, Mohamad HakamMohamad HakamShams EddinUniversity of Bonn2023-08-012024-10-092024-10-212410.240753387006639032607648460107374182400102916084266319856602811273607699722070773410427661025063408762648077252032734944825564142129166903application/x-7z-compressedapplication/x-7z-compressedapplication/octet-streamapplication/octet-streamapplication/x-7z-compressedapplication/x-7z-compressedapplication/x-7z-compressedapplication/x-7z-compressedapplication/x-7z-compressedtext/plainapplication/x-7z-compressedapplication/x-7z-compressedapplication/pdf1.0CC BY 4.0This data set allows to systematically evaluate approaches for the task of identifying extreme events in water cycle components by developing deep neural networks that detect anomalies and drivers of extremes in simulated data.German Research Foundation (DFG) - Collaborative Research Center (CRC)SFB 1502/1–2022 – project no. 450058266