KIT | KIT-Bibliothek | Impressum | Datenschutz

spateGAN: Spatio‐Temporal Downscaling of Rainfall Fields Using a cGAN Approach

Glawion, Luca 1; Polz, Julius ORCID iD icon 2; Kunstmann, Harald 2; Fersch, Benjamin ORCID iD icon 2; Chwala, Christian ORCID iD icon 1
1 Karlsruher Institut für Technologie (KIT)
2 Institut für Meteorologie und Klimaforschung – Atmosphärische Umweltforschung (IMK-IFU), Karlsruher Institut für Technologie (KIT)

Abstract:

Climate models face limitations in their ability to accurately represent highly variable atmospheric phenomena. To resolve fine-scale physical processes, allowing for local impact assessments, downscaling techniques are essential. We propose spateGAN, a novel approach for spatio-temporal downscaling of precipitation data using conditional generative adversarial networks. Our method is based on a video super-resolution approach and trained on 10 years of country-wide radar observations for Germany. It simultaneously increases the spatial and temporal resolution of coarsened precipitation observations from 32 to 2 km and from 1 hr to 10 min. Our experiments indicate that the ensembles of generated temporally consistent rainfall fields are in high agreement with the observational data. Spatial structures with plausible advection were accurately generated. Compared to trilinear interpolation and a classical convolutional neural network, the generative model reconstructs the resolution-dependent extreme value distribution with high skill. It showed a high fractions skill score of 0.6 (spatio-temporal scale: 32 km and 1 hr) for rainfall intensities over 15 mm h−1 and a low relative bias of 3.35%. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000163600
Veröffentlicht am 31.10.2023
Originalveröffentlichung
DOI: 10.1029/2023EA002906
Scopus
Zitationen: 8
Web of Science
Zitationen: 3
Dimensions
Zitationen: 12
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Meteorologie und Klimaforschung – Atmosphärische Umweltforschung (IMK-IFU)
Institut für Meteorologie und Klimaforschung (IMK)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 10.2023
Sprache Englisch
Identifikator ISSN: 2333-5084
KITopen-ID: 1000163600
HGF-Programm 12.11.33 (POF IV, LK 01) Regional Climate and Hydrological Cycle
Erschienen in Earth and Space Science
Verlag American Geophysical Union (AGU)
Band 10
Heft 10
Seiten e2023EA002906
Bemerkung zur Veröffentlichung Gefördert durch den KIT-Publikationsfonds
Vorab online veröffentlicht am 16.10.2023
Nachgewiesen in Scopus
Web of Science
Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page