TY  - CONF
AU  - Langguth, Michael
AU  - Harder, Paula
AU  - Schicker, Irene
AU  - Patnala, Ankit
AU  - Lehner, Sebastian
AU  - Dabernig, Markus
AU  - Mayer, Konrad
TI  - A Benchmark Dataset for Meteorological Downscaling
M1  - FZJ-2024-07378
SP  - N/A
PY  - 2024
AB  - High spatial resolution in atmospheric representations is crucial across Earth science domains, but global reanalysis datasets like ERA5 often lack the detail to capture local phenomena due to their coarse resolution. Recent efforts have leveraged deep neural networks from computer vision to enhance the spatial resolution of meteorological data, showing promise for statistical downscaling. However, methodological diversity and insufficient comparisons with traditional downscaling techniques challenge these advancements. Our study introduces a benchmark dataset for statistical downscaling, utilizing ERA5 and the finer-resolution COSMO-REA6, to facilitate direct comparisons of downscaling methods for 2m temperature, global (solar) irradiance and 100m wind fields. Accompanying U-Net, GAN, and transformer models with a suite of evaluation metrics aim to standardize assessments and promote transparency and confidence in applying deep learning to meteorological downscaling.
T2  - International Conference on Learning Representations
CY  - 7 May 2024 - 11 May 2024, Vienna (Austria)
Y2  - 7 May 2024 - 11 May 2024
M2  - Vienna, Austria
LB  - PUB:(DE-HGF)8
DO  - DOI:10.34734/FZJ-2024-07378
UR  - https://juser.fz-juelich.de/record/1034617
ER  -