Spatially Coherent Postprocessing of Cloud Cover Ensemble Forecasts

• Published in: Monthly weather review 2021-12, Vol.149 (12), p.3923-3937
• Main Authors: Dai, Y, Hemri, S
• Format: Article
• Language: English
• Subjects: Cloud cover; Deep learning; Economic forecasting; Ensemble forecasting; Generative adversarial networks; Machine learning; Methods; Neural networks; Numerical prediction; Numerical weather forecasting; Satellite data; Statistical analysis; Statistical methods; Weather forecasting
• ISSN: 0027-0644; 1520-0493
• DOI: 10.1175/MWR-D-21-0046.1

Statistical postprocessing is commonly applied to reduce location and dispersion errors of probabilistic forecasts provided by numerical weather prediction (NWP) models. If postprocessed forecast scenarios are required, the combination of ensemble model output statistics (EMOS) for univariate postprocessing with ensemble copula coupling (ECC) or the Schaake shuffle (ScS) to retain the dependence structure of the raw ensemble is a state-of-the-art approach. However, modern machine learning methods may lead to both a better univariate skill and more realistic forecast scenarios. In this study, we postprocess multimodel ensemble forecasts of cloud cover over Switzerland provided by COSMO-E and ECMWF-IFS using (i) EMOS + ECC, (ii) EMOS + ScS, (iii) dense neural networks (dense NN) + ECC, (iv) dense NN + ScS, and (v) conditional generative adversarial networks (cGAN). The different methods are verified using EUMETSAT satellite data. Dense NN shows the best univariate skill, but cGAN performed only slightly worse. Furthermore, cGAN generates realistic forecast scenario maps, while not relying on a dependence template like ECC or ScS, which is particularly favorable in the case of complex topography.