Dataset for "Uncertainty-Aware Methods for Enhancing Rainfall Prediction with deep-learning based Post-Processing Segmentation"

Title: Dataset for "Uncertainty-Aware Methods for Enhancing Rainfall Prediction with Deep-Learning Based Post-Processing Segmentation"

Authors: Simone Monaco, Luca Monaco, Daniele Apiletti

Description:This dataset supports the study presented in the paper "Uncertainty-Aware Methods for Enhancing Rainfall Prediction with Deep-Learning Based Post-Processing Segmentation". The work focuses on improving daily quantitative precipitation forecasts and uncertainty estimates over the Piedmont and Aosta Valley regions in Italy by blending outputs from four Numerical Weather Prediction (NWP) models using uncertainty-aware deep learning methods and NWIOI observational data (Turco et al., 2013). NWPs forecasts can be obtained on request, observational data is provided in this repository. The NWPs include:

BOLAM-ISAC-CNR (Buzzi et al., 1994): data requests are possibile at ISAC-CNR, at this link

COSMO-2I (Baldauf et al., 2011): data requests are possible at the COSMO Consortium, at this link

COSMO-5M (Doms & Baldauf, 2018): data requests are possible at the COSMO Consortium, at this link

ECMWF-IFS-HRES (ECMWF, 2016): data download is possible at this link

Observational data from NWIOI serve as the ground truth for model training. The dataset contains 420 gridded precipitation events from 2018 to 2024.

Dataset contents:

obs.zip: NWIOI observed precipitation data (.csv format, one file per event)

domain_mask.csv: Binary mask (1 for grid points in the study area, 0 otherwise)

allevents_dates.csv: Classification of all events by type and intensity, used for n-fold cross-validation and dataset splits

Citations:

BOLAM-ISAC-CNR: Buzzi, A., Fantini, M., Malguzzi, P., & Nerozzi, F. (1994). Validation of a limited area model in cases of Mediterranean cyclogenesis: surface fields and precipitation scores. Meteorology and Atmospheric Physics, 53(3), 137–153. Springer.

COSMO-2I: Baldauf, M., Seifert, A., Förstner, J., Majewski, D., Raschendorfer, M., & Reinhardt, T. (2011). Operational convective-scale numerical weather prediction with the COSMO model: Description and sensitivities. Monthly Weather Review, 139(12), 3887–3905. American Meteorological Society.

COSMO-5M: Doms, G., & Baldauf, M. (2018). A Description of the Nonhydrostatic Regional COSMO Model. Part I: Dynamics and Numerics. COSMO Technical Report, Deutscher Wetterdienst.

ECMWF-IFS-HRES: ECMWF. (2016). IFS Documentation CY43R1. ECMWF Technical Documentation.

NWIOI: Turco, M., Zollo, A. L., Ronchi, C., De Luigi, C., & Mercogliano, P. (2013). Assessing gridded observations for daily precipitation extremes in the Alps with a focus on northwest Italy. Natural Hazards and Earth System Sciences, 13(6), 1457–1468.

Related Repository: https://github.com/simone7monaco/probabilistic-rainprediction