Published December 23, 2019 | Version 1.0.0
Dataset Open

TAASRAD19 Radar Scans 2017-2019

Description

TAASRAD19 (Trentino-Alto Adige/Südtirol Radar 2019) is a high-resolution radar reflectivity dataset collected by the Civil Protection weather radar of the Trentino South Tyrol Region, in the Italian Alps.
The dataset includes 894,916 scans of precipitation from more than 9 years of data, offering a novel resource to develop and benchmark analog ensemble models and machine learning solutions for precipitation nowcasting. Data are expressed as 2D images, considering the maximum reflectivity on the vertical section and 5 minutes sampling rate, covering an area of 240km of diameter at 500m horizontal resolution. The TAASRAD19 distribution also includes a curated set of 1,732 sequences, for a total of 362,233 radar images, labeled with precipitation type tags assigned by expert meteorologists. We validated TAASRAD19 as a benchmark for nowcasting using deep learning model to forecast reflectivity and a procedure based on the UMAP dimensionality reduction method for interactive exploration.
Software methods for data pre-processing, model training and inference, and a pre-trained model are
publicly available at https://github.com/MPBA/TAASRAD19 for replication and reproducibility.

Notes

This dataset contains the radar scans for the years 2017 - 2019. The radar scans for years 2010 - 2016 are available here: https://doi.org/10.5281/zenodo.3577451 The precipitation sequences in HDF5 format, extracted from the full scan dataset are available here: https://doi.org/10.5281/zenodo.3591404

Files

2017.zip

Files (35.4 GB)

Name Size Download all
md5:52f7c922d712bb8905901b42f525a299
10.8 GB Preview Download
md5:a1a1a4f87c167cc93192ebdedaea96f4
11.9 GB Preview Download
md5:9fd7475b9310b94a403074ff4c319086
12.8 GB Preview Download
md5:45f4b3bfb40d0c09c4d05ac4163b973f
869.5 kB Preview Download

Additional details

Related works

Compiles
Dataset: 10.5281/zenodo.3591404 (DOI)
Dataset: 10.5281/zenodo.3866203 (DOI)
Continues
Dataset: 10.5281/zenodo.3577451 (DOI)
Is cited by
Journal article: 10.3390/atmos11030267 (DOI)
Is documented by
Journal article: 10.1038/s41597-020-0574-8 (DOI)