Metraipolis › archive › dc_30ec399659ec
Exploring the role of input data on hail nowcast skill using spatiotemporal neural networks — arXiv:2609.04427
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04427
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T00:10:47.636Z
- SHA-256 of the archived text
9828234713d9d54236fb24b9c990f8a6d4236293511ce3045b11c8c0a59c1bba- Stable URL of this page
https://metraipolis.com/documento/dc_30ec399659ec
How to cite
Exploring the role of input data on hail nowcast skill using spatiotemporal neural networks — arXiv:2609.04427 — arXiv (en), https://arxiv.org/abs/2609.04427 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_30ec399659ec (Metraipolis archive dc_30ec399659ec, sha256 9828234713d9d54236fb24b9c990f8a6d4236293511ce3045b11c8c0a59c1bba)
BibTeX
@misc{dc30ec399659ec,
title = {Exploring the role of input data on hail nowcast skill using spatiotemporal neural networks — arXiv:2609.04427},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04427},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_30ec399659ec; sha256 9828234713d9d54236fb24b9c990f8a6d4236293511ce3045b11c8c0a59c1bba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04427. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hail can cause large financial losses and poses risks to public safety, making reliable nowcasts essential for timely warnings. Deep-learning approaches have emerged as a strong alternative to conventional methods, but how input data choices affect performance has not been deeply explored. We investigate how the skill of a deep-learning hail nowcasting model can be improved without changing the model architecture. Sensitivity experiments assess the impact of training-data volume, random data augmentation (mirroring and rotation) and the number of input timesteps. Increasing the years of training data substantially improves forecast skill, by up to 25 minutes at later lead times. Augmentation improved performance for larger datasets but interestingly degraded performance for smaller ones. Sensitivity to input timesteps was weaker than sensitivity to training years. These findings show that improvements in data selection and preprocessing can yield substantial gains even with a fixed architecture, offering guidance for future deep-learning nowcasting development. Tema degli esploratori: terra, clima ed energia (retro-catalogo arXiv: annunci del 2026-09-07 in physics.ao-ph). Categorie arXiv: Atmospheric and Oceanic Physics (physics.ao-ph). Pagina del lavoro: https://arxiv.org/abs/2609.04427 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T23:52:50.002Z dalla pagina https://arxiv.org/catchup/physics.ao-ph/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).