DHDM: An interpretable masked deep‐learning model for hail potential forecasting
Quarterly Journal of the Royal Meteorological Society · 2026-10 · 152 (780)
DOI: 10.1002/qj.70236 ↗Kurz gefasst
Fachartikel in der Zeitschrift Quarterly Journal of the Royal Meteorological Society, online erschienen am 07.06.2026. Verfasst von Xinyi Zeng und 10 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Hailstorms pose a significant hazard, although how hail frequency may respond to climate change is still uncertain and varies by region. In addition, hail is spatially and temporally sporadic and depends on ground‐based reports, so observational samples of hail events are difficult to collect. To address this issue, this study proposes a deep‐learning‐based hail‐diagnosis model (DHDM). We developed a seven‐layer convolutional neural network with residual blocks and a masking mechanism. This model enhances hail‐detection capability under limited sample conditions. The results show that the DHDM has a hit rate of 80.7% and a false‐alarm rate of 50.9% for hail, under the condition of a dataset constructed with a 1:4 ratio of hail to non‐hail samples. Model interpretability analysis reveals that the incorporation of the masking mechanism enhances its focus on circulation patterns at 500‐ and 850‐hPa levels, thereby improving its capability to learn key features at these critical pressure levels. This suggests that the masking mechanism acts as a regularization and data augmentation strategy that encourages the model to learn more robust and distributed representations, rather than relying on fixed local patterns. This study highlights the potential of deep learning in severe convective weather forecasting and provides a reference for integrating masking mechanisms into meteorological applications to address the issue of learning with limited samples.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Zeng, X., Cheng, W., Liu, N., Liu, Q., Qi, C., Wang, M., Li, T., Ren, J., Fang, Y., Zhao, D., & Xia, J. (2026). DHDM: An interpretable masked deep‐learning model for hail potential forecasting. Quarterly Journal of the Royal Meteorological Society, 152(780). https://doi.org/10.1002/qj.70236
Vancouver
Zeng X, Cheng W, Liu N, Liu Q, Qi C, Wang M, et al. DHDM: An interpretable masked deep‐learning model for hail potential forecasting. Quarterly Journal of the Royal Meteorological Society. 2026;152(780). doi:10.1002/qj.70236
BibTeX
@article{Zeng2026,
author = {Zeng, Xinyi and Cheng, Wencong and Liu, Na and Liu, Qi and Qi, Chen and Wang, Miaobo and Li, Tianye and Ren, Junzhe and Fang, Yi and Zhao, Deming and Xia, Jiangjiang},
title = {DHDM: An interpretable masked deep‐learning model for hail potential forecasting},
journal = {Quarterly Journal of the Royal Meteorological Society},
year = {2026},
volume = {152},
number = {780},
doi = {10.1002/qj.70236}
}
EUVIMED