EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model

Pengfei Du, Jing-Jia Luo, Xianxuan Lin, Fan Meng

Remote Sensing · 01.06.2026 · 18 (11) · 1786

DOI: 10.3390/rs18111786 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 01.06.2026. Verfasst von Pengfei Du und 3 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, CCF-Baidu Open Fund, Jiangsu Graduate Student Research and Innovation Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predicting tropical cyclone (TC) precipitation is an important step in disaster prevention and mitigation. However, in the probability prediction of TC precipitation, traditional deep learning models are highly sensitive to initial conditions and can only provide deterministic forecasts, making it difficult to quantify uncertainty. In this study, we develop an AI-driven deep learning model based on diffusion models, incorporating historical data to reduce sensitivity to initial conditions and enhance precipitation distribution accuracy. Compared with traditional deep learning methods, this model outperforms other models in terms of the SSIM and PSNR for deterministic prediction of TC precipitation in 0–12 h. For probabilistic prediction, this model also achieves lower CRPS and Brier scores. Therefore, diffusion-based deep learning models not only show broad application prospects in TC-precipitation forecasting but also hold promise for providing probabilistic prediction methods for various disasters, enabling the widespread adoption of probabilistic forecasting across different prediction domains.

Förderung

  • National Natural Science Foundation of China
  • CCF-Baidu Open Fund
  • Jiangsu Graduate Student Research and Innovation Program
  • Startup Foundation for Introducing Talent of NUIST
  • the Natural Science Foundation of Jiangsu Province

Zitieren

APA

Du, P., Luo, J., Lin, X., & Meng, F. (2026). Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model. Remote Sensing, 18(11), 1786. https://doi.org/10.3390/rs18111786

Vancouver

Du P, Luo J, Lin X, Meng F. Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model. Remote Sensing. 2026;18(11):1786. doi:10.3390/rs18111786

BibTeX
@article{Du2026,
  author = {Du, Pengfei and Luo, Jing-Jia and Lin, Xianxuan and Meng, Fan},
  title = {Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1786},
  doi = {10.3390/rs18111786}
}
Kostenlos starten →