EUVIMEDEUVIMED entdecken
Crossref

SimNowcasting: Enhancing Precipitation Nowcasting via Lightweight Multiscale Convolution and Channel-Wise Attention Mechanism

Meihan Qi, Wei Fang, Yang Zhao

IEEE Internet of Things Journal · 01.06.2026 · 13 (11) · 23278-23287

DOI: 10.1109/jiot.2026.3670117 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.06.2026. Verfasst von Meihan Qi und 2 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China, State Key Laboratory of Severe Weather, Chinese Academy of Meteorological Sciences, Open Project of Provincial Key Laboratory for Computer Information Processing Technology, Soochow University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Precipitation nowcasting refers to the prediction of precipitation within 0–2 h. Extreme precipitation events have been occurring frequently; therefore, precipitation nowcasting is significantly important. Existing deep learning-based precipitation nowcasting methods usually use complex network structures, resulting in low computational efficiency and insufficient generalization. We introduce SimNowcasting, a straightforward, yet highly effective model for spatiotemporal sequence prediction. By developing the lightweight SimInception module, SimNowcasting extracts multiscale features from spatiotemporal data with fewer training parameters than standard Inception-based approaches. This approach shows improved generalization on the evaluated dataset. Furthermore, the integration of the spatial encoder (SE) module allows for the precise capture of critical features within the channel dimension of radar echo sequences, thereby heightening the network’s sensitivity to key features. Experimental results on Shanghai radar data indicate that SimNowcasting achieves competitive performance in forecast accuracy compared to baseline methods, suggesting potential for practical precipitation nowcasting applications.

Förderung

  • National Natural Science Foundation of China
  • State Key Laboratory of Severe Weather, Chinese Academy of Meteorological Sciences
  • Open Project of Provincial Key Laboratory for Computer Information Processing Technology, Soochow University
  • Bei Ji Ge Open Project of Nanjing Institute of Meteorological Science and Technology Innovation

Zitieren

APA

Qi, M., Fang, W., & Zhao, Y. (2026). SimNowcasting: Enhancing Precipitation Nowcasting via Lightweight Multiscale Convolution and Channel-Wise Attention Mechanism. IEEE Internet of Things Journal, 13(11), 23278-23287. https://doi.org/10.1109/jiot.2026.3670117

Vancouver

Qi M, Fang W, Zhao Y. SimNowcasting: Enhancing Precipitation Nowcasting via Lightweight Multiscale Convolution and Channel-Wise Attention Mechanism. IEEE Internet of Things Journal. 2026;13(11):23278-23287. doi:10.1109/jiot.2026.3670117

BibTeX
@article{Qi2026,
  author = {Qi, Meihan and Fang, Wei and Zhao, Yang},
  title = {SimNowcasting: Enhancing Precipitation Nowcasting via Lightweight Multiscale Convolution and Channel-Wise Attention Mechanism},
  journal = {IEEE Internet of Things Journal},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {23278--23287},
  doi = {10.1109/jiot.2026.3670117}
}
Kostenlos starten →