EUVIMEDEUVIMED entdecken
Crossref

Optimisation of waterlogging disaster warning system based on deep reinforcement learning

Nan Ma, Guowei Liu, Yijun Wang, Lisheng Xin

Infrastructure Asset Management · 19.11.2026 · 13 (4) · 314-327

DOI: 10.1680/jinam.25.00016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Infrastructure Asset Management, online erschienen am 23.06.2026. Verfasst von Nan Ma und 3 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: Science and Technology Project of China Southern Power Grid Company Limited.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study focuses on the optimisation of the urban waterlogging disaster warning system. In view of the limitations of traditional warning systems in complex urban environments, deep reinforcement learning (DRL) technology is introduced. The proposed DRL-EWS model integrates a spatiotemporal graph convolutional network for spatial feature extraction, a gated recurrent unit for temporal sequence modelling, and a policy gradient-based decision module for adaptive warning generation. By innovatively combining these components, the risk of urban waterlogging is accurately predicted. The results show that the waterlogging disaster warning system (DRL-EWS) based on DRL is superior to traditional and other machine learning warning models in terms of warning accuracy, false alarm rate, and false alarm rate, and has good adaptability to different terrains, pipe network density, rainfall patterns, and other conditions. This study not only enriches the waterlogging warning technology system in theory, but its practical results are expected to enhance the urban waterlogging defence capabilities and provide a strong guarantee for urban safety. At the same time, it also points out the direction for further improvement in subsequent research.

Förderung

  • Science and Technology Project of China Southern Power Grid Company Limited

Zitieren

APA

Ma, N., Liu, G., Wang, Y., & Xin, L. (2026). Optimisation of waterlogging disaster warning system based on deep reinforcement learning. Infrastructure Asset Management, 13(4), 314-327. https://doi.org/10.1680/jinam.25.00016

Vancouver

Ma N, Liu G, Wang Y, Xin L. Optimisation of waterlogging disaster warning system based on deep reinforcement learning. Infrastructure Asset Management. 2026;13(4):314-327. doi:10.1680/jinam.25.00016

BibTeX
@article{Ma2026,
  author = {Ma, Nan and Liu, Guowei and Wang, Yijun and Xin, Lisheng},
  title = {Optimisation of waterlogging disaster warning system based on deep reinforcement learning},
  journal = {Infrastructure Asset Management},
  year = {2026},
  volume = {13},
  number = {4},
  pages = {314--327},
  doi = {10.1680/jinam.25.00016}
}
Kostenlos starten →