Preprints
https://doi.org/10.5194/egusphere-2024-4053
https://doi.org/10.5194/egusphere-2024-4053
10 Mar 2025
 | 10 Mar 2025

Automated urban flood level detection based on flooded bus dataset using YOLOv8

Yanbin Qiu, Xudong Zhou, Jiaquan Wan, Tao Yang, Lvfei Zhang, Yuanzhuo Zhong, Leqi Shen, and Xinwu Ji

Abstract. Rapid and accurate acquisition of urban flood information is crucial for flood prevention, disaster mitigation, and emergency management. With the development of mobile internet, crowdsourced images on social media have been emerged as a novel and effective data source for flood information collection. However, selecting appropriate targets and employing suitable methods to determine flooding level has not been well investigated. This study proposes a method to assess urban flood risk levels based on the submerged status of buses captured in social media images. First, a dataset containing 1008 images in complex scenes is constructed from social media. The images are annotated using Labelimg, and expanded with a data augmentation strategy. Four YOLOv8 configurations are validated for their ability to identify urban flood risk levels. The validation process involves training the models on original datasets, augmented datasets, and datasets representing complex scenes. Results demonstrate that, compared to traditional reference objects (e.g., cars), buses exhibit greater stability and higher accuracy in identification of urban flood risk levels due to their standardized height and widespread presence as they remain service during flood events. The data augmentation strategy enhances the model's mAP50 and mAP50-95 metrics by over 10 % and 20 %, respectively. Additionally, through comparative analysis of YOLOv8 configurations, YOLOv8s demonstrates superior results and achieves an effective balance between accuracy, training time, and computational resources, recommended for the identification of urban flood risk levels. This method provides a reliable technical foundation for real-time flood risk assessment and emergency management of urban transportation systems, with substantial potential for practical applications.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share

Journal article(s) based on this preprint

23 Sep 2025
Automated urban flood level detection based on flooded bus dataset using YOLOv8
Yanbin Qiu, Xudong Zhou, Jiaquan Wan, Tao Yang, Lvfei Zhang, Yuanzhuo Zhong, Leqi Shen, and Xinwu Ji
Nat. Hazards Earth Syst. Sci., 25, 3525–3544, https://doi.org/10.5194/nhess-25-3525-2025,https://doi.org/10.5194/nhess-25-3525-2025, 2025
Short summary
Yanbin Qiu, Xudong Zhou, Jiaquan Wan, Tao Yang, Lvfei Zhang, Yuanzhuo Zhong, Leqi Shen, and Xinwu Ji

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-4053', Anonymous Referee #1, 29 Apr 2025
    • AC1: 'Reply on RC1', Yanbin Qiu, 29 Apr 2025
  • RC2: 'Comment on egusphere-2024-4053', Anonymous Referee #2, 29 Apr 2025
    • AC2: 'Reply on RC2', Yanbin Qiu, 30 Apr 2025

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-4053', Anonymous Referee #1, 29 Apr 2025
    • AC1: 'Reply on RC1', Yanbin Qiu, 29 Apr 2025
  • RC2: 'Comment on egusphere-2024-4053', Anonymous Referee #2, 29 Apr 2025
    • AC2: 'Reply on RC2', Yanbin Qiu, 30 Apr 2025

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
ED: Reconsider after major revisions (further review by editor and referees) (04 Jun 2025) by Dung Tran
AR by Yanbin Qiu on behalf of the Authors (15 Jun 2025)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (20 Jun 2025) by Dung Tran
RR by Anonymous Referee #1 (05 Jul 2025)
RR by Anonymous Referee #3 (09 Aug 2025)
ED: Publish subject to minor revisions (review by editor) (10 Aug 2025) by Dung Tran
AR by Yanbin Qiu on behalf of the Authors (13 Aug 2025)  Author's response   Author's tracked changes   Manuscript 
ED: Publish subject to technical corrections (19 Aug 2025) by Dung Tran
AR by Yanbin Qiu on behalf of the Authors (21 Aug 2025)  Author's response   Manuscript 

Journal article(s) based on this preprint

23 Sep 2025
Automated urban flood level detection based on flooded bus dataset using YOLOv8
Yanbin Qiu, Xudong Zhou, Jiaquan Wan, Tao Yang, Lvfei Zhang, Yuanzhuo Zhong, Leqi Shen, and Xinwu Ji
Nat. Hazards Earth Syst. Sci., 25, 3525–3544, https://doi.org/10.5194/nhess-25-3525-2025,https://doi.org/10.5194/nhess-25-3525-2025, 2025
Short summary
Yanbin Qiu, Xudong Zhou, Jiaquan Wan, Tao Yang, Lvfei Zhang, Yuanzhuo Zhong, Leqi Shen, and Xinwu Ji
Yanbin Qiu, Xudong Zhou, Jiaquan Wan, Tao Yang, Lvfei Zhang, Yuanzhuo Zhong, Leqi Shen, and Xinwu Ji

Viewed

Total article views: 716 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
593 101 22 716 14 34
  • HTML: 593
  • PDF: 101
  • XML: 22
  • Total: 716
  • BibTeX: 14
  • EndNote: 34
Views and downloads (calculated since 10 Mar 2025)
Cumulative views and downloads (calculated since 10 Mar 2025)

Viewed (geographical distribution)

Total article views: 700 (including HTML, PDF, and XML) Thereof 700 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 23 Sep 2025
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Short summary
Floods pose a significant risk to cities, so fast and accurate information is essential for disaster management. This study used social media images to assess flood levels by analyzing submerged buses, a reliable reference object. An advanced AI model (YOLOv8) trained on different datasets achieved high flood detection accuracy. The results provide a scalable solution for real-time flood monitoring, enhancing urban transportation safety, and supporting emergency planning.
Share