Articles | Volume 25, issue 11
https://doi.org/10.5194/nhess-25-4361-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/nhess-25-4361-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
05 Nov 2025
Research article |
| 05 Nov 2025
| 05 Nov 2025
Identification of nighttime urban flood inundation extent using deep learning
Jiaquan Wan
College of Hydrology and Water Resources, Hohai University, Nanjing, 210098, China
The National Key Laboratory of Water Disaster Prevention, Hohai University, Nanjing, 210098, China
Yangtze Institute for Conservation and Development, Hohai University, Jiangsu, 210098, China
School of Computer Engineering, Nanjing Institute of Technology, Nanjing 211167, China
Yannian Cheng
School of Remote Sensing and Surveying Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China
Cuiyan Zhang
School of Computer Engineering, Nanjing Institute of Technology, Nanjing 211167, China
Fengchang Xue
School of Remote Sensing and Surveying Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China
College of Hydrology and Water Resources, Hohai University, Nanjing, 210098, China
The National Key Laboratory of Water Disaster Prevention, Hohai University, Nanjing, 210098, China
Yangtze Institute for Conservation and Development, Hohai University, Jiangsu, 210098, China
Fei Tong
China Institute of Water Resources and Hydropower, Beijing, 100048, China
Quan J. Wang
Department of Infrastructure Engineering, Faculty of Engineering and Information Technology, The University of Melbourne, Melbourne, Victoria 3010, Australia
Related authors
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
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.
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
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.
Yuan Li, Kangning Xü, Zhiyong Wu, Zhiwei Zhu, and Quan J. Wang
Hydrol. Earth Syst. Sci., 27, 4187–4203, https://doi.org/10.5194/hess-27-4187-2023, https://doi.org/10.5194/hess-27-4187-2023, 2023
Short summary
Short summary
A spatial–temporal projection-based calibration, bridging, and merging (STP-CBaM) method is proposed. The calibration model is built by post-processing ECMWF raw forecasts, while the bridging models are built using atmospheric intraseasonal signals as predictors. The calibration model and bridging models are merged through a Bayesian modelling averaging (BMA) method. The results indicate that the newly developed method can generate skilful and reliable sub-seasonal precipitation forecasts.
Qichun Yang, Quan J. Wang, Andrew W. Western, Wenyan Wu, Yawen Shao, and Kirsti Hakala
Hydrol. Earth Syst. Sci., 26, 941–954, https://doi.org/10.5194/hess-26-941-2022, https://doi.org/10.5194/hess-26-941-2022, 2022
Short summary
Short summary
Forecasts of evaporative water loss in the future are highly valuable for water resource management. These forecasts are often produced using the outputs of climate models. We developed an innovative method to correct errors in these forecasts, particularly the errors caused by deficiencies of climate models in modeling the changing climate. We apply this method to seasonal forecasts of evaporative water loss across Australia and achieve significant improvements in the forecast quality.
Qichun Yang, Quan J. Wang, Kirsti Hakala, and Yating Tang
Hydrol. Earth Syst. Sci., 25, 4773–4788, https://doi.org/10.5194/hess-25-4773-2021, https://doi.org/10.5194/hess-25-4773-2021, 2021
Short summary
Short summary
Forecasts of water losses from land surface to the air are highly valuable for water resource management and planning. In this study, we aim to fill a critical knowledge gap in the forecasting of evaporative water loss. Model experiments across Australia clearly suggest the necessity of correcting errors in input variables for more reliable water loss forecasting. We anticipate that the strategy developed in our work will benefit future water loss forecasting and lead to more skillful forecasts.
Cited articles
Bai, Y., Li, J., Shi, L., Jiang, Q., Yan, B., and Wang, Z.: DME-DeepLabV3+: a lightweight model for diabetic macular edema extraction based on DeepLabV3+ architecture, Frontiers in Medicine, 10, 11, https://doi.org/10.3389/fmed.2023.1150295, 2023.
Bofana, J., Zhang, M., Wu, B., Zeng, H., Nabil, M., Zhang, N., Elnashar, A., Tian, F., Da Silva, J. M., Botão, A., Atumane, A., Mushore, T. D., and Yan, N.: How long did crops survive from floods caused by Cyclone Idai in Mozambique detected with multi-satellite data, Remote Sens. Environ., 269, 112808, https://doi.org/10.1016/j.rse.2021.112808, 2022.
Burn, D. H. and Whitfield, P. H.: Climate related changes to flood regimes show an increasing rainfall influence, Journal of Hydrology, 617, 13, https://doi.org/10.1016/j.jhydrol.2023.129075, 2023.
Choi, Y. H. and Yoo, S. J.: Quantized-state-based decentralized neural network control of a class of uncertain interconnected nonlinear systems with input and interaction time delays, Eng. Appl. Artif. Intel., 125, 106759, https://doi.org/10.1016/j.engappai.2023.106759, 2023.
Du, W., Qian, M., He, S., Xu, L., Zhang, X., Huang, M., and Chen, N.: An improved ResNet method for urban flooding water depth estimation from social media images, Measurement, 242, 12, https://doi.org/10.1016/j.measurement.2024.116114, 2025.
Fu, H., Meng, D., Li, W., and Wang, Y.: Bridge Crack Semantic Segmentation Based on Improved Deeplabv3+, Journal of Marine Science and Engineering, 9, 14, https://doi.org/10.3390/jmse9060671, 2021.
Ghosh, P., Sudarsan, J. S., and Nithiyanantham, S.: Nature-Based Disaster Risk Reduction of Floods in Urban Areas, Water Resources Management, 38, 1847–1866, https://doi.org/10.1007/s11269-024-03757-4, 2024.
Gu, Q., Chai, F., Zang, W., Zhang, H., Hao, X., and Xu, H.: A Two-Level Early Warning System on Urban Floods Caused by Rainstorm, Sustainability, 17, 16, https://doi.org/10.3390/su17052147, 2025.
Hao, X., Lyu, H., Wang, Z., Fu, S., and Zhang, C.: Estimating the spatial-temporal distribution of urban street ponding levels from surveillance videos based on computer vision, Water Resources Management, 36, 1799–1812, https://doi.org/10.1007/s11269-022-03107-2, 2022.
He, K., Zhang, X., Ren, S., and Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition, in: Proceedings of the 13th European Conference on Computer Vision (ECCV), 8691, 346–361, https://doi.org/10.1007/978-3-319-10578-9_23, 2014.
Jin, K., Zhang, J., Wang, Z., Zhang, J., Liu, N., Li, M., and Ma, Z.: Application of deep learning based on thermal images to identify the water stress in cotton under film-mulched drip irrigation, Agricultural Water Management, 299, 108901, https://doi.org/10.1016/j.agwat.2024.108901, 2024.
Kim, H., Villarini, G., Wasko, C., and Tramblay, Y.: Changes in the Climate System Dominate Inter-Annual Variability in Flooding Across the Globe, Geophysical Research Letters, 51, https://doi.org/10.1029/2023gl107480, 2024.
Kundzewicz, Z. W., Su, B., Wang, Y., Xia, J., Huang, J., and Jiang, T.: Flood risk and its reduction in China, Adv. Water Resour., 130, 37–45, https://doi.org/10.1016/j.advwatres.2019.05.020, 2019.
Land, E. H.: The retinex theory of color vision, Scientific American, 237, 108–128, https://doi.org/10.1038/scientificamerican1277-108, 1977.
Li, X., Wang, W., Feng, X., and Li, M.: Deep parametric Retinex decomposition model for low-light image enhancement, Computer Vision and Image Understanding, 241, 14, https://doi.org/10.1016/j.cviu.2024.103948, 2024
Liu, W., Feng, Q., Engel, B. A., Yu, T., Zhang, X., and Qian, Y.: A probabilistic assessment of urban flood risk and impacts of future climate change, Journal of Hydrology, 618, 11, https://doi.org/10.1016/j.jhydrol.2023.129267, 2023.
Liu, X., Song, L., Liu, S., and Zhang, Y.: A review of deep-learning-based medical image segmentation methods, Sustainability, 13, 1224, https://doi.org/10.3390/su13031224, 2020.
Mason, D. C., Davenport, I. J., Neal, J. C., Schumann, G. J. P., and Bates, P. D.: Near Real-Time Flood Detection in Urban and Rural Areas Using High-Resolution Synthetic Aperture Radar Images, IEEE Transactions on Geoscience and Remote Sensing, 50, 3041–3052, https://doi.org/10.1109/tgrs.2011.2178030, 2012.
Muhadi, N. A., Abdullah, A. F., Bejo, S. K., Mahadi, M. R., Mijic, A., and Vojinovic, Z.: Deep learning and LiDAR integration for surveillance camera-based river water level monitoring in flood applications, Natural Hazards, 120, 8367–8390, https://doi.org/10.1007/s11069-024-06503-6, 2024.
Munawar, H. S., Ullah, F., Qayyum, S., and Heravi, A.: Application of deep learning on UAV-based aerial images for flood detection, Smart Cities, 4, 1220–1242, https://doi.org/10.3390/smartcities4030065, 2021.
Peng, H., Zhong, J., Liu, H., Li, J., Yao, M., and Zhang, X.: ResDense-focal-DeepLabV3+ enabled litchi branch semantic segmentation for robotic harvesting, Computers and Electronics in Agriculture, 206, 12, https://doi.org/10.1016/j.compag.2023.107691, 2023.
Peng, H., Xiang, S., Chen, M., Li, H., and Su, Q.: DCN-Deeplabv3+: A Novel Road Segmentation Algorithm Based on Improved Deeplabv3+, Ieee Access, 12, 87397–87406, https://doi.org/10.1109/access.2024.3416468, 2024.
Sarp, S., Kuzlu, M., Cetin, M., Sazara, C., and Guler, O.: Detecting floodwater on roadways from image data using Mask-R-CNN, 2020 International Conference on INnovations in Intelligent SysTems and Applications, Novi Sad, Serbia, 24–26, https://doi.org/10.1109/INISTA49547.2020.9194655, 2020.
Sazara, C., Cetin, K., and Iftekharuddin, K.: Detecting floodwater on roadways from image data with handcrafted features and deep transfer learning, 2019 IEEE Intelligent Transportation Systems Conference, Auckland, New Zealand, 27–30, https://doi.org/10.1109/ITSC.2019.8917368, 2019.
Sengupta, S., Chyrmang, G., Bora, K., Das, H. S., Li, A., Lemos, B., and Mallik, S.: Assessment of different U-Net backbones in segmenting colorectal adenocarcinoma from H&E histopathology, Pathology Research and Practice, 266, 11, https://doi.org/10.1016/j.prp.2025.155820, 2025.
Siddique, N., Paheding, S., Elkin, C. P., and Devabhaktuni, V.: U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications, IEEE Access, 9, 82031–82057, https://doi.org/10.1109/access.2021.3086020, 2021.
Tang, Y., Tan, D, Li, H., Zhu, M., Li, X., Wang, X., Wang, J., Wang, Z., Gao, C., Wang, J., and Han, A.: RTC_TongueNet: An improved tongue image segmentation model based on DeepLabV3, Digital Health, 10, 20552076241242773, https://doi.org/10.1177/20552076241242773, 2024.
Visser, F.: Rapid mapping of urban development from historic Ordnance Survey maps: an application for pluvial flood risk in Worcester, J. Maps., 10, 276–288, https://doi.org/10.1080/17445647.2014.893847, 2014.
Wan, J., Qin, Y., Shen, Y., Yang, T., Yan, X., Zhang, S., Yang, G., Xue, F., and Wang, Q.: Automatic detection of urban flood level with YOLOv8 using flooded vehicle dataset, Journal of Hydrology, 639, 131625, https://doi.org/10.1016/j.jhydrol.2024.131625, 2024.
Wan, J., Xue, F., Shen, Y., Song, H., Shi, P., Qin, Y., Yang, T., and Wang, Q. J.: Automatic segmentation of urban flood extent in video image with DSS-YOLOv8n, Journal of Hydrology, 655, 12, https://doi.org/10.1016/j.jhydrol.2025.132974, 2025.
Wang, Y., Shen, Y., Salahshour, B., Cetin, M., Iftekharuddin, K., Tahvildari, N., Huang, G., Harris, D., Ampofo, K., and Goodall, J.: Urban flood extent segmentation and evaluation from real-world surveillance camera images using deep convolutional neural network, Environmental Modelling & Software, 173, 105939, https://doi.org/10.1016/j.envsoft.2023.105939, 2024a.
Wang, Y., Yang, L., Liu, X., and Yan, P.: An improved semantic segmentation algorithm for high-resolution remote sensing images based on DeepLabv3+, Scientific Reports, 14, 15, https://doi.org/10.1038/s41598-024-60375-1, 2024b.
Wei, Z., Chen, L., Tu, T., Ling, P., Chen, H., and Jin, Y.: Disentangle then Parse: Night-time Semantic Segmentation with Illumination Disentanglement, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 21593–21603, https://doi.org/10.48550/arXiv.2307.09362, 2023.
Yadavendra and Chand, S.: Semantic segmentation of human cell nucleus using deep U-Net and other versions of U-Net models, Network-Computation in Neural Systems, 33, 167–186, https://doi.org/10.1080/0954898x.2022.2096938, 2022.
Yang, Y., Zhuang, Y., Bi, F., Shi, H., and Xie, Y.: M-FCN: Effective Fully Convolutional Network-Based Airplane Detection Framework, IEEE Geoscience and Remote Sensing Letters, 14, 1293–1297, https://doi.org/10.1109/lgrs.2017.2708722, 2017.
Yu, F., Koltun, V., and Funkhouser, T.: Dilated residual networks, in: Proceedings of the 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 636–644, https://doi.org/10.1109/cvpr.2017.75, 2017.
Zeng, Y., Chang, M., and Lin, G.: A novel AI-based model for real-time flooding image recognition using super-resolution generative adversarial network, Journal of Hydrology, 638, 12, https://doi.org/10.1016/j.jhydrol.2024.131475, 2024.
Zhang, L., Han, G., Qiao, Y., Xu, L., Chen, L., and Tang, J.: Interactive Dairy Goat Image Segmentation for Precision Livestock Farming, Animals, 13, 17, https://doi.org/10.3390/ani13203250, 2023.
Zhao, J., Wang, X., Zhang, C., Hu, J., Wan, J., Cheng, L., Shi, S., and Zhu, X.: Urban Waterlogging Monitoring and Recognition in Low-Light Scenarios Using Surveillance Videos and Deep Learning, Water, 17, 19, https://doi.org/10.3390/w17050707, 2025.
Zhao, W., Zhang, H., Yan, Y., Fu, Y., and Wang, H.: A Semantic Segmentation Algorithm Using FCN with Combination of BSLIC, Applied Sciences-Basel, 8, 500, https://doi.org/10.3390/app8040500, 2018.
Zheng, F., Westra, S., Leonard, M., and Sisson, S. A.: Modeling dependence between extreme rainfall and storm surge to estimate coastal flooding risk, Water Resour. Res., 50, 2050–2071, https://doi.org/10.1002/2013WR014616, 2014.
Short summary
Urban flooding is a growing issue in cities, often disrupting daily life, especially at night, when the extent of flooding is harder to identify. This study introduces NWseg, a new deep learning model designed to identify the extent of urban flooding at night. Using a dataset of 4000 nighttime images, we found that NWseg outperforms existing models in accuracy. This research offers a practical solution for real-time flood monitoring, helping improve urban disaster response and management.
Urban flooding is a growing issue in cities, often disrupting daily life, especially at night,...
Altmetrics
Final-revised paper
Preprint