Capturing Urban Pluvial River Flooding Features Based on the Fusion of Physically Based and Data-Driven Approaches
Abstract
:1. Introduction
- (a)
- A dataset suitable for deep learning simulations was generated based on a physically based model, and data augmentation was implemented using Generative Adversarial Networks (GANs).
- (b)
- Various deep learning models applicable to urban pluvial river flooding were developed based on an encoder–decoder framework. The performance of these models and the impact of model parameters were evaluated, with the relationship between data volume and model complexity explored.
- (c)
- The capture of scheduling signals in urban pluvial river flooding was achieved, fitting the nonlinear effects of water engineering scheduling signals.
2. Methodology
2.1. Procedural Modeling
2.2. Physically Based Model (PBM)
2.3. Data-Driven Model (DDM)
2.3.1. Bidirectional Stacked LSTM (BS-LSTM)
2.3.2. Encoder–Decoder Structure with Attention Mechanism (EDA-LSTM)
2.4. One-Dimensional Data Augmentation
2.5. Capture of Water Engineering Scheduling Signals
2.6. Evaluation Metrics
3. Study Area and Materials
3.1. Case Study
3.2. Materials
3.2.1. Data Preprocessing
3.2.2. Construction of DDM Dataset
3.2.3. Hydraulic Scheduling Modes
4. Results and Discussion
4.1. Model Performance of Deep-River
4.2. Uncertainty Analysis of Model Hyperparameters
4.2.1. Hidden Layer Number
4.2.2. Batch Size
4.2.3. Learning Rate
4.3. Uncertainty Analysis of Model Structures
4.3.1. Comparison of Model Structures
4.3.2. Evaluation of Model Performances
4.4. Capturing Flooding Response for Regional Controls
4.4.1. Joint Scheduling Analysis Based on DRC
4.4.2. Regional Control Signals Capturing Based on FRC
4.5. Discussion
4.5.1. Advantages of Integrating Physically Based Models and Data-Driven Models
4.5.2. Limitations and Future Work
5. Conclusions
- (1)
- The Deep-River framework was developed based on the evolution characteristics of urban river flooding. The framework integrates multiple models, including B-LSTM, BS-LSTM, A-LSTM, ED-LSTM, and EDA-LSTM. The model performances at stations WS and GMG demonstrate a good fit of the Deep-River framework.
- (2)
- Model uncertainty stems from the parameters and structure. Optimal performance occurs at 80 or 130 hidden layers, with too few layers causing information loss, and too many leading to fluctuations. A batch size below 25 yields better results, while learning rates above 0.15 cause instability. BS-LSTM performs best, followed by B-LSTM and A-LSTM, due to their 1D output vectors, unlike ED-LSTM and EDA-LSTM, which allow weight sharing across stations. Increasing network depth within limits improves performance, with ED-LSTM and EDA-LSTM excelling in multi-station water level prediction.
- (3)
- Based on the A-LSTM architecture, a self-attention mechanism was introduced to capture the evolution characteristics of river flooding under scheduling influences. The results indicate that the dual-layer self-attention LSTM model exhibits strong adaptability. With scheduling information encoding, the simulated water level process shows a “double-peak” pattern, with the first peak significantly lower than that under non-scheduling conditions. The model effectively extracts global flood wave evolution trends, though its ability to capture local variations with large fluctuations is relatively weak.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Rubinato, M.; Nichols, A.; Peng, Y.; Zhang, J.M.; Lashford, C.; Cai, Y.P.; Lin, P.Z.; Tait, S. Urban and river flooding: Comparison of flood risk management approaches in the UK and China and an assessment of future knowledge needs. Water Sci. Eng. 2019, 12, 274–283. [Google Scholar] [CrossRef]
- Qi, M.; Huang, H.; Liu, L.; Chen, X. Spatial heterogeneity of controlling factors’ impact on urban pluvial flooding in Cincinnati, US. Appl. Geogr. 2020, 125, 102362. [Google Scholar] [CrossRef]
- Balistrocchi, M.; Grossi, G. Predicting the impact of climate change on urban drainage systems in northwestern Italy by a copula-based approach. J. Hydrol. Reg. Stud. 2020, 28, 100670. [Google Scholar] [CrossRef]
- Dash, P.; Punia, M. Governance and disaster: Analysis of land use policy with reference to Uttarakhand flood 2013, India. Int. J. Disaster Risk Reduct. 2019, 36, 101090. [Google Scholar] [CrossRef]
- Xu, T.; Li, K.; Engel, B.A.; Jia, H.; Leng, L.; Sun, Z.; Shaw, L.Y. Optimal adaptation pathway for sustainable low impact development planning under deep uncertainty of climate change: A greedy strategy. J. Environ. Manag. 2019, 248, 109280. [Google Scholar] [CrossRef]
- Kind, J.; Wouter Botzen, W.J.; Aerts, J.C. Accounting for risk aversion, income distribution and social welfare in cost-benefit analysis for flood risk management. Wiley Interdiscip. Rev. Clim. Change 2017, 8, e446. [Google Scholar] [CrossRef]
- Yin, J.; Yu, D.; Yin, Z.; Liu, M.; He, Q. Evaluating the impact and risk of pluvial flash flood on intra-urban road network: A case study in the city center of Shanghai, China. J. Hydrol. 2016, 537, 138–145. [Google Scholar] [CrossRef]
- Meng, Z.; Yao, D. Damage survey, radar, and environment analyses on the first-ever documented tornado in Beijing during the heavy rainfall event of 21 July 2012. Weather Forecast. 2014, 29, 702–724. [Google Scholar] [CrossRef]
- Huang, X.; Liu, G.; Liu, S.; Fan, Y.; Ma, J.; Fan, Z. Study on numerical simulation method of extreme rain flood risk in plain river network cities. China Flood Drought Manag. 2023, 33, 21–27,33. (In Chinese) [Google Scholar]
- Ye, C.; Xu, Z.; Lei, X.; Liao, W.; Ding, X.; Liang, Y. Assessment of urban flood risk based on data-driven models: A case study in Fuzhou City, China. Int. J. Disaster Risk Reduct. 2022, 82, 103318. [Google Scholar] [CrossRef]
- Berndtsson, R.; Becker, P.; Persson, A.; Aspegren, H.; Haghighatafshar, S.; Jönsson, K.; Larsson, R.; Mobini, S.; Mottaghi, M.; Nilsson, J.; et al. Drivers of changing urban flood risk: A framework for action. J. Environ. Manag. 2019, 240, 47–56. [Google Scholar] [CrossRef] [PubMed]
- Miller, J.D.; Hutchins, M. The impacts of urbanisation and climate change on urban flooding and urban water quality: A review of the evidence concerning the United Kingdom. J. Hydrol. Reg. Stud. 2017, 12, 345–362. [Google Scholar] [CrossRef]
- Qin, D.; Lu, C.; Liu, J.; Wang, H.; Wang, J.; Li, H.; Chu, J.; Chen, G. Theoretical framework of dualistic nature–social water cycle. Chin. Sci. Bull. 2014, 59, 810–820. [Google Scholar] [CrossRef]
- Zhang, S.; Fan, W.; Yi, Y.; Zhao, Y.; Liu, J. Evaluation method for regional water cycle health based on nature-society water cycle theory. J. Hydrol. 2017, 551, 352–364. [Google Scholar] [CrossRef]
- Liu, J.; Shao, W.; Xiang, C.; Mei, C.; Li, Z. Uncertainties of urban flood modeling: Influence of parameters for different underlying surfaces. Environ. Res. 2020, 182, 108929. [Google Scholar] [CrossRef]
- Ye, C.; Liao, W.; Xu, Z.; Li, X.; Shu, X. An enhanced framework for simulating urban pluvial flooding: Integrating nested watersheds and urban areas with spatial heterogeneity. J. Hydrol. 2025, 654, 132875. [Google Scholar] [CrossRef]
- Chen, Y.; Wang, C.; Yang, Q.; Lei, X.; Wang, H.; Jiang, S.; Wang, Z. Model predictive control and rainfall Uncertainties: Performance and risk analysis for drainage systems. J. Hydrol. 2024, 630, 130779. [Google Scholar] [CrossRef]
- Cao, W.; Zhou, Y.; Güneralp, B.; Li, X.; Zhao, K.; Zhang, H. Increasing global urban exposure to flooding: An analysis of long-term annual dynamics. Sci. Total Environ. 2022, 817, 153012. [Google Scholar] [CrossRef]
- Lin, T.; Liu, X.; Song, J.; Zhang, G.; Jia, Y.; Tu, Z.; Zheng, Z.; Liu, C. Urban waterlogging risk assessment based on internet open data: A case study in China. Habitat Int. 2018, 71, 88–96. [Google Scholar] [CrossRef]
- Konami, T.; Koga, H.; Kawatsura, A. Role of pre-disaster discussions on preparedness on consensus-making of integrated flood management (IFM) after a flood disaster, based on a case in the Abukuma River Basin, Fukushima, Japan. Int. J. Disaster Risk Reduct. 2021, 53, 102012. [Google Scholar] [CrossRef]
- Qi, W.; Ma, C.; Xu, H.; Chen, Z.; Zhao, K.; Han, H. A review on applications of urban flood models in flood mitigation strategies. Nat. Hazards 2021, 108, 31–62. [Google Scholar] [CrossRef]
- Salvadore, E.; Bronders, J.; Batelaan, O. Hydrological modelling of urbanized catchments: A review and future directions. J. Hydrol. 2015, 529, 62–81. [Google Scholar] [CrossRef]
- Mark, O.; Weesakul, S.; Apirumanekul, C.; Aroonnet, S.B.; Djordjević, S. Potential and limitations of 1D modelling of urban flooding. J. Hydrol. 2004, 299, 284–299. [Google Scholar] [CrossRef]
- Ferraro, D.; Costabile, P.; Costanzo, C.; Petaccia, G.; Macchione, F. A spectral analysis approach for the a priori generation of computational grids in the 2-D hydrodynamic-based runoff simulations at a basin scale. J. Hydrol. 2020, 582, 124508. [Google Scholar] [CrossRef]
- Hou, J.; Zhou, N.; Chen, G.; Huang, M.; Bai, G. Rapid forecasting of urban flood inundation using multiple machine learning models. Nat. Hazards 2021, 108, 2335–2356. [Google Scholar] [CrossRef]
- Eini, M.; Kaboli, H.S.; Rashidian, M.; Hedayat, H. Hazard and vulnerability in urban flood risk mapping: Machine learning techniques and considering the role of urban districts. Int. J. Disaster Risk Reduct. 2020, 50, 101687. [Google Scholar] [CrossRef]
- Zhao, G.; Pang, B.; Xu, Z.; Peng, D.; Xu, L. Assessment of urban flood susceptibility using semi-supervised machine learning model. Sci. Total Environ. 2019, 659, 940–949. [Google Scholar] [CrossRef]
- Situ, Z.; Zhong, Q.; Zhang, J.; Teng, S.; Ge, X.; Zhou, Q.; Zhao, Z. Attention-based deep learning framework for urban flood damage and risk assessment with improved flood prediction and land use segmentation. Int. J. Disaster Risk Reduct. 2025, 116, 105165. [Google Scholar] [CrossRef]
- Chen, C.; Jiang, J.; Liao, Z.; Zhou, Y.; Wang, H.; Pei, Q. A short-term flood prediction based on spatial deep learning network: A case study for Xi County, China. J. Hydrol. 2020, 607, 127535. [Google Scholar] [CrossRef]
- Zhu, S.; Wei, J.; Zhang, H.; Xu, Y.; Qin, H. Spatiotemporal deep learning rainfall-runoff forecasting combined with remote sensing precipitation products in large scale basins. J. Hydrol. 2023, 616, 128727. [Google Scholar] [CrossRef]
- Moon, H.; Yoon, S.; Moon, Y. Urban flood forecasting using a hybrid modeling approach based on a deep learning technique. J. Hydroinformatics 2023, 25, 593–610. [Google Scholar] [CrossRef]
- Chen, Z.; Lin, H.; Shen, G. TreeLSTM: A spatiotemporal machine learning model for rainfall-runoff estimation. J. Hydrol. Reg. Stud. 2023, 48, 101474. [Google Scholar] [CrossRef]
- Kim, H.I.; Han, K.Y. Urban flood prediction using deep neural network with data augmentation. Water 2020, 12, 899. [Google Scholar] [CrossRef]
- Guo, Z.; Leitao, J.P.; Simões, N.E.; Moosavi, V. Data-driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks. J. Flood Risk Manag. 2021, 14, e12684. [Google Scholar] [CrossRef]
- Darabi, H.; Choubin, B.; Rahmati, O.; Haghighi, A.T.; Pradhan, B.; Kløve, B. Urban flood risk mapping using the GARP and QUEST models: A comparative study of machine learning techniques. J. Hydrol. 2019, 569, 142–154. [Google Scholar] [CrossRef]
- Lin, L.; Tang, C.; Liang, Q.; Wu, Z.; Wang, X.; Zhao, S. Rapid urban flood risk mapping for data-scarce environments using social sensing and region-stable deep neural network. J. Hydrol. 2023, 617, 128758. [Google Scholar] [CrossRef]
- Mohamadiazar, N.; Ebrahimian, A.; Hosseiny, H. Integrating deep learning, satellite image processing, and spatial-temporal analysis for urban flood prediction. J. Hydrol. 2024, 639, 131508. [Google Scholar] [CrossRef]
- Feng, B.; Wang, J.; Zhang, Y.; Hall, B.; Zeng, C. Urban flood hazard mapping using a hydraulic–GIS combined model. Nat. Hazards 2020, 100, 1089–1104. [Google Scholar] [CrossRef]
- Wu, Z.; Ma, B.; Wang, H.; Hu, C.; Lv, H.; Zhang, X. Identification of sensitive parameters of urban flood model based on artificial neural network. Water Resour. Manag. 2021, 35, 2115–2128. [Google Scholar] [CrossRef]
- Berkhahn, S.; Fuchs, L.; Neuweiler, I. An ensemble neural network model for real-time prediction of urban floods. J. Hydrol. 2019, 575, 743–754. [Google Scholar] [CrossRef]
- Bermúdez, M.; Cea, L.; Puertas, J. A rapid flood inundation model for hazard mapping based on least squares support vector machine regression. J. Flood Risk Manag. 2019, 12, e12522. [Google Scholar] [CrossRef]
- Yan, J.; Jin, J.; Chen, F.; Yu, G.; Yin, H.; Wang, W. Urban flash flood forecast using support vector machine and numerical simulation. J. Hydroinformatics 2018, 20, 221–231. [Google Scholar] [CrossRef]
- Sadler, J.M.; Goodall, J.L.; Morsy, M.M.; Spencer, K. Modeling urban coastal flood severity from crowd-sourced flood reports using Poisson regression and Random Forest. J. Hydrol. 2018, 559, 43–55. [Google Scholar] [CrossRef]
- Lin, J.; He, X.; Lu, S.; Liu, D.; He, P. Investigating the influence of three-dimensional building configuration on urban pluvial flooding using random forest algorithm. Environ. Res. 2021, 196, 110438. [Google Scholar] [CrossRef]
- Wu, Z.; Zhou, Y.; Wang, H.; Jiang, Z. Depth prediction of urban flood under different rainfall return periods based on deep learning and data warehouse. Sci. Total Environ. 2020, 716, 137077. [Google Scholar] [CrossRef]
- Yang, F.; Ding, W.; Zhao, J.; Song, L.; Yang, D.; Li, X. Rapid urban flood inundation forecasting using a physics-informed deep learning approach. J. Hydrol. 2024, 643, 131998. [Google Scholar] [CrossRef]
- Le, X.H.; Nguyen, D.H.; Jung, S.; Yeon, M.; Lee, G. Comparison of deep learning techniques for river streamflow forecasting. IEEE Access 2021, 9, 71805–71820. [Google Scholar] [CrossRef]
- Ye, C.; Xu, Z.; Lei, X.; Zhang, R.; Chu, Q.; Li, P.; Ban, C. Assessment of the impact of urban water system scheduling on urban flooding by using coupled hydrological and hydrodynamic model in Fuzhou City, China. J. Environ. Manag. 2022, 321, 115935. [Google Scholar] [CrossRef]
- Gupta, A.; Govindaraju, R.S. Propagation of structural uncertainty in watershed hydrologic models. J. Hydrol. 2019, 575, 66–81. [Google Scholar] [CrossRef]
- Knoben, W.J.; Freer, J.E.; Peel, M.C.; Fowler, K.J.A.; Woods, R.A. A brief analysis of conceptual model structure uncertainty using 36 models and 559 catchments. Water Resour. Res. 2020, 56, e2019WR025975. [Google Scholar] [CrossRef]
- Chenlei, Y.E.; Zongxue, X.U.; Weihong, L.I.A.O.; Xinyi, S.H.U.; Ruting, L.I.A.O. Urban pluvial flooding process: Semi-distributed tank model and river flood simulation. J. Beijing Norm. Univ. Nat. Sci. 2024, 60, 667–680. [Google Scholar]
- Yang, S.; Yang, D.; Chen, J.; Zhao, B. Real-time reservoir operation using recurrent neural networks and inflow forecast from a distributed hydrological model. J. Hydrol. 2019, 579, 124229. [Google Scholar] [CrossRef]
- Liang, Y.; Liao, W.; Zhang, Z.; Li, H.; Wang, H. Using a multiphysics coupling-oriented flood modelling approach to assess urban flooding under various regulation scenarios combined with rainstorms and tidal effects. J. Hydrol. 2024, 645, 132189. [Google Scholar] [CrossRef]
- Huang, H.; Lei, X.; Liao, W.; Liu, D.; Wang, H. A hydrodynamic-machine learning coupled (HMC) model of real-time urban flood in a seasonal river basin using mechanism-assisted temporal cross-correlation (MTC) for space decoupling. J. Hydrol. 2023, 624, 129826. [Google Scholar] [CrossRef]
- Rasool, U.; Yin, X.; Xu, Z.; Rasool, M.A.; Hussain, M.; Siddique, J.; Hai, N.T. Quantifying pluvial flood simulation in ungauged urban area; A case study of 2022 unprecedented pluvial flood in Karachi, Pakistan. J. Hydrol. 2025, 655, 132905. [Google Scholar] [CrossRef]
Data Type | Abbreviation | Source |
---|---|---|
Designed event-based rainfall | DER | Design Rainfall Intensity Formula [49] |
Observed event-based rainfall | OER | Measured data provided by Hydrology Bureau of Fuzhou |
Typical event-based rainfall | TER | Locally designed rainfall patterns provided by Hydrology Bureau of Fuzhou |
Classical event-based rainfall | CER | Seven classic rainfall patterns [50] |
Synthetic event-based rainfall | SER | Generated by GAN |
Network Layer | Output Dimension | Parameter Numbers |
---|---|---|
Input layer | None, 145, 4 | 0 |
LSTM layer | None, 145, 50 | 11,000 |
LSTM layer | None, 145, 50 | 11,000 |
Self-attention layer | None, 50 | 195 |
Fully connected layer | None, 145 | 7395 |
Model | Network Layer | Output Dimension | Parameter Numbers |
---|---|---|---|
B-LSTM | Bidirection | None, 40 | 4000 |
Dense | None, 145 | 5945 | |
BS-LSTM | Bidirection | None, 40 | 4000 |
Bidirection | None, 40 | 4000 | |
Dense | None, 145 | 5945 | |
A-LSTM | InputLayer | None, 145, 4 | 0 |
LSTM | None, 100 | 3280 | |
Dot | None, 145, 100 | 0 | |
Activation | None, 145, 100 | 80,400 | |
BatchNormalization-5 | None, 145 | 80 | |
Dense | None, 145 | 3200 | |
ED-LSTM | InputLayer | None, 145, 4 | 0 |
LSTM | None, 100 | 0 | |
RepeatVector | None, 145, 100 | 0 | |
LSTM | None, 145, 100 | 80,400 | |
TimeDistributed | None, 145, 2 | 202 | |
EDA-LSTM | InputLayer | None, 145, 4 | 0 |
LSTM | None, 145, 20 | 0 | |
BatchNormalization-3 | None, 20 | 80 | |
RepeatVector | None, 145, 20 | 0 | |
BatchNormalization-4 | None, 20 | 80 | |
LSTM | None, 145, 20 | 3280 | |
Dot | None, 145, 20 | 0 | |
Activation | None, 145, 145 | 0 | |
Dot | None, 145, 20 | 0 | |
BatchNormalization-5 | None, 145, 20 | 80 | |
Concatenate | None, 145, 40 | 0 | |
TimeDistributed | None, 145, 2 | 82 |
Model Structure | MAE | MSE | MSLE | RMSE |
---|---|---|---|---|
B-LSTM | 0.024 | 0.002 | 0.0020 | 0.050 |
BS-LSTM | 0.016 | 0.001 | 0.0007 | 0.033 |
A-LSTM | 0.043 | 0.006 | 0.003 | 0.078 |
ED-LSTM | 0.067 | 0.014 | 0.008 | 0.119 |
EDA-LSTM | 0.065 | 0.011 | 0.007 | 0.100 |
Model Structure | MAE | MSE | MSLE | RMSE |
---|---|---|---|---|
B-LSTM | 0.019 | 0.002 | 0.0010 | 0.039 |
BS-LSTM | 0.014 | 0.001 | 0.0006 | 0.032 |
A-LSTM | 0.034 | 0.004 | 0.0030 | 0.072 |
ED-LSTM | 0.056 | 0.012 | 0.007 | 0.110 |
EDA-LSTM | 0.054 | 0.008 | 0.006 | 0.096 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Ye, C.; Xu, Z.; Liao, W.; Li, X.; Shu, X. Capturing Urban Pluvial River Flooding Features Based on the Fusion of Physically Based and Data-Driven Approaches. Sustainability 2025, 17, 2524. https://doi.org/10.3390/su17062524
Ye C, Xu Z, Liao W, Li X, Shu X. Capturing Urban Pluvial River Flooding Features Based on the Fusion of Physically Based and Data-Driven Approaches. Sustainability. 2025; 17(6):2524. https://doi.org/10.3390/su17062524
Chicago/Turabian StyleYe, Chenlei, Zongxue Xu, Weihong Liao, Xiaoyan Li, and Xinyi Shu. 2025. "Capturing Urban Pluvial River Flooding Features Based on the Fusion of Physically Based and Data-Driven Approaches" Sustainability 17, no. 6: 2524. https://doi.org/10.3390/su17062524
APA StyleYe, C., Xu, Z., Liao, W., Li, X., & Shu, X. (2025). Capturing Urban Pluvial River Flooding Features Based on the Fusion of Physically Based and Data-Driven Approaches. Sustainability, 17(6), 2524. https://doi.org/10.3390/su17062524