Data-driven rapid flood prediction mapping with catchment generalizability

Guo, Zifeng; Moosavi, Vahid; Leitão, João P.

doi:10.1016/j.jhydrol.2022.127726

Cited by 41 publications

(33 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data-driven model does not need to consider the physical mechanism. Through the analysis of time series, it can capture the nonlinear relationship between driving factors and runoff, which can avoid the influence of subjective factors on the uncertainty of the model [ 19 ]. Time series prediction models such as Back Propagation (BP) [ 20 ], Long Short-Term Memory (LSTM) [ 21 ] and Gated Recurrent Unit (GRU) [ 22 ] have been successfully applied to the study of runoff prediction.…”

Section: Introductionmentioning

confidence: 99%

Improved runoff forecasting based on time-varying model averaging method and deep learning

et al. 2022

View full text Add to dashboard Cite

In order to improve the accuracy and stability of runoff prediction. This study proposed a dynamic model averaging method with Time-varying weight (TV-DMA). Using this method, an integrated prediction model framework for runoff prediction was constructed. The framework determines the main variables suitable for runoff prediction through correlation analysis, and uses TV-DMA and deep learning algorithm to construct an integrated prediction model for runoff. The results demonstrate that the current monthly runoff, the runoff of the previous month, the current monthly temperature, the temperature of the previous month and the current monthly rainfall were the variables suitable for runoff prediction. The results of runoff prediction show that the TV-DMA model has the highest prediction accuracy (with 0.97 Nash-efficiency coefficient (NSE)) and low uncertainty. The interval band of uncertainty was 33.3%-65.5% lower than single model. And the prediction performance of the single model and TV-DMA model in flood season is obviously lower than that in non-flood season. In addition, this study indicate that the current monthly runoff, rainfall and temperature are the important factor affecting the runoff prediction, which should be paid special attention in the runoff prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

Improved runoff forecasting based on time-varying model averaging method and deep learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This study adopted the U-Net architecture (Ronneberger et al, 2015) as shown in Figure 2. The U-Net architecture showed a good performance to predict water depth in the literature (Löwe et al, 2021;Guo et al, 2022). The model input is a terrain raster with 13 image channels (13 channels represent the predictive features ) and the output is the resulting water depth at the surface.…”

Section: U-netmentioning

confidence: 99%

“…CNNs have recently demonstrated the potential to map urban pluvial flood susceptibility (Zhao et al, 2020(Zhao et al, , 2021Seleem et al, 2022) and flood hazard (Löwe et al, 2021;Guo et al, 2022).They are designed to extract spatial information from the input data and to handle image (raster) data without an unwarranted growth in the model complexity. Löwe et al (2021) trained a CNN model based on the U-Net architecture (Ronneberger et al, 2015) to predict urban pluvial flood water depth.…”

mentioning

confidence: 99%

“…The testing areas were close to or surrounded by training areas which guaranteed that the testing dataset had minimal diversity from the training dataset. Guo et al (2022) used four topographic predictive features and one precipitation event to train a CNN model. The model performed well outside the training domain for the same precipitation event used to train the model.…”

mentioning

confidence: 99%

“…A data-driven model that generalizes outside the training domain is still a major challenge in literature (Bentivoglio et al, 2022). While previous studies tried to examine the transferability of CNN in space to predict flood water depth under certain limitations (Löwe et al, 2021;Guo et al, 2022) and use transfer learning techniques to improve the CNN performance outside the training domain to map flood susceptibility (Zhao et al, 2021), such efforts have been examined neither for RF models nor for surrogates of physical numerical 2D hydrodynamic models. It is not obvious how transfer learning techniques could improve the data-driven model performance and be a useful tool to overcome the limitations of applying computationally expensive 2D hydrodynamic models to a big region.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany

Seleem

Ayzel

Bronstert

et al. 2022

Preprint

View full text Add to dashboard Cite

Abstract. Data-driven models have been recently suggested to surrogate computationally expensive hydrodynamic models to map flood hazards. However, most studies focused on developing models for the same area or the same precipitation event. It is hence not obvious how transferable the models are in space. This study evaluates the performance of a convolutional neural network (CNN) based on the U-Net architecture and the random forest (RF) algorithm to predict flood water depth, the models' transferability in space and performance improvement using transfer learning techniques. We used three study areas in Berlin to train, validate and test the models. The results showed that (1) the RF models outperformed the CNN models for predictions within the training domain, presumable at the cost of overfitting; (2) the CNN models had significantly higher potential than the RF models to generalize beyond the training domain; and (3) the CNN models could better benefit from transfer learning technique to boost their performance outside training domains than RF models.

show abstract

A coordinated drainage and regulation model of urban water systems in China: A case study in Fuzhou city

Wang

Lei

Wang

et al. 2023

River

View full text Add to dashboard Cite

Extreme climate and urbanization lead to frequent urban floods, and urban water system dispatching is an important means of urban flood control. A coupled model is proposed to simulate urban floods in real-time and achieve comprehensive water system control for urban floods. First, the systematical description of coordinated drainage and regulation model of urban water systems in China is introduced, then the practice of Fuzhou city was taken as an example to introduce the prediction and forecast systems, as well as water system regulation for urban flood and waterlogging disaster in detail. Results show that the root-mean-square error of river flood prediction is less than 0.3 and that the calculation time of waterlogging simulation is less than 10 min; the optimization regulation reduces the peak river water level by 31 cm. This study will establish a novel urban water system management model to help urban managers better reduce the loss caused by urban floods.

show abstract

Data-driven rapid flood prediction mapping with catchment generalizability

Cited by 41 publications

References 36 publications

Improved runoff forecasting based on time-varying model averaging method and deep learning

Improved runoff forecasting based on time-varying model averaging method and deep learning

Transferability of data-driven models to predict urban pluvial flood water depth in Berlin, Germany

A coordinated drainage and regulation model of urban water systems in China: A case study in Fuzhou city

Contact Info

Product

Resources

About