A real-time flow forecasting with deep convolutional generative adversarial network: Application to flooding event in Denmark

Real-time flood forecasting is crucial for supporting emergency responses to inundation-prone regions. Due to uncertainties in the future (e.g., meteorological conditions and model parameter inputs), it is challenging to make accurate forecasts of spatiotemporal floods. In this paper, a real-time pr...

Full description

Saved in:
Bibliographic Details
Published in:Physics of fluids (1994) 2021-05, Vol.33 (5)
Main Authors: Navon, I. M., Pain, C. C.
Format: Article
Language:English
Subjects:
100 year floods
Artificial neural networks
Computational fluid dynamics
Correlation coefficients
Emergency response
Flood forecasting
Flood predictions
Flooding
Floods
Flow distribution
Fluid dynamics
Fluid flow
Forecasting
Generative adversarial networks
Lead time
Mathematical models
Physics
Real time
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Real-time flood forecasting is crucial for supporting emergency responses to inundation-prone regions. Due to uncertainties in the future (e.g., meteorological conditions and model parameter inputs), it is challenging to make accurate forecasts of spatiotemporal floods. In this paper, a real-time predictive deep convolutional generative adversarial network (DCGAN) is developed for flooding forecasting. The proposed methodology consists of a two-stage process: (1) dynamic flow learning and (2) real-time forecasting. In dynamic flow learning, the deep convolutional neural networks are trained to capture the underlying flow patterns of spatiotemporal flow fields. In real-time forecasting, the DCGAN adopts a cascade predictive procedure. The last one-time step-ahead forecast from the DCGAN can act as a new input for the next time step-ahead forecast, which forms a long lead-time forecast in a recursive way. The model capability is assessed using a 100-year return period extreme flood event occurred in Greve, Denmark. The results indicate that the predictive fluid flows from the DCGAN and the high fidelity model are in a good agreement (the correlation coefficient ≥ 97 % and the mean absolute error ≤ 0.008   m) for a lead-900 time step forecast. This is an important step toward real-time flow forecasting although further evaluation of the DCGAN performance is required in complex realistic cases in the future.
ISSN:1070-6631
1089-7666
DOI:10.1063/5.0051213