Regional flood inundation nowcast using hybrid SOM and dynamic neural networks

Flash flood warnings using the ensemble precipitation forecasting technique: A case study on forecasting floods in Taiwan caused by typhoons

. Various types of artificial neural networks (ANNs) have been successfully applied in hydrological fields, but relatively scant on multistep-ahead flood inundation forecasting, which is very difficult to achieve, especially when dealing with forecasts without regular observed data. This study proposes a recurrent configuration of nonlinear autoregressive with exogenous inputs (NARX) network, called R-NARX, to forecast multistep-ahead inundation depths in an inundation area. The proposed R-NARX is constructed based on the recurrent neural network (RNN), which is commonly used for modeling nonlinear dynamical systems. The models were trained and tested based on a large number of inundation data generated by a well validated two-dimensional simulation model at thirteen inundation-prone sites in Yilan County, Taiwan. We demonstrate that the R-NARX model can effectively inhibit error growth and accumulation when being applied to online multistep-ahead inundation forecasts over a long lasting forecast period. For comparison, a feedforward time-delay and an online feedback configuration of NARX networks (T-NARX and O-NARX) were performed. The results show that (1) T-NARX networks cannot make online forecasts due to unavailable inputs in the constructed networks even though they provide the best performances for reference only; and (2) R-NARX networks consistently outperform O-NARX networks and can be adequately applied to online multistep-ahead forecasts of inundation depths in the study area during typhoon events.

/pdf/online-multistep-ahead-inundation-depth-forecasts-by-2c0idji4o7.pdf

Online multistep-ahead inundation depth forecasts by recurrent NARX networks

An integrated two-stage support vector machine approach to forecast inundation maps during typhoons

Runoff discharge in the Tuku lowlands, Taiwan, has increased with land development. Frequent floods caused by extreme weather conditions have resulted in considerable economic and social losses in recent years. Currently, numerous infrastructures have been built in the lowland areas that are prone to inundation; the measures and solutions for flood mitigation focus mainly on engineering aspects. Public participation in the development of principles for future flood management has helped both stakeholders and engineers. An integrated drainage–inundation model, combining a drainage flow model with a two-dimensional overland-flow inundation model is used to evaluate the flood management approaches with damage loss estimation. The proposed approaches include increasing drainage capacity, using fishponds as retention ponds, constructing pumping stations, and building flood diversion culverts. To assess the effects on the drainage system of projected increase of rainfall due to climate change, for each ...

https://www.tandfonline.com/doi/pdf/10.1080/02626667.2013.836276

Improvement of a drainage system for flood management with assessment of the potential effects of climate change

. This study attempts to achieve real-time rainfall-inundation forecasting in lowland regions, based on a synthetic potential inundation database. With the principal component analysis and a feed-forward neural network, a rainfall-inundation hybrid neural network (RiHNN) is proposed to forecast 1-h-ahead inundation depth as hydrographs at specific representative locations using spatial rainfall intensities and accumulations. A systematic procedure is presented to construct the RiHNN, which combines the merits of detailed hydraulic modeling in flood-prone lowlands via a two-dimensional overland-flow model and time-saving calculation in a real-time rainfall-inundation forecasting via ANN model. Analytical results from the RiHNNs with various principal components indicate that the RiHNNs with fewer weights can have about the same performance as a feed-forward neural network. The RiHNNs evaluated through four types of real/synthetic rainfall events also show to fit inundation-depth hydrographs well with high rainfall. Moreover, the results of real-time rainfall-inundation forecasting help the emergency manager set operational responses, which are beneficial for flood warning preparations.

/pdf/hybrid-neural-networks-in-rainfall-inundation-forecasting-59rkhxm77c.pdf

K.-C. Chang

Papers

Hybrid neural networks in rainfall-inundation forecasting based on a synthetic potential inundation database