Application of tank,NAM, ARMA and neural network models to flood forecasting

Two lumped conceptual hydrological models, namely tank and NAM and a neural network model are applied to flood forecasting in two river basins in Thailand, the Wichianburi on the Pasak River and the Tha Wang Pha on the Nan River using the flood forecasting procedure developed in this study. The tank and NAM models were calibrated and verified and found to give similar results. The results were found to improve significantly by coupling stochastic and deterministic models (tank and NAM) for updating forecast output. The neural network (NN) model was compared with the tank and NAM models. The NN model does not require knowledge of catchment characteristics and internal hydrological processes. The training process or calibration is relatively simple and less time consuming compared with the extensive calibration effort required by the tank and NAM models. The NN model gives good forecasts based on available rainfall, evaporation and runoff data. The black‐box nature of the NN model and the need for selecting parameters based on trial and error or rule‐of‐thumb, however, characterizes its inherent weakness. The performance of the three models was evaluated statistically. Copyright © 2000 John Wiley & Sons, Ltd.     

Application of an artificial neural network to typhoon rainfall forecasting

A neural network with two hidden layers is developed to forecast typhoon rainfall. First, the model configuration is evaluated using eight typhoon characteristics. The forecasts for two typhoons based on only the typhoon characteristics are capable of showing the trend of rainfall when a typhoon is nearby. Furthermore, the influence of spatial rainfall information on rainfall forecasting is considered for improving the model design. A semivariogram is also applied to determine the required number of nearby rain gauges whose rainfall information will be used as input to the model. With the typhoon characteristics and the spatial rainfall information as input to the model, the forecasting model can produce reasonable forecasts. It is also found that too much spatial rainfall information cannot improve the generalization ability of the model, because the inclusion of irrelevant information adds noise to the network and undermines the performance of the network. Copyright © 2005 John Wiley & Sons, Ltd.     

Enforced self‐organizing map neural networks for river flood forecasting

Self‐organizing maps (SOMs) have been successfully accepted widely in science and engineering problems; not only are their results unbiased, but they can also be visualized. In this study, we propose an enforced SOM (ESOM) coupled with a linear regression output layer for flood forecasting. The ESOM re‐executes a few extra training patterns, e.g. the peak flow, as recycling input data increases the mapping space of peak flow in the topological structure of SOM, and the weighted sum of the extended output layer of the network improves the accuracy of forecasting peak flow. We have investigated an ESOM neural network by using the flood data of the Da‐Chia River, Taiwan, and evaluated its performance based on the results obtained from a commonly used back‐propagation neural network. The results demonstrate that the ESOM neural network has great efficiency for clustering, especially for the peak flow, and super capability of modelling the flood forecast. The topology maps created from the ESOM are interesting and informative. Copyright © 2007 John Wiley & Sons, Ltd.     

Classified real-time flood forecasting by coupling fuzzy clustering and neural network

This paper presented a new classified real-time flood forecasting framework by integrating a fuzzy clustering model and neural network with a conceptual hydrological model. A fuzzy clustering model was used to classify historical floods in terms of flood peak and runoff depth, and the conceptual hydrological model was calibrated for each class of floods. A back-propagation (BP) neural network was trained by using real-time rainfall data and outputs from the fuzzy clustering model. BP neural network provided a rapid on-line classification for real-time flood events. Based on the on-line classification, an appropriate parameter set of hydrological model was automatically chosen to produce real-time flood forecasting. Different parameter sets was continuously used in the flood forecasting process because of the changes of real-time rainfall data and on-line classification results. The proposed methodology was applied to a large catchment in Liaoning province, China. Results show that the classified framework provided a more accurate prediction than the traditional non-classified method. Furthermore, the effects of different index weights in fuzzy clustering were also discussed.     

Distributed rainfall‐runoff modelling for flood frequency estimation and flood forecasting

Nowadays, in the scientific literature many rainfall‐runoff (RR) models are available ranging from simpler ones, with a limited number of parameters, to highly complex ones, with many parameters. Therefore, the selection of the best structure and parameterisation for a model is not straightforward as it is dependent on a number of factors: climatic conditions, catchment characteristics, temporal and spatial resolution, model objectives, etc. In this study, the structure of a continuous semi‐distributed RR model, named MISDc (‘Modello Idrologico Semi‐Distribuito in continuo’) developed for flood simulation in the Upper Tiber River (central Italy) is presented. Most notably, the methodology employed to detect the more relevant processes involved in the modelling of high floods, and hence, to build the model structure and its parameters, is developed. For this purpose, an intense activity of monitoring soil moisture and runoff in experimental catchments was carried out allowing to derive a parsimonious and reliable continuous RR model operating at an hourly (or smaller) time scale. Specifically, in order to determine the catchment hydrological response, the important role of the antecedent wetness conditions is emphasized. The application of MISDc both for design flood estimation and for flood forecasting is reported here demonstrating its reliability and also its computational efficiency, another important factor in hydrological practice. As far as the flood forecasting applications are concerned, only the accuracy of the model in reproducing discharge hydrographs by assuming rainfall correctly known throughout the event is investigated indepth. In particular, the MISDc has been implemented in the framework of Civil Protection activities for the Upper Tiber River basin. Copyright © 2011 John Wiley & Sons, Ltd.     

Uncertainties in real‐time flood forecasting with neural networks

Although artificial neural networks (ANNs) have been applied in rainfall runoff modelling for many years, there are still many important issues unsolved that have prevented this powerful non‐linear tool from wide applications in operational flood forecasting activities. This paper describes three ANN configurations and it is found that a dedicated ANN for each lead‐time step has the best performance and a multiple output form has the worst result. The most popular form with multiple inputs and single output has the average performance. In comparison with a linear transfer function (TF) model, it is found that ANN models are uncompetitive against the TF model in short‐range predictions and should not be used in operational flood forecasting owing to their complicated calibration process. For longer range predictions, ANN models have an improved chance to perform better than the TF model; however, this is highly dependent on the training data arrangement and there are undesirable uncertainties involved, as demonstrated by bootstrap analysis in the study. To tackle the uncertainty issue, two novel approaches are proposed: distance analysis and response analysis. Instead of discarding the training data after the model's calibration, the data should be retained as an integral part of the model during its prediction stage and the uncertainty for each prediction could be judged in real time by measuring the distances against the training data. The response analysis is based on an extension of the traditional unit hydrograph concept and has a very useful potential to reveal the hydrological characteristics of ANN models, hence improving user confidence in using them in real time. Copyright © 2006 John Wiley & Sons, Ltd.     

Evaluation of four hydrological models for operational flood forecasting in a Canadian Prairie watershed

The complexities of the Prairie watersheds, including potholes, drainage interconnectivities, changing land-use patterns, dynamic watershed boundaries and hydro-meteorological factors, have made hydrological modelling on Prairie watersheds one of the most complex task for hydrologists and operational hydrological forecasters. In this study, four hydrological models (WATFLOOD, HBV-EC, HSPF and HEC-HMS) were developed, calibrated and tested for their efficiency and accuracy to be used as operational flood forecasting tools. The Upper Assiniboine River, which flows into the Shellmouth Reservoir, Canada, was selected for the analysis. The performance of the models was evaluated by the standard statistical methods: the Nash-Sutcliffe efficiency coefficient, correlation coefficient, root mean squared error, mean absolute relative error and deviation of runoff volumes. The models were evaluated on their accuracy in simulating the observed runoff for calibration and verification periods (2005–2015 and 1994–2004, respectively) and also their use in operational forecasting of the 2016 and 2017 runoff.     

Quantifying hydrological budgets and pathways in a small upland catchment using a combined modelling and tracer approach

Hydrological budgets and flow pathways have been quantified for a small upland catchment (1.76 km²) in the northeast of Scotland. Water balance calculations for four subcatchments identified spatial variability within the catchment, with an estimated runoff enhancement of up to 25% for the upper western area, compared with the rest of the catchment. Data from spatial hydrochemical sampling, over a range of flow conditions, were used to identify the principal hillslope runoff mechanisms within the catchment. A hydrochemical mixing analysis revealed that runoff emerging from springs in various locations of the hillslope accounted for a significant proportion of flow in the streams, even during storm events. A hydrological model of the catchment was calibrated using the calculated stream flows for four locations, together with results from the mixing analysis for different time points. The calibrated model was used to predict the temporal variability in contributions to stream flow from the hillslope springs and soil water flows. The overall split ranged from 57%:43% spring water:soil water in the upper eastern subcatchment, to 76%:24% in the upper western subcatchment. Copyright © 2006 John Wiley & Sons, Ltd.     

A comparison of one‐ and two‐dimensional approaches to modelling flood inundation over complex upland floodplains

A much understudied aspect of flood inundation is examined, i.e. upland environments with topographically complex floodplains. Although the presence of high‐resolution topographic data (e.g. lidar) has improved the quality of river flood inundation predictions, the optimum dimensionality of hydraulic models for this purpose has yet to be fully evaluated for situations of both topographic and topological (i.e. the connectivity of floodplain features) complexity. In this paper, we present the comparison of three treatments of upland flood inundation using: (a) a one‐dimensional (1D) model (HEC‐RAS v. 3·1·2) with the domain defined as series of extended cross‐sections; (b) the same 1D model, but with the floodplain defined by a series of storage cells, hydraulically connected to the main river channel and other storage cells on the floodplain according to floodplain topological characteristics; (c) a two‐dimensional (2D) diffusion wave treatment, again with explicit representation of floodplain structural features. The necessary topographic and topological data were derived using lidar and Ordnance Survey Landline data. The three models were tested on a 6 km upland reach of the River Wharfe, UK. The models were assessed by comparison with measured inundation extent. The results showed that both the extended cross‐section and the storage cell 1D modes were conceptually problematic. They also resulted in poorer model predictions, requiring incorrect parameterization of the main river to floodplain flux in order to approach anything like the level of agreement observed when the 2D diffusion wave treatment was assessed. We conclude that a coupled 1D–2D treatment is likely to provide the best modelling approach, with currently available technology, for complex floodplain configurations. Copyright © 2007 John Wiley & Sons, Ltd.     

An integrated approach of flash flood analysis in ungauged Mediterranean watersheds using post-flood surveys and unmanned aerial vehicles

This study analyzes the flash flood event of two ungauged ephemeral streams in Olympiada region (Chalkidiki, North Greece), which occurred at the 21–22 of November 2019. Aim of the study is to reconstruct the specific flash flood event, investigate the causes of flood generation mechanisms, evaluate the performance of SCS-CN hydrological and HEC-RAS hydraulic models, investigate the relation between extreme flash floods and human intervention, using the combination of ground and aerial observations obtained from the field survey and unmanned aerial vehicles (UAVs), respectively. The results of the specific discharge ranged between 9 and 11 m³ s⁻¹ km², values that are typical for flash flood events in Mediterranean region. The comparison between the observed and simulated values of flood extent showed sufficiently good performance of the hydraulic model (CSI = 82%). However, the statistical analysis of the observed and simulated flood depths displayed a flood depth overestimation by the applied model, despite that the values of the used statistic indexes are acceptable (RMSE = 0.35 m, SD = 0.53, NSE = 0.56, PBIAS = 11.26%). The model overestimation of flood depth was attributed to the DEM low resolution and quality. Ground and aerial observations depicted the alluvial fan activation, the alternation of flow paths and the huge sediment transport. Human intervention in main streams, urban sprawl, wet AMC and sediment transport were among the main factors that contributed to the flash flood generation. This integrated approach revealed the necessity of the constant evaluation and validation of hydrological and hydraulic models in small ungauged Mediterranean watersheds and ephemeral streams. The use of UAVs in combination with ground observations and hydraulic simulation could significantly contribute to the enhanced understanding of flash flood mechanisms, in the direction of flood risk mitigation, improvement of the planning efficiency of flood prevent measures, flood hazard estimation, evolution of flood warning systems and floodplain geomorphology analysis.     

Natural flood management,land use and climate change trade-offs: the case of Tarland catchment,Scotland

A distributed hydrological model (WaSiM-ETH) was applied to a mesoscale catchment to investigate natural flood management as a nonstructural approach to tackle flood risks from climate change. Peak flows were modelled using climate projections (UKCP09) combined with afforestation-based land-use change options. A significant increase in peak flows was modelled from climate change. Afforestation could reduce some of the increased flow, with greatest benefit from coniferous afforestation, especially replacing lowland farmland. Nevertheless, large-scale woodland expansion was required to maintain peak flows similar to present and beneficial effects were significantly reduced for larger “winter-type” extreme floods. Afforestation was also modelled to increase low-flow risks. Land-use scenarios showed catchment-scale trade-offs across multiple objectives meant “optimal” flood risk solutions were unlikely, especially for afforestation replacing lowland farmland. Hence, combined structural/nonstructural measures may be required in such situations, with integrated catchment management to synergize multiple objectives.     

A modelling framework for evaluation of the hydrological impacts of nature‐based approaches to flood risk management,with application to in‐channel interventions across a 29‐km2 scale catchment in the United Kingdom

Nature‐based approaches to flood risk management are increasing in popularity. Evidence for the effectiveness at the catchment scale of such spatially distributed upstream measures is inconclusive. However, it also remains an open question whether, under certain conditions, the individual impacts of a collection of flood mitigation interventions could combine to produce a detrimental effect on runoff response. A modelling framework is presented for evaluation of the impacts of hillslope and in‐channel natural flood management interventions. It couples an existing semidistributed hydrological model with a new, spatially explicit, hydraulic channel network routing model. The model is applied to assess a potential flood mitigation scheme in an agricultural catchment in North Yorkshire, United Kingdom, comprising various configurations of a single variety of in‐channel feature. The hydrological model is used to generate subsurface and surface fluxes for a flood event in 2012. The network routing model is then applied to evaluate the response to the addition of up to 59 features. Additional channel and floodplain storage of approximately 70,000 m³ is seen with a reduction of around 11% in peak discharge. Although this might be sufficient to reduce flooding in moderate events, it is inadequate to prevent flooding in the double‐peaked storm of the magnitude that caused damage within the catchment in 2012. Some strategies using features specific to this catchment are suggested in order to improve the attenuation that could be achieved by applying a nature‐based approach.     

Artificial neural networks as an alternative approach to groundwater numerical modelling and environmental design

Classical optimization methodologies based on mathematical theories have been developed for the solution of various constrained environmental design problems. Numerical models have been widely used to represent an environmental system accurately. The use of methodologies such as artificial neural networks (ANNs), which approximate the complicated behaviour and response of physical systems, allows the optimization of a large number of case scenarios with different set of constraints within a short period of time, whereas the corresponding simulation time using a numerical model would be prohibitive. In this paper, a combination of an ANN with a differential evolution algorithm is proposed to replace the classical finite‐element numerical model in water resources management problems. The objective of the optimization problem is to determine the optimal operational strategy for the productive pumping wells located in the northern part of Rhodes Island in Greece, to cover the water demand and maintain the water table at certain levels. The conclusions of this study show that the use of ANN as an approximation model could (a) significantly reduce the computational burden associated with the accurate simulation of complex physical systems and (b) provide solutions very close to the optimal ones for various constrained environmental design problems. Copyright © 2008 John Wiley & Sons, Ltd.     

The data‐driven approach as an operational real‐time flood forecasting model

Accurate water level forecasts are essential for flood warning. This study adopts a data‐driven approach based on the adaptive network–based fuzzy inference system (ANFIS) to forecast the daily water levels of the Lower Mekong River at Pakse, Lao People's Democratic Republic. ANFIS is a hybrid system combining fuzzy inference system and artificial neural networks. Five ANFIS models were developed to provide water level forecasts from 1 to 5 days ahead, respectively. The results show that although ANFIS forecasts of water levels up to three lead days satisfied the benchmark, four‐ and five‐lead‐day forecasts were only slightly better in performance compared with the currently adopted operational model. This limitation is imposed by the auto‐ and cross‐correlations of the water level time series. Output updating procedures based on the autoregressive (AR) and recursive AR (RAR) models were used to enhance ANFIS model outputs. The RAR model performed better than the AR model. In addition, a partial recursive procedure that reduced the number of recursive steps when applying the AR or the RAR model for multi‐step‐ahead error prediction was superior to the fully recursive procedure. The RAR‐based partial recursive updating procedure significantly improved three‐, four‐ and five‐lead‐day forecasts. Our study further shows that for long lead times, ANFIS model errors are dominated by lag time errors. Although the ANFIS model with the RAR‐based partial recursive updating procedure provided the best results, this method was able to reduce the lag time errors significantly for the falling limbs only. Improvements for the rising limbs were modest. Copyright © 2011 John Wiley & Sons, Ltd.     

Application of integrated back‐propagation network and self organizing map for flood forecasting

Much of the nonlinearity and uncertainty regarding the flood process is because hydrologic data required for estimation are often tremendously difficult to obtain. This study employed a back‐propagation network (BPN) as the main structure in flood forecasting to learn and to demonstrate the sophisticated nonlinear mapping relationship. However, a deterministic BPN model implies high uncertainty and poor consistency for verification work even when the learning performance is satisfactory for flood forecasting. Therefore, a novel procedure was proposed in this investigation which integrates linear transfer function (LTF) and self‐organizing map (SOM) to efficiently determine the intervals of weights and biases of a flood forecasting neural network to avoid the above problems. A SOM network with classification ability was applied to the solutions and parameters of the BPN model in the learning stage, to classify the network parameter rules and to obtain the winning parameters. The outcomes from the previous stage were then used as the ranges of the parameters in the recall stage. Finally, a case study was carried out in Wu‐Shi basin to demonstrate the effectiveness of the proposal. Copyright © 2009 John Wiley & Sons, Ltd.     

Wavelet regression model as an alternative to neural networks for monthly streamflow forecasting

The accuracy of the wavelet regression (WR) model in monthly streamflow forecasting is investigated in the study. The WR model is improved combining the two methods—the discrete wavelet transform (DWT) model and the linear regression (LR) model—for 1‐month‐ahead streamflow forecasting. In the first part of the study, the results of the WR model are compared with those of the single LR model. Monthly flow data from two stations, Gerdelli Station on Canakdere River and Isakoy Station on Goksudere River, in Eastern Black Sea region of Turkey are used in the study. The comparison results reveal that the WR model could increase the forecast accuracy of the LR model. In the second part of the study, the accuracy of the WR model is compared with those of the artificial neural networks (ANN) and auto‐regressive (AR) models. On the basis of the results, the WR is found to be better than the ANN and AR models in monthly streamflow forecasting. Copyright © 2009 John Wiley & Sons, Ltd.     

An experiment to gauge an ungauged catchment: rapid data assessment and eco-hydrological modelling in a data-scarce rural catchment

Abstract

We conducted a PUB (predictions in ungauged basins) experiment looking at hydrology and crop dynamics in the semi-arid rural Mod catchment in India. The experiment was motivated by the aims (a) to develop a coupled eco-hydrological model capable of analysing land-use strategies concerning crop water need, erosion protection, crop yield and resistivity against droughts and floods, and (b) to assess the feasibility of a strategy for collecting the necessary data in a data-scarce region. Our experiment combines parsimonious data assessment and eco-hydrological model coupling at the lower mesoscale. Linking bottom-up sampling of functionally representative soil classes and top-down regionalization based on spectral properties of the same resulted in a comprehensive distributed data basis for the model. A clear focus on the dominating processes and the catena as the organizing landscape element in the given environmental setting enabled this. We employed the WASA (Water Availability in Semi-Arid environments) model for uncalibrated process-based water balance modelling and integrated a crop simulation subroutine based on the SWAP (Soil Water Atmosphere Plant) model to account for crop dynamics, feedbacks and yield estimation. While we found the data assessment strategy and the hydrological model application largely feasible, in terms of its accounting for scale, processes and model concepts, the simulation of feedbacks with crops was problematic. Contributing to the PUB issue, more general conclusions are drawn concerning spatially-distributed structural information and uncalibrated modelling.

Editor Z.W. Kundzewicz; Associate editor F. Hattermann     

Probabilistic flood forecasting for a mountainous headwater catchment using a nonparametric stochastic dynamic approach

Abstract

Hydrological models are commonly used to perform real-time runoff forecasting for flood warning. Their application requires catchment characteristics and precipitation series that are not always available. An alternative approach is nonparametric modelling based only on runoff series. However, the following questions arise: Can nonparametric models show reliable forecasting? Can they perform as reliably as hydrological models? We performed probabilistic forecasting one, two and three hours ahead for a runoff series, with the aim of ascribing a probability density function to predicted discharge using time series analysis based on stochastic dynamics theory. The derived dynamic terms were compared to a hydrological model, LARSIM. Our procedure was able to forecast within 95% confidence interval 1-, 2- and 3-h ahead discharge probability functions with about 1.40 m³/s of range and relative errors (%) in the range [–30; 30]. The LARSIM model and the best nonparametric approaches gave similar results, but the range of relative errors was larger for the nonparametric approaches.

Editor D. Koutsoyiannis; Associate editor K. Hamed

Citation Costa, A.C., Bronstert, A. and Kneis, D., 2012. Probabilistic flood forecasting for a mountainous headwater catchment using a nonparametric stochastic dynamic approach. Hydrological Sciences Journal, 57 (1), 10–25.     

The strategy of building a flood forecast model by neuro‐fuzzy network

A methodology is proposed for constructing a flood forecast model using the adaptive neuro‐fuzzy inference system (ANFIS). This is based on a self‐organizing rule‐base generator, a feedforward network, and fuzzy control arithmetic. Given the rainfall‐runoff patterns, ANFIS could systematically and effectively construct flood forecast models. The precipitation and flow data sets of the Choshui River in central Taiwan are analysed to identify the useful input variables and then the forecasting model can be self‐constructed through ANFIS. The analysis results suggest that the persistent effect and upstream flow information are the key effects for modelling the flood forecast, and the watershed's average rainfall provides further information and enhances the accuracy of the model performance. For the purpose of comparison, the commonly used back‐propagation neural network (BPNN) is also examined. The forecast results demonstrate that ANFIS is superior to the BPNN, and ANFIS can effectively and reliably construct an accurate flood forecast model. Copyright © 2005 John Wiley & Sons, Ltd.