Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis

In this study, a new method of stand-alone short-term spring snowmelt river flood forecasting was developed based on wavelet and cross-wavelet analysis. Wavelet and cross-wavelet analysis were used to decompose flow and meteorological time series data and to develop wavelet based constituent components which were then used to forecast floods 1, 2, and 6 days ahead. The newly developed wavelet forecasting method (WT) was compared to multiple linear regression analysis (MLR), autoregressive integrated moving average analysis (ARIMA), and artificial neural network analysis (ANN) for forecasting daily stream flows with lead-times equal to 1, 2, and 6 days. This comparison was done using data from the Rideau River watershed in Ontario, Canada. Numerical analysis was performed on daily maximum stream flow data from the Rideau River station and on meteorological data (rainfall, snowfall, and snow on ground) from the Ottawa Airport weather station. Data from 1970 to 1997 were used to train the models while data from 1998 to 2001 were used to test the models. The most significant finding of this research was that it was demonstrated that the proposed wavelet based forecasting method can be used with great accuracy as a stand-alone forecasting method for 1 and 2 days lead-time river flood forecasting, assuming that there are no significant trends in the amplitude for the same Julian day year-to-year, and that there is a relatively stable phase shift between the flow and meteorological time series. The best forecasting model for 1 day lead-time was a wavelet analysis model. In testing, it had the lowest RMSE value (13.8229), the highest R² value (0.9753), and the highest EI value (0.9744). The best forecasting model for 2 days lead-time was also a wavelet analysis model. In testing, it had the lowest RMSE value (31.7985), the highest R² value (0.8461), and the second highest EI value (0.8410). It was also shown that the proposed wavelet based forecasting method is not particularly accurate for longer lead-time forecasting such as 6 days, with the ANN method providing more accurate results. The best forecasting model for 6 days lead-time was an ANN model, with the wavelet model not performing as well. In testing, the wavelet model had an RMSE of 57.6917, an R² of 0.4835, and an EI of 0.4366.     

Univariate streamflow forecasting using commonly used data-driven models: literature review and case study

Eight data-driven models and five data pre-processing methods were summarized; the multiple linear regression (MLR), artificial neural network (ANN) and wavelet decomposition (WD) models were then used in short-term streamflow forecasting at four stations in the East River basin, China. The wavelet–artificial neural network (W-ANN) method was used to predict 1-month-ahead monthly streamflow at Longchuan station (LS). The results indicate better performance of MLR and wavelet–multiple linear regression (W-MLR) in analysing the stationary trained dataset. Four models showed similar performance in 1-day-ahead streamflow forecasting, while W-MLR and W-ANN performed better in 5-day-ahead forecasting. Three reservoirs were shown to have more influence on downstream than upstream streamflow and models had the worst performance at Boluo station. Furthermore, the W-ANN model performed well for 1-month-ahead streamflow forecasting at LS with consideration of a deterministic component.     

On the relationship between hydrographs and chemographs

The spatial representativeness of gauging stations was investigated in two low‐mountainous river basins near the city of Trier, southwest Germany. Longitudinal profiles during low and high flow conditions were sampled in order to identify sources of solutes and to characterize the alteration of flood wave properties during its travel downstream. Numerous hydrographs and chemographs of natural flood events were analysed in detail. Additionally, artificial flood events were investigated to study in‐channel transport processes. During dry weather conditions the gauging station was only representative for a short river segment upstream, owing to discharge and solute concentrations of sources contiguous to the measurement site. During artificial flood events the kinematic wave velocity was considerably faster than the movement of water body and solutes, refuting the idea of a simple mixing process of individual runoff components. Depending on hydrological boundary conditions, the wave at a specific gauge could be entirely composed of old in‐channel water, which notably reduces the spatial representativeness of a sampling site. Natural flood events were characterized by a superimposition of local overland flow, riparian water and the kinematic wave process comprising the downstream conveyance of solutes. Summer floods in particular were marked by a chronological occurrence of distinct individual runoff components originating only from a few contributing areas adjacent to the stream and gauge. Thus, the representativeness of a gauge for processes in the whole basin depends on the distance of the nearest significant source to the station. The consequence of our study is that the assumptions of mixing models are not satisfied in river basins larger than 3 km². Copyright © 2006 John Wiley & Sons, Ltd.     

Stream flow forecasting using neuro‐wavelet technique

This paper proposes the application of a neuro‐wavelet technique for modelling monthly stream flows. The neuro‐wavelet model is improved by combining two methods, discrete wavelet transform and multi‐layer perceptron, for one‐month‐ahead stream flow forecasting and results are compared with those of the single multi‐layer perceptron (MLP), multi‐linear regression (MLR) and auto‐regressive (AR) models. Monthly flow data from two stations, Gerdelli Station on Canakdere River and Isakoy Station on Goksudere River, in the Eastern Black Sea region of Turkey are used in the study. The comparison results revealed that the suggested model could increase the forecast accuracy and perform better than the MLP, MLR and AR models. Copyright © 2008 John Wiley & Sons, Ltd.     

Daily streamflow forecasting using a wavelet transform and artificial neural network hybrid models

Abstract

New wavelet and artificial neural network (WA) hybrid models are proposed for daily streamflow forecasting at 1, 3, 5 and 7 days ahead, based on the low-frequency components of the original signal (approximations). The results show that the proposed hybrid models give significantly better results than the classical artificial neural network (ANN) model for all tested situations. For short-term (1-day ahead) forecasts, information on higher-frequency signal components was essential to ensure good model performance. However, for forecasting more days ahead, lower-frequency components are needed as input to the proposed hybrid models. The WA models also proved to be effective for eliminating the lags often seen in daily streamflow forecasts obtained by classical ANN models. 

Editor D. Koutsoyiannis; Associate editor L. See

Citation Santos, C.A.G. and Silva, G.B.L., 2013. Daily streamflow forecasting using a wavelet transform and artificial neural network hybrid models. Hydrological Sciences Journal, 59 (2), 312–324.     

Simulating and predicting river discharge time series using a wavelet‐neural network hybrid modelling approach

Accurate simulation and prediction of the dynamic behaviour of a river discharge over any time interval is essential for good watershed management. It is difficult to capture the high‐frequency characteristics of a river discharge using traditional time series linear and nonlinear model approaches. Therefore, this study developed a wavelet‐neural network (WNN) hybrid modelling approach for the predication of river discharge using monthly time series data. A discrete wavelet multiresolution method was employed to decompose the time series data of river discharge into sub‐series with low (approximation) and high (details) frequency, and these sub‐series were then used as input data for the artificial neural network (ANN). WNN models with different wavelet decomposition levels were employed to predict river discharge 48 months ahead of time. Comparison of results from the WNN models with those of the ANN models alone indicated that WNN models performed a more accurate prediction. Copyright © 2011 John Wiley & Sons, Ltd.     

Neural network and wavelet conjunction model for modelling monthly level fluctuations in Turkey

This paper proposes the application of a conjunction model (neuro‐wavelet) for forecasting monthly lake levels. The neuro‐wavelet (NW) conjunction model is improved combining two methods, discrete wavelet transform and artificial neural networks. The application of the methodology is presented for the Lake Van, which is the biggest lake in Turkey, and Lake Egirdir. The accuracy of the NW model is investigated for 1‐ and 6‐month‐ahead lake level forecasting. The root mean square errors, mean absolute relative errors and determination coefficient statistics are used for evaluating the accuracy of NW models. The results of the proposed models are compared with those of the neural networks. In the 1‐month‐ahead lake level forecasting, the NW conjunction model reduced the root mean square errors and mean absolute relative errors by 87–34% and 86–31% for the Van and Egirdir lakes, respectively. In the 6‐month‐ahead lake level forecasting, the NW conjunction model reduced the root mean square errors and mean absolute relative errors by 34–48% and 30‐46% for the Van and Egirdir lakes, respectively. The comparison results indicate that the suggested model could significantly increase the short‐ and long‐term forecast accuracy. Copyright © 2009 John Wiley & Sons, Ltd.     

Modelling wetland connectivity during overbank flooding in a tropical floodplain in north Queensland,Australia

Hydrological connectivity between floodplain wetlands and rivers is one of the principal driving mechanisms for the diversity, productivity and interactions of the major biota in river–floodplain systems. This article describes a method of quantifying flood‐induced overbank connectivity using a hydrodynamic model (MIKE 21) to calculate the timing, the duration and the spatial extent of the connections between several floodplain wetlands and rivers in the Tully–Murray catchment, north Queensland, Australia. Areal photogrammetry and field surveyed stream cross data were used to reproduce floodplain topography and rivers in the model. Laser altimetry (LiDAR)–derived fine resolution elevation data, for the central floodplain, were added to the topography model to improve the resolution of key features including wetlands, flow pathways and natural and artificial flow barriers. The hydrodynamic model was calibrated using a combination of in‐stream and floodplain gauge records. A range of off‐stream wetlands including natural and artificial, small and large were investigated for their connectivity with two main rivers (Tully and Murray) flowing over the floodplain for flood events of 1‐, 20‐ and 50‐year recurrence intervals. The duration of the connection of individual wetlands varied from 1 to 12 days, depending on flood magnitude and location in the floodplain, with some wetlands only connected during large floods. All of the wetlands studied were connected to the Tully River for shorter periods than they were to the Murray River because of the higher bank heights and levees on the Tully River and wetland proximity to the Murray River. Other than hydrology, land relief, riverbank elevation and levee banks along the river were found key factors controlling the degree of connectivity. These variations in wetland connectivity could have important implications for aquatic biota that move between rivers and off‐stream habitats during floods. Copyright © 2011 John Wiley & Sons, Ltd.     

Predicting and forecasting flow discharge at sites receiving significant lateral inflow

Two models, one linear and one non‐linear, were employed for the prediction of flow discharge hydrographs at sites receiving significant lateral inflow. The linear model is based on a rating curve and permits a quick estimation of flow at a downstream site. The non‐linear model is based on a multilayer feed‐forward back propagation (FFBP) artificial neural network (ANN) and uses flow‐stage data measured at the upstream and downstream stations. ANN predicted the real‐time storm hydrographs satisfactorily and better than did the linear model. The results of sensitivity analysis indicated that when the lateral inflow contribution to the channel reach was insignificant, ANN, using only the flow‐stage data at the upstream station, satisfactorily predicted the hydrograph at the downstream station. The prediction error of ANN increases exponentially with the difference between the peak discharge used in training and that used in testing. ANN was also employed for flood forecasting and was compared with the modified Muskingum model (MMM). For a 4‐h lead time, MMM forecasts the floods reliably but could not be applied to reaches for lead times greater than the wave travel time. Although ANN and MMM had comparable performances for an 8‐h lead time, ANN is capable of forecasting floods with lead times longer than the wave travel time. Copyright © 2007 John Wiley & Sons, Ltd.     

Evaluation of nonlinear models for precipitation forecasting

Prediction of factors affecting water resources systems is important for their design and operation. In hydrology, wavelet analysis (WA) is known as a new method for time series analysis. In this study, WA was combined with an artificial neural network (ANN) for prediction of precipitation at Varayeneh station, western Iran. The results obtained were compared with the adaptive neural fuzzy inference system (ANFIS) and ANN. Moreover, data on relative humidity and temperature were employed in addition to rainfall data to examine their influence on precipitation forecasting. Overall, this study concluded that the hybrid WANN model outperformed the other models in the estimation of maxima and minima, and is the best at forecasting precipitation. Furthermore, training and transfer functions are recommended for similar studies of precipitation forecasting.     

River flow modelling: comparison of performance and evaluation of uncertainty using data-driven models and conceptual hydrological model

Hydrological and statistical models are playing an increasing role in hydrological forecasting, particularly for river basins with data of different temporal scales. In this study, statistical models, e.g. artificial neural networks, adaptive network-based fuzzy inference system, genetic programming, least squares support vector machine, multiple linear regression, were developed, based on parametric optimization methods such as particle swarm optimization (PSO), genetic algorithm (GA), and data-preprocessing techniques such as wavelet decomposition (WD) for river flow modelling using daily streamflow data from four hydrological stations for a period of 1954–2009. These models were used for 1-, 3- and 5-day streamflow forecasting and the better model was used for uncertainty evaluation using bootstrap resampling method. Meanwhile, a simple conceptual hydrological model GR4J was used to evaluate parametric uncertainty based on generalized likelihood uncertainty estimation method. Results indicated that: (1) GA and PSO did not help improve the forecast performance of the model. However, the hybrid model with WD significantly improved the forecast performance; (2) the hybrid model with WD as a data preprocessing procedure can clarify hydrological effects of water reservoirs and can capture peak high/low flow changes; (3) Forecast accuracy of data-driven models is significantly influenced by the availability of streamflow data. More human interferences from the upper to the lower East River basin can help to introduce greater uncertainty in streamflow forecasts; (4) The structure of GR4J may introduce larger parametric uncertainty at the Longchuan station than at the Boluo station in the East river basin. This study provides a theoretical background for data-driven model-based streamflow forecasting and a comprehensive view about data and parametric uncertainty in data-scarce river basins.     

Multiple model combination methods for annual maximum water level prediction during river ice breakup

The Athabasca River is the largest unregulated river in Alberta, Canada, with ice jams frequently occurring in the vicinity of Fort McMurray. Modelling tools are desired to forecast ice‐related flood events. Multiple model combination methods can often obtain better predictive performances than any member models due to possible variance reduction of forecast errors or correction of biases. However, few applications of this method to river ice forecasting are reported. Thus, a framework of multiple model combination methods for maximum breakup water level (MBWL) Prediction during river ice breakup is proposed. Within the framework, the member models describe the relations between the MBWL (predicted variable) and their corresponding indicators (predictor variables); the combining models link the relations between the predicted MBWL by each member model and the observed MBWL. Especially, adaptive neuro‐fuzzy inference systems, artificial neural networks, and multiple linear regression are not only employed as member models but also as combining models. Simple average methods (SAM) are selected as the basic combining model due to simple calculations. In the SAM, an equal weight (1/n) is assigned to n member models. The historical breakup data of the Athabasca River at Fort McMurray for the past 36 years (1980 to 2015) are collected to facilitate the comparison of models. These models are examined using the leave‐one‐out cross validation and the holdout validation methods. A SAM, which is the average output from three optimal member models, is selected as the best model as it has the optimal validation performance (lowest average squared errors). In terms of lowest average squared errors, the SAM improves upon the optimal artificial neural networks, adaptive neuro‐fuzzy inference systems, and multiple linear regression member models by 21.95%, 30.97%, and 24.03%, respectively. This result sheds light on the effectiveness of combining different forecasting models when a scarce river ice data set is investigated. The indicators included in the SAM may indicate that the MBWL is affected by water flow conditions just after freeze‐up, overall freezing conditions during winter, and snowpack conditions before breakup.     

Performance of an artificial neural network on forecasting the daily occurrence and annual depth of rainfall at a tropical site

Performance of a feed‐forward back‐propagation artificial neural network on forecasting the daily occurrence and annual depth of rainfall at a single meteorological station is presented. Both short‐term and long‐term forecasting was attempted, with ground level data collected by the meteorological station in Colombo, Sri Lanka (79° 52′E, 6° 54′N) during two time periods, 1994–2003 and 1869–2003. Two neural network models were developed; a one‐day‐ahead model for predicting the rainfall occurrence of the next day, which was able to make predictions with a 74·3% accuracy, and one‐year‐ahead model for yearly rainfall depth predictions with an 80·0% accuracy within a ± 5% error bound. Each of these models was extended to make predictions several time steps into the future, where accuracies were found to decrease rapidly with the number of time steps. The success rates and rainfall variability within the north‐east and south‐west monsoon seasons are also discussed. Copyright © 2007 John Wiley & Sons, Ltd.     

PAI-OFF: A new proposal for online flood forecasting in flash flood prone catchments

The Process Modelling and Artificial Intelligence for Online Flood Forecasting (PAI-OFF) methodology combines the reliability of physically based, hydrologic/hydraulic modelling with the operational advantages of artificial intelligence. These operational advantages are extremely low computation times and straightforward operation. The basic principle of the methodology is to portray process models by means of ANN. We propose to train ANN flood forecasting models with synthetic data that reflects the possible range of storm events. To this end, establishing PAI-OFF requires first setting up a physically based hydrologic model of the considered catchment and – optionally, if backwater effects have a significant impact on the flow regime – a hydrodynamic flood routing model of the river reach in question. Both models are subsequently used for simulating all meaningful and flood relevant storm scenarios which are obtained from a catchment specific meteorological data analysis. This provides a database of corresponding input/output vectors which is then completed by generally available hydrological and meteorological data for characterizing the catchment state prior to each storm event. This database subsequently serves for training both a polynomial neural network (PoNN) – portraying the rainfall–runoff process – and a multilayer neural network (MLFN), which mirrors the hydrodynamic flood wave propagation in the river. These two ANN models replace the hydrological and hydrodynamic model in the operational mode. After presenting the theory, we apply PAI-OFF – essentially consisting of the coupled “hydrologic” PoNN and “hydrodynamic” MLFN – to the Freiberger Mulde catchment in the Erzgebirge (Ore-mountains) in East Germany (3000 km²). Both the demonstrated computational efficiency and the prediction reliability underline the potential of the new PAI-OFF methodology for online flood forecasting.     

Real‐time recurrent learning neural network for stream‐flow forecasting

Various types of neural networks have been proposed in previous papers for applications in hydrological events. However, most of these applied neural networks are classified as static neural networks, which are based on batch processes that update action only after the whole training data set has been presented. The time variate characteristics in hydrological processes have not been modelled well. In this paper, we present an alternative approach using an artificial neural network, termed real‐time recurrent learning (RTRL) for stream‐flow forecasting. To define the properties of the RTRL algorithm, we first compare the predictive ability of RTRL with least‐square estimated autoregressive integrated moving average models on several synthetic time‐series. Our results demonstrate that the RTRL network has a learning capacity with high efficiency and is an adequate model for time‐series prediction. We also investigated the RTRL network by using the rainfall–runoff data of the Da‐Chia River in Taiwan. The results show that RTRL can be applied with high accuracy to the study of real‐time stream‐flow forecasting networks. Copyright © 2002 John Wiley & Sons, Ltd.     

Fuzzy computing based rainfall–runoff model for real time flood forecasting

This paper analyses the skills of fuzzy computing based rainfall–runoff model in real time flood forecasting. The potential of fuzzy computing has been demonstrated by developing a model for forecasting the river flow of Narmada basin in India. This work has demonstrated that fuzzy models can take advantage of their capability to simulate the unknown relationships between a set of relevant hydrological data such as rainfall and river flow. Many combinations of input variables were presented to the model with varying structures as a sensitivity study to verify the conclusions about the coherence between precipitation, upstream runoff and total watershed runoff. The most appropriate set of input variables was determined, and the study suggests that the river flow of Narmada behaves more like an autoregressive process. As the precipitation is weighted only a little by the model, the last time‐steps of measured runoff are dominating the forecast. Thus a forecast based on expected rainfall becomes very inaccurate. Although good results for one‐step‐ahead forecasts are received, the accuracy deteriorates as the lead time increases. Using the one‐step‐ahead forecast model recursively to predict flows at higher lead time, however, produces better results as opposed to different independent fuzzy models to forecast flows at various lead times. Copyright © 2004 John Wiley & Sons, Ltd.     

Determining the amplitude and timing of streamflow discontinuities: A cross wavelet analysis approach

Records of natural processes, such as gradual streamflow fluctuations, are commonly interrupted by long or short disruptions from natural non‐linear responses to gradual changes, such as from river‐ice break‐ups, freezing as a result of annual solar cycles, or human causes, such as flow blocking by dams and other means, instrument calibrations and failure. The resulting abrupt or gradual shifts and missing data are considered to be discontinuities with respect to the normal signal. They differ from random noise as they do not follow any fixed distribution over time and, hence, cannot be eliminated by filtering. The multi‐scale resolution features of continuous wavelet analysis and cross wavelet analysis were used in this study to determine the amplitude and timing of such streamflow discontinuities for specific wavebands. The cross wavelet based method was able to detect the strength and timing of abrupt shifts to new streamflow levels, gaps in data records longer than the waveband of interest and a sinusoidal discontinuity curve following an underlying modeled annual signal at ±0.5 year uncertainty. Parameter testing of the time‐frequency resolution demonstrated that high temporal resolution using narrow analysis windows is favorable to high‐frequency resolution for detection of waveband‐related discontinuities. Discontinuity analysis on observed daily streamflow records from Canadian rivers showed the following: (i) that there is at least one discontinuity/year related to the annual spring flood in each record studied, and (ii) neighboring streamflows have similar discontinuity patterns. In addition, the discontinuity density of the Canadian streamflows studied in this paper exhibit 11‐year cycles that are inversely correlated with the solar intensity cycle. This suggests that more streamflow discontinuities, such as through fast freezing, snowmelt, or ice break‐up, may occur during years with slightly lowered solar insolation. Copyright © 2013 John Wiley & Sons, Ltd.     

Longitudinal distributions of river flood power: the combined automated flood,elevation and stream power (CAFES) methodology

Stream power can be an extremely useful index of fluvial sediment transport, channel pattern, river channel erosion and riparian habitat development. However, most previous studies of downstream changes in stream power have relied on field measurements at selected cross‐sections, which are time consuming, and typically based on limited data, which cannot fully represent important spatial variations in stream power. We present here, therefore, a novel methodology we call CAFES (combined automated flood, elevation and stream power), to quantify downstream change in river flood power, based on integrating in a GIS framework Flood Estimation Handbook systems with the 5 m grid NEXTMap Britain digital elevation model derived from IFSAR (interferometric synthetic aperture radar). This provides a useful modelling platform to quantify at unprecedented resolution longitudinal distributions of flood discharge, elevation, floodplain slope and flood power at reach and basin scales. Values can be resolved to a 50 m grid. CAFES approaches have distinct advantages over current methodologies for reach‐ and basin‐scale stream power assessments and therefore for the interpretation and prediction of fluvial processes. The methodology has significant international applicability for understanding basin‐scale hydraulics, sediment transport, erosion and sedimentation processes and river basin management. Copyright © 2008 John Wiley & Sons, Ltd.     

Wavelet-ANFIS models for forecasting monsoon flows: Case study for the Gandak River (India)

WANFIS, a conjunction model of discreet wavelet transform (DWT) and adaptive neuro-fuzzy inference system (ANFIS) was developed for forecasting the current-day flow in a river when only available data are historical flows. Discreet wavelet transform decomposed the observed flow time series (OFTS) into wavelet components which captured useful information on three resolution levels. A smoothened flow time series (SFTS) was formed by filtering out the noise wavelet components and recombining the effective wavelet components. WANFIS model is essentially an ANFIS model with SFTS hydrograph as the input, while ANFIS and autoregression (AR) models, developed for comparison purpose, use OFTS hydrograph as input. For performance evaluation, the developed models were utilized for predicting daily monsoon flows for the Gandak River in Bihar state of India. During monsoon (June–October), this river carries large flows making the entire North Bihar unsafe for habitation or cultivation. Based on various performance indices, it was concluded that WANFIS models simulate the monsoon flows in the Gandak more reliably than ANFIS and AR models. The best performing WANFIS model, with four previous days’ flows as input, predicted the current-day Gandak flows with 80.7% accuracy while ANFIS and AR models predicted it with only 71.8 and 51.2% accuracies.     

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.