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 modelling for mean velocity and turbulence intensities of steep channel flows

The main purpose of this study is to evaluate the potential of simulating the profiles of the mean velocity and turbulence intensities for the steep open channel flows over a smooth boundary using artificial neural networks. In a laboratory flume, turbulent flow conditions were measured using a fibre‐optic laser doppler velocimeter (FLDV). One thousand and sixty‐four data sets were collected for different slopes and aspect ratios at different locations. These data sets were randomly split into two subsets, i.e. training and validation sets. The multi‐layer functional link network (MFLN) was used to construct the simulation model based on the training data. The constructed MFLN models can almost perfectly simulate the velocity profile and turbulence intensity. The values of correlation coefficient (γ) are close to one and the values of root mean square error (RMSE) are close to zero in all conditions. The results demonstrate that the MFLN can precisely simulate the velocity profiles, while the log law and Reynolds stress model (RSM) are less effective when used to simulate the velocity profiles close to the side wall. The simulated longitudinal turbulence intensities yielded by the MFLN were also fairly consistent with the measured data, while the simulated vertical turbulence intensities by the RSM were not consistent with the measured data. Copyright © 2007 John Wiley & Sons, Ltd.     

A methodological approach for estimating turbidity in a river

During the operations of purging and disposal of sediments of a reservoir it is necessary to know the values of turbidity in the river downstream in natural condition,in the absence of dams or river training works.The paper shows that under these conditions the ratio of the average values of sediment discharge to the annual maximum value of water discharge is a function of the average annual turbidity.Turbidity can be considered as representative synthetic index of the climatic conditions,the lithological features and the land cover of the basin,and the geometric characteristics of the river network.The proposed relationship of sediment discharge as a function of water discharge were validated on the basis of data collected from different Italian regions that have very different morphological,geo-lithological and rainfall features and that are characterised by a basin area changing between a few dozen and thousands of square kilometres.The results can be considered satisfying.     

A neural network approach for regional vertical total electron content modelling

A Neural Network model has been developed for estimating the total electron content (TEC) of the ionosphere. TEC is proportional to the delay suffered by electromagnetic signals crossing the ionosphere and is among the errors that impact GNSS (Global Navigation Satellite Systems) observations. Ionospheric delay is particularly a problem for single frequency receivers, which cannot eliminate the (first-order) ionospheric delay by combining observations at two frequencies. Single frequency users rely on applying corrections based on prediction models or on regional models formed based on actual data collected by a network of receivers. A regional model based on a neural network has been designed and tested using data sets collected by the Brazilian GPS Network (RMBC) covering periods of low and high solar activity. Analysis of the results indicates that the model is capable of recovering, on average, 85% of TEC values.     

A novel semi-analytical approach for non-uniform vegetated flows

In this paper a semi-analytical approach is proposed to understand the mechanism by which a non-uniform vegetated flowpasses over a finite thick soil layer covered with grass. The flow region is divided into three layers: a homogenous water layer, a mixed water-grass layer, and a finite thick soil layer (hereafter referred to as the water layer, the grass layer, and the soil layer). The flow of the water layer is governed by the Navier–Stokes equations. Both the grass and soil layers are regarded as porous media and the Biot’s theory of poroelasticity is applied to the porous medium flow. The semi-closed solutions are then obtained by the Runge–Kutta method. The drag force induced by the flow through the grass layer and the flow profiles of three patterns: submerged grass, emergent grass and mixed type are also discussed.     

A combined rotated general regression neural network method for river flow forecasting

ABSTRACT

This study focused on the performance of the rotated general regression neural network (RGRNN), as an enhancement of the general regression neural network (GRNN), in monthly-mean river flow forecasting. The study of forecasting of monthly mean river flows in Heihe River, China, was divided into two steps: first, the performance of the RGRNN model was compared with the GRNN model, the feed-forward error back-propagation (FFBP) model and the soil moisture accounting and routing (SMAR) model in their initial model forms; then, by incorporating the corresponding outputs of the SMAR model as an extra input, the combined RGRNN model was compared with the combined FFBP and combined GRNN models. In terms of model efficiency index, R², and normalized root mean squared error, NRMSE, the performances of all three combined models were generally better than those of the four initial models, and the RGRNN model performed better than the GRNN model in both steps, while the FFBP and the SMAR were consistently the worst two models. The results indicate that the combined RGRNN model could be a useful river flow forecasting tool for the chosen arid and semi-arid region in China.

Editor D. Koutsoyiannis; Associate editor not assigned     

A hybrid neural network model for typhoon-rainfall forecasting

A hybrid neural network model is proposed in this paper to forecast the typhoon rainfall. Two different types of artificial neural networks, the self-organizing map (SOM) and the multilayer perceptron network (MLPN), are combined to develop the proposed model. In the proposed model, a data analysis technique is developed based on the SOM, which can perform cluster analysis and discrimination analysis in one step. The MLPN is used as the nonlinear regression technique to construct the relationship between the input and output data. First, the input data are analyzed using a SOM-based data analysis technique. Through the SOM-based data analysis technique, input data with different properties are first divided into distinct clusters, which can help the multivariate nonlinear regression of each cluster. Additionally, the topological relationships among data are discovered from which more insight into the typhoon-rainfall process can be revealed. Then, for each cluster, the individual relationship between the input and output data is constructed by a specific MLPN. For evaluating the forecasting performance of the proposed model, an application is conducted. The proposed model is applied to the Tanshui River Basin to forecast the typhoon rainfall. The results show that the proposed model can forecast more precisely than the model developed by the conventional neural network approach.     

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.     

Describing alpine lake influence on stream network temperatures: A statistical modelling approach

Systematic variations in atmospheric heat exchange, surface residence time, and groundwater influx across montane stream networks commonly produce an increasing stream temperature trend with decreasing elevation. However, complex stream temperature profiles that differ from this common longitudinal trend also exist, suggesting that stream temperatures may be influenced by complex interactions among hydrologic and atmospheric processes. Lakes within stream networks form one potential source of temperature profile complexity due to the spatially variable contribution of lake-sourced water to stream flow. We investigated temperature profile complexity in a multi-season stream temperature dataset collected across a montane stream network containing many alpine lakes. This investigation was performed by making comparisons between multiple statistical models that used different combinations of stream and lake characteristics to represent specific hypotheses for the controls on stream temperature. The compared models included a set of models which used a topographically derived estimate of the hydrologic influence of lakes to separate and quantify the effects of stream elevation and lake source-water contributions to longitudinal stream temperature patterns. This source-water mixing model provided a parsimonious explanation for complex stream-network temperature patterns in the summer and autumn, and this approach may be further applicable to other systems where stream temperatures are influenced by multiple water sources. Simpler models that discounted lake effects were more optimal during the winter and spring, suggesting that complex patterns in stream temperature profiles may emerge and subside temporally, across seasons, in response to diversity of water temperatures from different sources.     

A modelling approach for estimating suspended sediment concentrations for multiple rivers influenced by agriculture

A data-driven model based on an adaptive neuro-fuzzy inference system (ANFIS) was tested for the estimation of suspended sediment concentrations within watersheds influenced by agriculture. ANFIS models were developed using different combinations of inputs such as precipitation, streamflow, surface runoff and the watershed vulnerability index. A multi-watershed ANFIS model was also developed combining the datasets from all studied watersheds. The best results were obtained from a combination of precipitation, streamflow and watershed vulnerability index as input variables. Nash-Sutcliffe coefficients were improved for the multi-watershed ANFIS compared to watershed-specific ANFIS models. The introduction of the erosion vulnerability index significantly improved the ability of the ANFIS model to estimate suspended sediment concentrations within the watersheds. Furthermore, the inclusion of this index opens the possibility of using the ANFIS model to investigate the impact of land-use changes on sediment delivery.     

Assessment of flow paths and confluences for saltwater intrusion in a deltaic river network

Saltwater intrusion is a serious issue in estuarine deltas all over the world due to rapid urban sprawl and water shortage. Therefore, detecting the major flow paths or locations at risk of saltwater intrusion in estuarine ecosystems is important for mitigating saltwater intrusion. In this paper, we introduce a centrality index, the betweenness centrality (BC), to address this problem. Using the BC as the weighted attribute of the river network, we identify the critical confluences for saltwater intrusion and detect the preferential flow paths for saltwater intrusion through the least‐cost‐path algorithm from a graph theory approach. Moreover, we analyse the responses of the BC values of confluences calculated in the river network to salinity. Our results show that the major flow paths and critical confluences for saltwater intrusion in a deltaic river network can be represented by the least cost paths and the BC values of confluences, respectively. In addition, a significant positive correlation between the BC values of confluences and salinity is determined in the Pearl River Delta. Changes in the salinity can produce significant variation in the BC values of confluences. Therefore, freshwater can be diverted into these major flow paths and critical confluences to improve river network management under saltwater intrusion. Copyright © 2015 John Wiley & Sons, Ltd.     

A multi-model ensemble approach for the assessment of climatic and anthropogenic impacts on river flow change

ABSTRACT

Climate variability and human activities are considered to be the most likely reasons for negative trends in river inflow and the water level of some lakes and wetlands in the world. To quantify the uncertain impacts of climate variations and anthropogenic activities on Ajichay River flow in Iran, a multi-model ensemble approach based on the Bayesian model averaging (BMA) method is applied. Several statistical and simulation-based methods are used to distinguish the impacts of climatic and anthropogenic factors on river flow. The results show that almost all the methods identified human activities as the dominant impact on streamflow (about 73–85% of the change). The between-model and within-model uncertainty analyses using BMA showed that the 95% uncertainty intervals of the individual approaches have relatively large deviation ranges. The BMA mean prediction could reduce the range of between-model uncertainties to 14–27% for climate impacts and 74–80% for human impacts. This approach provides a way to better understand the contributions of climatic and anthropogenic impacts on river flow change.     

A fusion-based neural network methodology for monthly reservoir inflow prediction using MODIS products

ABSTRACT

A model fusion approach was developed based on five artificial neural networks (ANNs) and MODIS products. Static and dynamic ANNs – the multi-layer perceptron (MLP) with one and two hidden layers, general regression neural network (GRNN), radial basis function (RBF) and nonlinear autoregressive network with exogenous inputs (NARX) – were used to predict the monthly reservoir inflow in Mollasadra Dam, Fars Province, Iran. Leaf area index and snow cover from MODIS, and rainfall and runoff data were used to identify eight different combinations to train the models. Statistical error indices and the Borda count method were used to verify and rank the identified combinations. The best results for individual ANNs were combined with MODIS products in a fusion model. The results show that using MODIS products increased the accuracy of predictions, with the MLP with two hidden layers giving the best performance. Also, the fusion model was found to be superior to the best individual ANNs.     

Spatial variation of flow characteristics in a subarctic meandering river in ice-covered and open-channel conditions: A 2D hydrodynamic modelling approach

To be able to understand year-round river channel evolution both at present and in the future, the spatial variation of the flow characteristics and their sediment transport capabilities under ice cover need to be detected. As the measurements done through cross-sectional drill holes cover only a small portion of the river channel area, the numerical simulations give insight into the wider spatial horizontal variation of the flow characteristics. Therefore, we simulate the ice-covered flow with a hydrodynamic two-dimensional (2D) model in a meandering subarctic river (Pulmanki River, Finland) in mid-winter conditions and compare them to the pre-winter open-channel low flow situation. Based on the simulations, which are calibrated with reference measurements, we aim to detect (1) how ice-covered mid-winter flow characteristics vary spatially and (2) the erosion and sedimentation potential of the ice-covered flow compared to open-channel conditions. The 2D hydrodynamic model replicated the observed flow characteristics in both open-channel and ice-covered conditions. During both seasons, the greatest erosional forces locate in the shallow sections. The narrow, freely flowing channel area found in mid-winter cause the main differences in the spatial flow variation between seasons. Despite the causes of the horizontal recirculating flow structures being similar in both seasons, the structures formed in different locations depended on whether the river was open or ice covered. The critical thresholds for particle entrainment are exceeded more often in open-channel conditions than during ice-covered flow. The results indicate spatially extensive sediment transport in open-channel conditions, but that the spatial variability and differences in depositional and erosional locations increase in ice-covered conditions. Asymmetrical bends and straight reaches erode throughout the year, whereas symmetrical, smaller bends mainly erode in open-channel conditions and are prone to deposition in winter. The long ice-covered season can greatly affect the annual morphology of the submerged channel. © 2019 John Wiley & Sons, Ltd.     

A distributed TOPMODEL for modelling impacts of land‐cover change on river flow in upland peatland catchments

There is global concern about headwater management and associated impacts on river flow. In many wet temperate zones peatlands can be found covering headwater catchments. In the UK there is major concern about how environmental change, driven by human interventions, has altered the surface cover of headwater blanket peatlands. However, the impact of such land‐cover changes on river flow is poorly understood. In particular, there is poor understanding of the impacts of different spatial configurations of bare peat or well‐vegetated, restored peat on river flow peaks in upland catchments. In this paper, a physically based, distributed and continuous catchment hydrological model was developed to explore such impacts. The original TOPMODEL, with its process representation being suitable for blanket peat catchments, was utilized as a prototype acting as the basis for the new model. The equations were downscaled from the catchment level to the cell level. The runoff produced by each cell is divided into subsurface flow and saturation‐excess overland flow before an overland flow calculation takes place. A new overland flow module with a set of detailed stochastic algorithms representing overland flow routing and re‐infiltration mechanisms was created to simulate saturation‐excess overland flow movement. The new model was tested in the Trout Beck catchment of the North Pennines of England and found to work well in this catchment. The influence of land cover on surface roughness could be explicitly represented in the model and the model was found to be sensitive to land cover. Copyright © 2014 John Wiley & Sons, Ltd.     

A hybrid approach of artificial neural network and multiple regression to forecast typhoon rainfall and groundwater-level change

ABSTRACT

A forecasting model is developed using a hybrid approach of artificial neural network (ANN) and multiple regression analysis (MRA) to predict the total typhoon rainfall and groundwater-level change in the Zhuoshui River basin. We used information from the raingauge stations in eastern Taiwan and open source typhoon data to build the ANN model for forecasting the total rainfall and the groundwater level during a typhoon event; then we revised the predictive values using MRA. As a result, the average accuracy improved up to 80% when the hybrid model of ANN and MRA was applied, even where insufficient data were available for model training. The outcome of this research can be applied to forecasts of total rainfall and groundwater-level change before a typhoon event reaches the Zhuoshui River basin once the typhoon has made landfall on the east coast of Taiwan.     

A neural network approach for the real-time detection of faults

Fault detection is an essential part of the operation of any chemical plant. Early detection of faults is important in chemical industry since a lot of damage and loss can result before a fault present in the system is detected. Even though fault detection algorithms are designed and implemented for quickly detecting incidents, most these algorithms do not have an optimal property in terms of detection delay with respect to false alarm rate. Based on the optimization property of cumulative sum (CUSUM), a real-time system for detecting changes in dynamic systems is designed in this paper. This work is motivated by combining two fault detection (FD) strategies; a simplified procedure of the incident detection problem is formulated by using both the artificial neural networks (ANN) and the CUSUM statistical test (Page–Hinkley test). The design of a model-based residual generator is intended to reveal any drift from the normal behavior of the process. In order to obtain a reliable model for the normal process dynamics, the neural black-box modeling by means of a nonlinear auto-regressive with eXogenous input (NARX) model has been chosen in this study. This paper also shows the choice and the performance of the neural network in the training and test phases. After describing the system architecture and the proposed methodology of the fault detection, we present a realistic application in order to show the technique’s potential. The purpose is to develop and test the fault detection method on a real incident data, to detect the change presence, and pinpoint the moment it occurred. The experimental results demonstrate the robustness of the FD method.     

A Bayesian network for analyzing biological acute and long-term impacts of an oil spill in the Gulf of Finland

Knowledge of oil-induced impacts from the literature and experts were used to develop a Bayesian network to evaluate the biological consequences of an oil accident in the low-saline Gulf of Finland (GOF). Analysis was carried out for selected groups of organisms. Subnetworks were divided into subgroups according to a predicted response to oil exposure. Two scenario analyses are presented: the most probable and the worst-case accident.The impact of the most probable accident in the GOF is rather small. In most of the groups studied oil-induced long-term effects are evaluated to be minor at least from the perspective of the whole GOF. After the worst-case accident negative effects are more likely. The model predicts that the most vulnerable groups are auks and ducks. Amphipods, gulls and to a lesser extend littoral fishes and seals may show delayed recovery after an accident. Also annual plant species may be susceptible to oil-induced disturbances.