Artificial neural networks for sheet sediment transport

Abstract

Sheet sediment transport was modelled by artificial neural networks (ANNs). A three-layer feed-forward artificial neural network structure was constructed and a back-propagation algorithm was used for the training of ANNs. Event-based, runoff-driven experimental sediment data were used for the training and testing of the ANNs. In training, data on slope and rainfall intensity were fed into the network as inputs and data on sediment discharge were used as target outputs. The performance of the ANNs was tested against that of the most commonly used physically-based models, whose transport capacity was based on one of the dominant variables—flow velocity (V), shear stress (SS), stream power (SP), and unit stream power (USP). The comparison results revealed that the ANNs performed as well as the physically-based models for simulating nonsteady-state sediment loads from different slopes. The performances of the ANNs and the physically-based models were also quantitatively investigated to estimate mean sediment discharges from experimental runs. The investigation results indicated that better estimations were obtained for V over mild and steep slopes, under low rainfall intensity; for USP over mild and steep slopes, under high rainfall intensity; for SP and SS over very steep slopes, under high rainfall intensity; and for ANNs over steep and very steep slopes, under very high rainfall intensities.     

Relationship between bedload and suspended sediment in the sand-bed Exu River,in the semi-arid region of Brazil

Abstract

Suspended sediment and bedload discharges in sand-bed rivers shape semi-arid landscapes and impact sediment delivery from these landscapes, but are still incompletely understood. Suspended sediment and bedload fluxes of the intermittent Exu River, Brazil, were sampled by direct measurements. The highest suspended sediment concentration observed was 4847.4 mg L^-1 and this value was possibly associated with the entrainment of sediment that was deposited in the preceding year. The bedload flux was well related to the stream power and the river efficiently transported all available bedload with a mean rate of 0.0047 kg m^-1 s^-1, and the percentage of bedload to suspended sediment varied between 4 and 12.72. The bed sediment of Exu River was prone to entrainment and showed a proclivity for transport. Thus, sand-bed and gravel-bed rivers of arid environments seem to exhibit the same mobility in the absence of armour layer.

Editor D. Koutsoyiannis; Associate editor B. Touaibia

Citation Cantalice, J.R.B., Cunha Filho, M., Stosic, B.D., Piscoya, V.C., Guerra, S.M.S., and Singh, V.P., 2013. Relationship between bedload and suspended sediment in the sand-bed Exu River, in the semi-arid region of Brazil. Hydrological Sciences Journal, 58 (8), 1789–1802.     

The influence of climate change on suspended sediment transport in Danish rivers

The HIRHAM regional climate model suggests an increase in temperature in Denmark of about 3 °C and an increase in mean annual precipitation of 6–7%, with a larger increase during winter and a decrease during summer between a control period 1961–1990 and scenario period 2071–2100. This change of climate will affect the suspended sediment transport in rivers, directly through erosion processes and increased river discharges and indirectly through changes in land use and land cover. Climate‐change‐induced changes in suspended sediment transport are modelled for five scenarios on the basis of modelled changes in land use/land cover for two Danish river catchments: the alluvial River Ansager and the non‐alluvial River Odense. Mean annual suspended sediment transport is modelled to increase by 17% in the alluvial river and by 27% in the non‐alluvial for steady‐state scenarios. Increases by about 9% in the alluvial river and 24% in the non‐alluvial river were determined for scenarios incorporating a prolonged growing season for catchment vegetation. Shortening of the growing season is found to have little influence on mean annual sediment transport. Mean monthly changes in suspended sediment transport between ? 26% and + 68% are found for comparable suspended sediment transport scenarios between the control and the scenario periods. The suspended sediment transport increases during winter months as a result of the increase in river discharge caused by the increase in precipitation, and decreases during summer and early autumn months. Copyright © 2007 John Wiley & Sons, Ltd.     

Bedload transport of small rivers in Malaysia

Numerous time-consuming equations, based on the relationship between the reliability and representativeness of the data utilized in defining variables and constants, require complex parameters to estimate bedload transport. In this study the easily accessible data including flow discharge, water depth, water surface slope, and surface grain diameter （ds0） from small rivers in Malaysia were used to estimate bedload transport. Genetic programming （GP） and artificial neural network （ANN） models are applied as complementary tools to estimate bed load transport based on a balance between simplicity and accuracy in small rivers. The developed models demonstrate higher performance with an overall accuracy of 97% and 93% for ANN and GP, respectively compared with other traditional methods and empirical equations.     

Neuro-fuzzy models employing wavelet analysis for suspended sediment concentration prediction in rivers

Abstract

The study of sediment load is important for its implications to the environment and water resources engineering. Four models were considered in the study of suspended sediment concentration prediction: artificial neural networks (ANNs), neuro-fuzzy model (NF), conjunction of wavelet analysis and neuro-fuzzy (WNF) model, and the conventional sediment rating curve (SRC) method. Using data from a US Geological Survey gauging station, the suspended sediment concentration predicted by the WNF model was in satisfactory agreement with the measured data. Also the proposed WNF model generated reasonable predictions for the extreme values. The cumulative suspended sediment load estimated by this model was much higher than that predicted by the other models, and is close to the observed data. However, in the current modelling, the ANN, NF and SRC models underestimated sediment load. The WNF model was successful in reproducing the hysteresis phenomenon, but the SRC method was not able to model this behaviour. In general, the results showed that the NF model performed better than the ANN and SRC models.

Citation Mirbagheri, S. A., Nourani, V., Rajaee, T. & Alikhani, A. (2010) Neuro-fuzzy models employing wavelet analysis for suspended sediment concentration prediction in rivers. Hydrol. Sci. J. 55(7), 1175–1189.     

Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis

ABSTRACT

Ensemble machine learning models have been widely used in hydro-systems modeling as robust prediction tools that combine multiple decision trees. In this study, three newly developed ensemble machine learning models, namely gradient boost regression (GBR), AdaBoost regression (ABR) and random forest regression (RFR) are proposed for prediction of suspended sediment load (SSL), and their prediction performance and related uncertainty are assessed. The SSL of the Mississippi River, which is one of the major world rivers and is significantly affected by sedimentation, is predicted based on daily values of river discharge (Q) and suspended sediment concentration (SSC). Based on performance metrics and visualization, the RFR model shows a slight lead in prediction performance. The uncertainty analysis also indicates that the input variable combination has more impact on the obtained predictions than the model structure selection.     

Modelling long-term groundwater fluctuations by extreme learning machine using hydro-climatic data

The ability of the extreme learning machine (ELM) is investigated in modelling groundwater level (GWL) fluctuations using hydro-climatic data obtained for Hormozgan Province, southern Iran. Monthly precipitation, evaporation and previous GWL data were used as model inputs. Developed ELM models were compared with the artificial neural networks (ANN) and radial basis function (RBF) models. The models were also compared with the autoregressive moving average (ARMA), and evaluated using mean square errors, mean absolute error, Nash-Sutcliffe efficiency and determination coefficient statistics. All the data-driven models had better accuracy than the ARMA, and the ELM model’s performance was superior to that of the ANN and RBF models in modelling 1-, 2- and 3-month-ahead GWL. The RMSE accuracy of the ANN model was increased by 37, 34 and 52% using ELM for the 1-, 2- and 3-month-ahead forecasts, respectively. The accuracy of the ELM models was found to be less sensitive to increasing lead time.     

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.     

Estimation of suspended sediment concentration in the Saint John River using rating curves and a machine learning approach

ABSTRACT

Sedimentation in navigable waterways and harbours is of concern for many water and port managers. One potential source of variability in sedimentation is the annual sediment load of the river that empties in the harbour. The main objective of this study was to use some of the regularly monitored hydro-meteorological variables to compare estimates of hourly suspended sediment concentration in the Saint John River using a sediment rating curve and a model tree (M5?) with different combinations of predictors. Estimated suspended sediment concentrations were multiplied by measured flows to estimate suspended sediment loads. Best results were obtained using M5? with four predictors, returning an R² of 0.72 on calibration data and an R² of 0.46 on validation data. Total load was underestimated by 1.41% for the calibration period and overestimated by 2.38% for the validation period. Overall, the model tree approach is suggested for its relative ease of implementation and constant performance.

EDITOR M.C. Acreman; ASSOCIATE EDITOR B. Touaibia     

Support vector machine method for forecasting future strong earthquakes in Chinese mainland

Statistical learning theory is for small-sample statistics. And support vector machine is a new machine learning method based on the statistical learning theory. The support vector machine not only has solved certain problems in many learning methods, such as small sample, over fitting, high dimension and local minimum, but also has a higher generalization （forecasting） ability than that of artificial neural networks. The strong earthquakes in Chinese mainland are related to a certain extent to the intensive seismicity along the main plate boundaries in the world, however, the relation is nonlinear. In the paper, we have studied this unclear relation by the support vector machine method for the purpose of forecasting strong earthquakes in Chinese mainland.     

Machine learning for accelerating 2D flood models: Potential and challenges

Two-dimensional hydrodynamic models numerically solve full Shallow Water Equations (SWEs). Despite their high accuracy, these models have long simulation run times and therefore are of limited use for exploratory or real-time flood predictions. We investigated the possibility of improving flood modelling speed using Machine Learning (ML). We propose a new method that replaces the computationally expensive parts of the hydrodynamic models with simple and efficient data-driven approximations. Our hypothesis is that by integrating ML with physics-based numerical methods, we can achieve improved generalization performance: that is, the trained model for one case study can be used in other studies without the need for new training. We tested two ML approaches: for the first, we integrated curve fitting, and, for the second, artificial neural networks (ANN) with a finite volume scheme to solve the local inertial approximation of the SWEs. The data-driven models approximated the Momentum Equation, which explicitly solved the time derivative of flow rates. Water depths were then updated by applying a water balance equation. We also tested two different training datasets: the simulated dataset, generated from the results of hydrodynamic model, and the random dataset, generated by directly solving the momentum equation on randomly sampled input data. Various combinations of input features, for example, water slope and depth, were explored. The proposed models were trained in a small hypothetical case and tested in a different hypothetical and in two real case studies. Results showed that the curve-fitting method can be implemented successfully, given sufficient training and input data. The ANN model trained with a random dataset was substantially more accurate than that of the model trained with the simulated dataset. However, it was not successful in the real case studies. The curve-fitting method resulted in better generalization performance and increased the simulation speed of the local inertial model by 23%. Future research should test the performance of ML in terms of an increase in stable time step size and approximation of the full SWEs.     

Genetic programming model for forecast of short and noisy data

Though forecasting of river flow has received a great deal of attention from engineers and researchers throughout the world, this still continues to be a challenging task owing to the complexity of the process. In the last decade or so, artificial neural networks (ANNs) have been widely applied, and their ability to model complex phenomena has been clearly demonstrated. However, the success of ANNs depends very crucially on having representative records of sufficient length. Further, the forecast accuracy decreases rapidly with an increase in the forecast horizon. In this study, the use of the Darwinian theory‐based recent evolutionary technique of genetic programming (GP) is suggested to forecast fortnightly flow up to 4‐lead. It is demonstrated that short lead predictions can be significantly improved from a short and noisy time series if the stochastic (noise) component is appropriately filtered out. The deterministic component can then be easily modelled. Further, only the immediate antecedent exogenous and/or non‐exogenous inputs can be assumed to control the process. With an increase in the forecast horizon, the stochastic components also play an important role in the forecast, besides the inherent difficulty in ascertaining the appropriate input variables which can be assumed to govern the underlying process. GP is found to be an efficient tool to identify the most appropriate input variables to achieve reasonable prediction accuracy for higher lead‐period forecasts. A comparison with ANNs suggests that though there is no significant difference in the prediction accuracy, GP does offer some unique advantages. Copyright © 2006 John Wiley & Sons, Ltd.     

Data-based modelling approach for variable density flow and solute transport simulation in a coastal aquifer

Data-based models, namely artificial neural network (ANN), support vector machine (SVM), genetic programming (GP) and extreme learning machine (ELM), were developed to approximate three-dimensional, density-dependent flow and transport processes in a coastal aquifer. A simulation model, SEAWAT, was used to generate data required for the training and testing of the data-based models. Statistical analysis of the simulation results obtained by the four models show that the data-based models could simulate the complex salt water intrusion process successfully. The selected models were also compared based on their computational ability, and the results show that the ELM is the fastest technique, taking just 0.5 s to simulate the dataset; however, the SVM is the most accurate, with a Nash-Sutcliffe efficiency (NSE) ≥ 0.95 and correlation coefficient R ≥ 0.92 for all the wells. The root mean square error (RMSE) for the SVM is also significantly less, ranging from 12.28 to 77.61 mg/L.     

Multigene genetic programming for sediment transport modeling in sewers for conditions of non-deposition with a bed deposit

It is known that construction of large sewers based on consideration of flow with non-deposition without a bed deposit is not economical. Sewer design based on consideration of flow with non-deposition with a bed deposit reduces channel bed slope and construction cost in which the presence of a small depth of sediment deposition on the bed increases the sediment transport capacity of the flow. This paper suggests a new Pareto-optimal model developed by the multigene genetic programming (MGGP) technique to estimate particle Froude number (Fr_p) in large sewers with conditions of sediment deposition on the bed. To this end, four data sets including wide ranges of sediment size and concentration, deposit thickness, and pipe size are used. On the basis of different statistical performance indices, the efficiency of the proposed Pareto-optimal MGGP model is compared to those of the best MGGP model developed in the current study as well as the conventional regression models available in the literature. The results indicate the higher efficiency of the MGGP-based models for Fr_p estimation in the case of no additional deposition onto a bed with a sediment deposit. Inasmuch as the Pareto-optimal MGGP model utilizes a lower number of input parameters to yield comparatively higher performance than the conventional regression models, it can be used as a parsimonious model for self-cleansing design of large sewers in practice.     

Intelligent control for modeling of real‐time reservoir operation,part II: artificial neural network with operating rule curves

To bridge the gap between academic research and actual operation, we propose an intelligent control system for reservoir operation. The methodology includes two major processes, the knowledge acquired and implemented, and the inference system. In this study, a genetic algorithm (GA) and a fuzzy rule base (FRB) are used to extract knowledge based on the historical inflow data with a design objective function and on the operating rule curves respectively. The adaptive network‐based fuzzy inference system (ANFIS) is then used to implement the knowledge, to create the fuzzy inference system, and then to estimate the optimal reservoir operation. To investigate its applicability and practicability, the Shihmen reservoir, Taiwan, is used as a case study. For the purpose of comparison, a simulation of the currently used M‐5 operating rule curve is also performed. The results demonstrate that (1) the GA is an efficient way to search the optimal input–output patterns, (2) the FRB can extract the knowledge from the operating rule curves, and (3) the ANFIS models built on different types of knowledge can produce much better performance than the traditional M‐5 curves in real‐time reservoir operation. Moreover, we show that the model can be more intelligent for reservoir operation if more information (or knowledge) is involved. Copyright © 2004 John Wiley & Sons, Ltd.     

Comparison of data-driven modelling techniques for river flow forecasting

Abstract

Accurate forecasting of streamflow is essential for the efficient operation of water resources systems. The streamflow process is complex and highly nonlinear. Therefore, researchers try to devise alterative techniques to forecast streamflow with relative ease and reasonable accuracy, although traditional deterministic and conceptual models are available. The present work uses three data-driven techniques, namely artificial neural networks (ANN), genetic programming (GP) and model trees (MT) to forecast river flow one day in advance at two stations in the Narmada catchment of India, and the results are compared. All the models performed reasonably well as far as accuracy of prediction is concerned. It was found that the ANN and MT techniques performed almost equally well, but GP performed better than both these techniques, although only marginally in terms of prediction accuracy in normal and extreme events.

Citation Londhe, S. & Charhate, S. (2010) Comparison of data-driven modelling techniques for river flow forecasting. Hydrol. Sci. J. 55(7), 1163–1174.     

Are artificial neural network techniques relevant for the estimation of longitudinal dispersion coefficient in rivers? / Les techniques de réseaux de neurones artificiels sont-elles pertinentes pour estimer le coefficient de dispersion longitudinale en rivières?

Abstract

Abstract Accurate application of the longitudinal dispersion model requires that specially designed experimental studies are performed in the river reach under consideration. Such studies are usually very expensive, so in order to quantify the longitudinal dispersion coefficient, as an alternative approach, various researchers have proposed numerous empirical formulae based on hydraulic and morphometric characteristics. The results are presented of the application of artificial neural networks as a parameter estimation technique. Five different cases were considered with the network trained for different arrangements of input nodes, such as channel depth, channel width, cross-sectionally averaged water velocity, shear velocity and sinuosity index. In the case where the sinuosity index is included as an input node, the results turned out to be better than those presented by other authors.     

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.     

On the importance of training methods and ensemble aggregation for runoff prediction by means of artificial neural networks

ABSTRACT

Artificial neural networks (ANNs) become widely used for runoff forecasting in numerous studies. Usually classical gradient-based methods are applied in ANN training and a single ANN model is used. To improve the modelling performance, in some papers ensemble aggregation approaches are used whilst in others, novel training methods are proposed. In this study, the usefulness of both concepts is analysed. First, the applicability of a large number of population-based metaheuristics to ANN training for runoff forecasting is tested on data collected from four catchments, namely upper Annapolis (Nova Scotia, Canada), Biala Tarnowska (Poland), upper Allier (France) and Axe Creek (Victoria, Australia). Then, the importance of the search for novel training methods is compared with the importance of the use of a very simple ANN ensemble aggregation approach. It is shown that although some metaheuristics may slightly outperform the classical gradient-based Levenberg-Marquardt algorithm for a specific catchment, none performs better for the majority of the tested ones. One may also point out a few metaheuristics that do not suit ANN training at all. On the other hand, application of even the simplest ensemble aggregation approach clearly improves the results when the ensemble members are trained by any suitable algorithms.

EDITOR D. Koutsoyiannis; ASSOCIATE EDITOR E. Toth