Rainstorm-generated sediment yield model based on soil moisture proxies (SMP)

This study develops improved Soil Moisture Proxies (SMP) based suspended sediment yield (SMPSY) models corresponding to three antecedent moisture conditions (AMCs) (i.e., AMC-I-AMC-III) by coupling the improved initial abstraction (I_a-λ) model, the SMA procedure and the SMP concept for modelling the rainfall generated suspended sediment yield. The SMPSY models specifically incorporate a watershed storage index (S) model to accentuate the transformation from storm to storm and to avoid the sudden jumps in sediment yield computation. The workability of the SMPSY models is tested using a large dataset of rainfall and sediment yield (98 storm events) from twelve small watersheds and a comparison has been made with the existing MSY model. The goodness-of-fit (GOF) statistics is evaluated in terms of the Nash Sutcliffe efficiency (NSE), and error indices, i.e., root mean square error (RMSE), normalized root mean square error (nRMSE), standard error (SE), mean absolute error (MAE), and RMSE-observations standard deviation ratio (RSR). The NSE values vary from 74.31% to 96.57% and from 75.21% to 91.78%, respectively for the SPMSY and MSY model. The NSE statistics indicate that the SMPSY model has lower uncertainty in simulating sediment yield as compared to the MSY model. The error indices are lower for the SMPSY model than the MSY model for most of the watersheds. These results show that the SMPSY model has less uncertainty and performs better than the MSY model. A sensitivity analysis of the SMPSY model shows that the parameter β is most sensitive followed by parameter S, α and A. Overall, the results show that the characterization of soil moisture variability in terms of SMPs and incorporation of improved delivery ratio and runoff coefficient relationship improves the simulation of the erosion and sediment yield generation process.     

Polynomial chaos expansion and response surface method for nonlinear modelling of reference evapotranspiration

The feasibility of polynomial chaos expansion (PCE) and response surface method (RSM) models is investigated for modelling reference evapotranspiration (ET₀). The modelling results of the proposed models are validated against the M5 model tree and multi-layer perceptron neural network (MLPNN) methods. Two meteorological stations, Isparta and Antalya, in the Mediterranean region of Turkey, are inspected. Various input combinations of daily air temperature, solar radiation, wind speed and relative humidity are constructed as input attributes for the ET₀. Generally, the modelling accuracy is increased by increasing the number of inputs. Including wind speed in the model inputs considerably increases their accuracy in modelling ET₀. Mean absolute error (MAE), root mean square error (RMSE), agreement index (d) and Nash-Sutcliffe efficiency (NSE) are used as comparison criteria. The PCE is the most accurate model in estimating daily ET₀, giving the lowest MAE (0.036 and 0.037 mm) and RMSE (0.047 and 0.050 mm) and the highest d (0.9998 and 0.9999) and NSE (0.9992 and 0.9996) with the four-input PCE models for Isparta and Antalya, respectively.     

Modelling daily suspended sediment of rivers in Turkey using several data-driven techniques / Modélisation de la charge journalière en matières en suspension dans des rivières turques à l'aide de plusieurs techniques empiriques

Abstract

The transport of sediment load in rivers is important with respect to pollution, channel navigability, reservoir filling, longevity of hydroelectric equipment, fish habitat, river aesthetics and scientific interest. However, conventional sediment rating curves cannot estimate sediment load accurately. An adaptive neuro-fuzzy technique is investigated for its ability to improve the accuracy of the streamflow—suspended sediment rating curve for daily suspended sediment estimation. The daily streamflow and suspended sediment data for four stations in the Black Sea region of Turkey are used as case studies. A comparison is made between the estimates provided by the neuro-fuzzy model and those of the following models: radial basis neural network (RBNN), feed-forward neural network (FFNN), generalized regression neural network (GRNN), multi-linear regression (MLR) and sediment rating curve (SRC). Comparison of results reveals that the neuro-fuzzy model, in general, gives better estimates than the other techniques. Among the neural network techniques, the RBNN is found to perform better than the FFNN and GRNN.     

Modeling the initiation of sediment motion under a wide range of flow conditions using a Geno-Mamdani Fuzzy Inference System method

The current study introduces a novel approach to estimate the incipient motion of sediments under a wide range of flow regimes by developing a fuzzy model with a fuzzy-band that refers to a transition from weak motion to general motion of sediment. The partial sediment entrainment is defined by fuzzy sets considering the uncertainty related to the individual ratio of inertia to viscous forces which is the definition of shear Reynolds number. In the current study, the Mamdani Fuzzy Inference System (Mamdani FIS) is used to develop a comprehensive fuzzy model of the incipient motion of sediment. The Mamdani FIS has a shortcoming regarding the training of the fuzzy model. To estimate the dimensionless shear stress, a new method is developed by combining a genetic algorithm with the fuzzy approach which is named the Geno-Mamdani Fuzzy Inference System (GMFIS) method. The performance of the GMFIS model is evaluated using experimental data by considering root mean square error (RMSE), Nash-Sutcliffe coefficient of efficiency (CE), degree of robustness (D_r), and concordance coefficient (CC) as evaluation criteria. The GMFIS model performed very well based on the RMSE, CE, D_r, and CC values and satisfactorily represented the three types of incipient motion. Finally, a new range of fuzzy, dimensionless, critical shear stress values is established in all flow conditions from weak to general sediment entrainment.     

Evaluation of the WEPP model and digital elevation grid size,for simulation of streamflow and sediment yield in a heterogeneous catchment

The paper presents the result of an application of the GeoWEPP model in a heterogeneous semi‐agricultural catchment located in the northern Italian Apennines mountain range. The objectives were: (a) to evaluate the GeoWEPP model in a heterogeneous catchment in a Mediterranean climate and (b) to examine the effect of digital elevation model grid size on hydrological and sediment yield simulations. The catchment is characterized by large heterogeneity in geology, soil type, vegetation cover and topography. In addition, 10% of its area is occupied by calanchi (badlands), characterized by steep, bare soil and accentuated erosion. Experimental streamflow data were compared with those simulated by GeoWEPP for a period of eight years and the results were evaluated by means of statistical indices, with the analysis of the flow duration curve. Simulated sediment yields were compared with experimental data for one year. The streamflow cumulative annual results were satisfactory with NSE oscillating between 0.40 and 0.83 and RMSE between 1.1 and 2.9 mm. Also, the performance of the model with daily streamflow data was positive (NSE = 0.68 and RMSE = 1.9 mm). The flow duration curve indicated that GeoWEPP could represent the experimental streamflow for fluxes over 1 mm d^?1. The model performance for simulation of sediment yield was satisfactory with both digital elevation models of different grid sizes (NSE = 0.84 and 0.87). Indeed, the sensitivity analysis tests of the model showed that there was no statistically significant improvement in the accuracy of the digital elevation model between 10 and 2 m resolution. These results were confirmed for both streamflow as well as sediment yield. Additional sensitivity analysis of other model parameters performed on the entire catchment and badlands hillslopes showed that bedrock hydraulic conductivity primarily affected the model in both settings. Copyright © 2014 John Wiley & Sons, Ltd.     

Forecasting streamflow by combination of a genetic input selection algorithm and wavelet transforms using ANFIS models

ABSTRACT

In this study, a data-driven streamflow forecasting model is developed, in which appropriate model inputs are selected using a binary genetic algorithm (GA). The process involves using a combination of a GA input selection method and two adaptive neuro-fuzzy inference systems (ANFIS): subtractive (Sub)-ANFIS and fuzzy C-means (FCM)-ANFIS. Moreover, the application of wavelet transforms coupled with these models is tested. Long-term data for the Lighvan and Ajichai basins in Iran are used to develop the models. The results indicate considerable improvements when GA selection and wavelet methods are used in both models. For example, the Nash-Sutcliffe efficiency (NSE) coefficient for Lighvan using FCM-ANFIS is 0.74. However, when GA selection is applied, the NSE is improved to 0.85. Moreover, when the wavelet method is added, the performance of new hybrid models shows noticeable enhancements. The NSE value of wavelet-FCM-ANFIS is improved to 0.97 for Lighvan basin.

Editor D. Koutsoyiannis Associate editor E. Toth     

Deep learning long short-term memory combined with discrete element method for porosity prediction in gravel-bed rivers

The porosity of gravel riverbed material often is an essential parameter to estimate the sediment transport rate, groundwater-river flow interaction, river ecosystem, and fluvial geomorphology. Current methods of porosity estimation are time-consuming in simulation. To evaluate the relation between porosity and grain size distribution (GSD), this study proposed a hybrid model of deep learning Long Short-Term Memory (LSTM) combined with the Discrete Element Method (DEM). The DEM is applied to model the packing pattern of gravel-bed structure and fine sediment infiltration processes in three-dimensional (3D) space. The combined approaches for porosity calculation enable the porosity to be determined through real time images, fast labeling to be applied, and validation to be done. DEM outputs based on the porosity dataset were utilized to develop the deep learning LSTM model for predicting bed porosity based on the GSD. The simulation results validated with the experimental data then segregated into 800 cross sections along the vertical direction of gravel pack. Two DEM packing cases, i.e., clogging and penetration are tested to predict the porosity. The LSTM model performance measures for porosity estimation along the z-direction are the coefficient of determination (R²), root mean squared error (RMSE), and mean absolute error (MAE) with values of 0.99, 0.01, and 0.01 respectively, which is better than the values obtained for the Clogging case which are 0.71, 0.14, and 0.03, respectively. The use of the LSTM in combination with the DEM model yields satisfactory results in a less complex gravel pack DEM setup, suggesting that it could be a viable alternative to minimize the simulation time and provide a robust tool for gravel riverbed porosity prediction. The simulated results showed that the hybrid model of the LSTM combined with the DEM is reliable and accurate in porosity prediction in gravel-bed river test samples.     

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.     

A neuro-fuzzy-based modelling approach for sediment transport computation

Abstract

The application of a data-driven adaptive neuro-fuzzy modelling technique for predicting bed load and total bed-material load for the River Rhine is summarized. Four main parameters affecting sediment transport are used to construct the model, using 560 and 510 measured bed load and total bed-material load data, respectively. Two-thirds of the available data sets are used for training and one third for testing. The initial fuzzy model is obtained by grid partitioning of the input variables. The optimization of the model is performed by data-driven tuning of the fuzzy model parameters using the adaptive neuro-fuzzy inference system, so that the model output is able to reproduce the measured value. A sensitivity analysis for the combination of input parameters, as well as the number and type of membership functions, is also performed. The model results show that the data-driven adaptive neuro-fuzzy modelling approach can be a powerful alternative technique for estimating both bed load and total bed-material load.

Editor D. Koutsoyiannis

Citation Wieprecht, S., Tolossa, H.G., and Yang, C.T., 2013. A neuro-fuzzy-based modelling approach for sediment transport computation. Hydrological Sciences Journal, 58 (3), 587–599.     

Seasonal Short‐Term Prediction of Dissolved Oxygen in Rivers via Nature‐Inspired Algorithms

This study challenges the use of three nature‐inspired algorithms as learning frameworks of the adaptive‐neuro‐fuzzy inference system (ANFIS) machine learning model for short‐term modeling of dissolved oxygen (DO) concentrations. Particle swarm optimization (PSO), butterfly optimization algorithm (BOA), and biogeography‐based optimization (BBO) are employed for developing predictive ANFIS models using seasonal 15 min data collected from the Rock Creek River in Washington, DC. Four independent variables are used as model inputs including water temperature (T), river discharge (Q), specific conductance (SC), and pH. The Mallow's Cp and R² parameters are used for choosing the best input parameters for the models. The models are assessed by several statistics such as the coefficient of determination (R²), root‐mean‐square error (RMSE), Nash–Sutcliffe efficiency, mean absolute error, and the percent bias. The results indicate that the performance of all‐nature‐inspired algorithms is close to each other. However, based on the calculated RMSE, they enhance the accuracy of standard ANFIS in the spring, summer, fall, and winter around 13.79%, 15.94%, 6.25%, and 12.74%, respectively. Overall, the ANFIS‐PSO and ANFIS‐BOA provide slightly better results than the other ANFIS models.     

River temperature forecasting: case study for Little Southwest Miramichi River (New Brunswick,Canada)

River temperature models play an increasingly important role in the management of fisheries and aquatic resources. Among river temperature models, forecasting models remain relatively unused compared to water temperature simulation models. However, water temperature forecasting is extremely important for in-season management of fisheries, especially when short-term forecasts (a few days) are required. In this study, forecast and simulation models were applied to the Little Southwest Miramichi River (New Brunswick, Canada), where water temperatures can regularly exceed 25–29°C during summer, necessitating associated fisheries closures. Second- and third-order autoregressive models (AR2, AR3) were calibrated and validated using air temperature as the exogenous variable to predict minimum, mean and maximum daily water temperatures. These models were then used to predict river temperatures in forecast mode (1-, 2- and 3-day forecasts using real-time data) and in simulation mode (using only air temperature as input). The results showed that the models performed better when used to forecast rather than simulate water temperatures. The AR3 model slightly outperformed the AR2 in the forecasting mode, with root mean square errors (RMSE) generally between 0.87°C and 1.58°C. However, in the simulation mode, the AR2 slightly outperformed the AR3 model (1.25°C < RMSE < 1.90°C). One-day forecast models performed the best (RMSE ~ 1°C) and model performance decreased as time lag increased (RMSE close to 1.5°C after 3 days). The study showed that marked improvement in the modelling can be accomplished using forecasting models compared to water temperature simulations, especially for short-term forecasts.

EDITOR M.C. Acreman ASSOCIATE EDITOR S. Huang     

Suitability of MUSLT for storm sediment yield prediction in Chehelgazi watershed,Iran

Abstract

The Chehelgazi watershed of Gheshlagh Dam in western Iran was selected to check the capability of the MUSLT (Theoretical Modified Universal Soil Loss Equation) model for estimating sediment yield during storms. The efficiency of MUSLT for sediment yield prediction was assessed using observed sediment data recorded for 11 storm events between October 2006 and April 2007. The results showed that MUSLT overestimated sediment yield with a high coefficient of determination (R² = 0.636 and p < 0.05), and it was then calibrated by examining regression models. The developed calibrated model (C-MUSLT) performed well, with a coefficient of determination of 0.739 (p < 0.05) and relative estimation and verification errors of 49.36 and 25.18%, respectively. The results of comparison between observed and estimated values, obtained by applying the calibrated model, confirmed that the difference was significant with a t value of 1.453 (p?=?0.05).

Citation Sadeghi, S.H.R., Gholami, L., and Khaledi Darvishan, A.V., 2013. Suitability of MUSLT for storm sediment yield prediction in Chehelgazi watershed, Iran. Hydrological Sciences Journal, 58 (4), 892–897.     

Artificial neural network simulation for prediction of suspended sediment concentration in the River Ramganga,Ganges Basin,India

The relation between the water discharge (Q) and suspended sediment concentration (SSC) of the River Ramganga at Bareilly, Uttar Pradesh, in the Himalayas, has been modeled using Artificial Neural Networks (ANNs). The current study validates the practical capability and usefulness of this tool for simulating complex nonlinear, real world, river system processes in the Himalayan scenario. The modeling approach is based on the time series data collected from January to December (2008-2010) for Q and SSC. Three ANNs (T1-T3) with different network configurations have been developed and trained using the Levenberg Marquardt Back Propagation Algorithm in the Matlab routines. Networks were optimized using the enumeration technique, and, finally, the best network is used to predict the SSC values for the year 2011. The values thus obtained through the ANN model are compared with the observed values of SSC. The coefficient of determination (R2), for the optimal network was found to be 0.99. The study not only provides insight into ANN modeling in the Himalayan river scenario, but it also focuses on the importance of understanding a river basin and the factors that affect the SSC, before attempting to model it. Despite the temporal variations in the study area, it is possible to model and successfully predict the SSC values with very simplistic ANN models.     

Wavelet and Neuro‐fuzzy Conjunction Approach for Suspended Sediment Prediction

Simulation approaches employed in suspended sediment processes are important in the areas of water resources and environmental engineering. In the current study, neuro‐fuzzy (NF), a combination of wavelet transform and neuro‐fuzzy (WNF), multi linear regression (MLR), and the conventional sediment rating curve (SRC) models were considered for suspended sediment load (S) modeling in a gauging station in the USA. In the proposed WNF model, the discrete wavelet analysis was linked to a NF approach. To achieve this aim, the observed time series of river flow discharge (Q) and S were decomposed to sub time series at different scales by discrete wavelet transform. Afterwards, the effective sub time series were added together to obtain a useful Q and S time series for prediction. Eventually, the obtained total time series were imposed as inputs to the NF method for daily S prediction. The results illustrated that the predicted values by the proposed WNF model were in good agreement with the observed S values and gave better results than other models. Furthermore, the WNF model satisfactorily estimated the cumulative suspended sediment load and produced relatively reasonable predictions for extreme values of S, while NF, MLR, and SRC models provided unacceptable predictions.     

2D NUMERICAL SIMULATION OF FLOOD AND FLUVIAL PROCESS IN THE MEANDERING AND ISLAND-BRAIDED MIDDLE YANGTZE RIVER

The characteristics of water flow and sediment transport in a typical meandering and island-braided reach of the middle Yangtze River is investigated using a two-dimensional （2D） mathematical model. The major problems studied in the paper include the carrying capacity for suspended load, the incipient velocity and transport formula of non-uniform sediment, the thickness of the mixed layer on the riverbed, and the partitioning of bed load and suspended load. The model parameters are calibrated using extensive field data. Water surface profiles, distribution of flow velocities, riverbed deformation are verified with site measurements. The model is applied to a meandering and island-braided section of the Wakouzi-Majiazui reach in the middle Yangtze River, which is about 200 km downstream from the Three Gorges Dam, to study the training scheme of the navigation channels. The model predicts the processes of sediment deposition and fiver bed erosion, changes of flow stage and navigation conditions for the first 20 years of impoundment of the Three Gorges Project.     

A NUMERICAL MODEL FOR SEDIMENTATION IN FENHE RESERVOIR AND THE ADJOINING REACHES

In this paper, a numerical model for sedimentation in Fenhe Reservoir and the adjoining reaches has been presented on the basis of the theory of non-equilibrium sediment transport. The model is calibrated by using a part of the sediment data collected for Fenhe Reservoir and checked by simulating the remaining data. Moreover, the method of optimization in nonlinear programming has been applied to determine the basic parameters of the model applying a concept of fuzzy mathematics to formulate the objective functions. The computed amounts of reservoir deposition and channel deformation arc found to be substantially in agreement with the values observed.     

Development of a river delta: a case study of Cimanuk river mouth,Indonesia

This paper describes delta development processes with particular reference to Cimanuk Delta in Indonesia. Cimanuk river delta, the most rapidly growing river delta in Indonesia, is located on the northern coast of Java Island. The delta is subject to ocean waves of less than 1 m height due to its position in the semi‐enclosed Java Sea in the Indonesian archipelago. The study has been carried out using a hydrodynamic model that accounts for sediment movement through the rivers and estuaries. As an advanced approach to management of river deltas, a numerical model, namely MIKE‐21, is used as a tool in the management of Cimanuk river delta. From calibration and verification of hydrodynamic model, it was found that the best value of bed roughness was 0·1 m. For the sediment‐transport model, the calibration parameters were adjusted to obtain the most satisfactory results of suspended sediment concentration and volume of deposition. By comparing the computed and observed data in the calibration, the best values of critical bed shear stress for deposition, critical bed shear stress for erosion and erosion coefficient were 0·05 N m^?2, 0·15 N m^?2, and 0·00001 kg m^?2 s^?1, respectively. The calibrated model was then used to analyse sensitivity of model parameters and to simulate delta development during the periods 1945–1963 and 1981–1997. It was found that the sensitive model parameters were bed shear stresses for deposition and erosion, while the important model inputs were river suspended sediment concentration, sediment characteristics and hydrodynamic. The model result showed reasonable agreement with the observed data. As evidenced by field data, the mathematical model proves that the Cimanuk river delta is a river‐dominated delta because of its protrusion pattern and very high sediment loads from the Cimanuk river. It was concluded that 86% of sediment load from the Cimanuk river was deposited in the Cimanuk delta. Copyright © 2008 John Wiley & Sons, Ltd.     

Spatial prediction and modeling of soil salinity using simple cokriging,artificial neural networks,and support vector machines in El Outaya plain,Biskra, southeastern Algeria

Soil salinization is one of the most predominant environmental hazards responsible for agricultural land degradation, especially in the arid and semi-arid regions.An accurate spatial prediction and modeling of soil salinity in agricultural land are so important for farmers and decision-makers to develop the appropriate mechanisms to prevent the loss of fertile soil and increase crop production.El Outaya plain is marked by soil salinity increases due to the excessive use of poor groundwater quality for irrigation. This study aims to compare the performance of simple kriging, cokriging(SCOK), multilayer perceptron neural networks(MLP-NN), and support vector machines(SVM)in the prediction of topsoil and subsoil salinity. The field covariates including geochemical properties of irrigation groundwater and physical properties of soil and environmental covariates including digital elevation model and remote sensing derivatives were used as input candidates to SCOK, MLP-NN, and SVM. The optimal input combination was determined using multiple linear stepwise regression(MLSR). The results revealed that the SCOK using field covariates including water electrical conductivity(ECw) and sand percentage(sand %), and environmental covariates including land surface temperature(LST), topographic wetness index(TWI), and elevation could significantly increase the accuracy of soil salinity spatial prediction. The comparison of the prediction accuracy of the different modeling techniques using the Taylor diagram indicated that MLP-NN using LST, TWI, and elevation as inputs were more accurate in predicting the topsoil salinity [ECs(TS)] with a mean absolute error(MAE) of 0.43, root mean square error(RMSE) of 0.6 and correlation coefficient of 0.946. MLP-NN using ECw and sand % as inputs were more accurate in predicting the subsoil salinity [ECs(SS)] with MAE of 0.38, RMSE of0.6, and R of 0.968.     

NUMERICAL MODELING OF THE SEABED MORPHOLOGY OF THE SUBAQUEOUS YELLOW RIVER DELTA

1 wrsoorCnoxThe Yenow mver delta is ereated by the river transponing sediment bom the Loess Plateau to the shallOWBOhai Gulf during the paSt l45 years. lh recent years, the water discharge and sediment load enedg thesea have bein ched dramacaily The river end chann shital northeastWed hom QingshulgOuN to qngshulgou-Chah chaDnel in 1996, resulting in a new regfor of sedimenboon and erosion ofthe subaqucous delta.,A nUInerial model for river sediInen dispersion and seabed mOrPhofogy of t…