River Suspended Sediment Load Research Articles

Mode decomposition based large margin distribution machines for sediment load prediction

Precise suspended sediment load (SSL) prediction is essential for irrigation, hydropower and river management practices. But due to some external factors such as high altitude, heavy monsoon and tropical climate conditions, the data we collect may contain noisy samples. Hence, it becomes a challenging task to accurately predict the SSL in rivers. Therefore, to diminish the influence of noise, the empirical mode decomposition (EMD) -based techniques can be adopted. Moreover, the large margin distribution machine-based regression (LDMR) can deal efficiently with noisy datasets as it simultaneously minimizes the insensitive loss as well as quadratic loss. The significance of this work lies in its contribution to improving the accuracy of suspended sediment load (SSL) prediction in rivers, which has practical implications for various applications such as irrigation, hydropower, and river management. We recognize the challenges posed by external factors, which introduce noise into the collected data, making accurate prediction of SSL difficult. Overall, the significance of this work lies in its novel integration of EMD-based techniques and LDMR-based models, which address the challenges posed by noisy and non-stationary sediment load data. The findings contribute to the field of SSL prediction, offering practical solutions for managing and utilizing river resources more effectively in various domains. The main advantage of the least squares LDMR (LS-LDMR) approach is that it solves a system of linear equations rather than solving a large QPPs unlike SVR, TSVR, LDMR, which makes it computationally efficient. It is well known that the sediment load data is complex and non-stationary in nature. Therefore, for daily SSL prediction, the LDMR and least squares LDMR (LSLDMR) models are embedded with two different decomposition techniques, EMD and ensemble EMD (EEMD), to handle the nonlinear and non-stationary characteristics of sediment load data on the forecasted outputs and to increase prediction ability. The results of the proposed EMD-LDMR, EEMD-LDMR, EMD-LSLDMR and EEMD-LSLDMR are compared with the conventional support vector regression (SVR), twin SVR (TSVR), LDMR and LSLDMR. The performance of the evaluated using the best-fit model using the mean absolute error (MAE), root mean square error (RMSE), symmetric mean absolute percentage error (SMAPE), Willmott’s index (WI), correlation coefficient (CC) and R2. Better or comparable results specify the efficiency of the suggested models. For graphical visualization, scatterplots, prediction error plots and violin plots are shown. Numerical results show that these hybrid models show excellent prediction performance. The overall analysis of the results suggests using EEMD-LSLDMR for SSL estimation.

A comparison of machine learning models for suspended sediment load classification

The suspended sediment load (SSL) is one of the major hydrological processes affecting the sustainability of river planning and management. Moreover, sediments have a significant impact on dam operation and reservoir capacity. To this end, reliable and applicable models are required to compute and classify the SSL in rivers. The application of machine learning models has become common to solve complex problems such as SSL modeling. The present research investigated the ability of several models to classify the SSL data. This investigation aims to explore a new version of machine learning classifiers for SSL classification at Johor River, Malaysia. Extreme gradient boosting, random forest, support vector machine, multi-layer perceptron and k-nearest neighbors classifiers have been used to classify the SSL data. The sediment values are divided into multiple discrete ranges, where each range can be considered as one category or class. This study illustrates two different scenarios related to the number of categories, which are five and 10 categories, with two time scales, daily and weekly. The performance of the proposed models was evaluated by several statistical indicators. Overall, the proposed models achieved excellent classification of the SSL data under various scenarios.

Assessment of Soft Computing Techniques for the Prediction of Suspended Sediment Loads in Rivers

A key goal of sediment management is the quantification of suspended sediment load (SSL) in rivers. This research focused on a comparison of different means of suspended sediment estimation in rivers. This includes sediment rating curves (SRC) and soft computing techniques, i.e., local linear regression (LLR), artificial neural networks (ANN) and the wavelet-cum-ANN (WANN) method. Then, different techniques were applied to predict daily SSL at the Pirna and Magdeburg Stations of the Elbe River in Germany. By comparing the results of all the best models, it can be concluded that the soft computing techniques (LLR, ANN and WANN) better predicted the SSL than the SRC method. This is due to the fact that the former employed non-linear techniques for the data series reconstruction. The WANN models were the overall best performer. The WANN models in the testing phase showed a mean R2 of 0.92 and a PBIAS of −0.59%. Additionally, they were able to capture the suspended sediment peaks with greater accuracy. They were more successful as they captured the dynamic features of the non-linear and time-variant suspended sediment load, while other methods used simple raw data. Thus, WANN models could be an efficient technique to simulate the SSL time series because they extract key features embedded in the SSL signal.

Land-Use/-Cover Changes and Their Effect on Soil Erosion and River Suspended Sediment Load in Different Landscape Zones of European Russia during 1970–2017

Contemporary trends in cultivated land and their influence on soil/gully erosion and river suspended sediment load were analyzed by various landscape zones within the most populated and agriculturally developed part of European Russia, covering 2,222,390 km2. Based on official statistics from the Russian Federation and the former Soviet Union, this study showed that after the collapse of the Soviet Union in 1991, there was a steady downward trend in cultivated land throughout the study region. From 1970–1987 to 2005–2017, the region lost about 39% of its croplands. Moreover, the most significant relative reduction in cultivated land was noted in the forest zone (south taiga, mixed and broadleaf forests) and the dry steppes and the semi-desert of the Caspian Lowland—about 53% and 65%, respectively. These territories are with climatically risky agriculture and less fertile soils. There was also a widespread reduction in agricultural machinery on croplands and livestock on pastures of the region. A decrease in soil/gully erosion rates over the past decades was also revealed based on state hydrological monitoring data on river suspended sediment load as one of the indicators of the temporal variability of erosion intensity in river basins and the published results of some field research in various parts of the studied landscape zones. The most significant reduction in the intensity of erosion and the load of river suspended sediment was found in European Russia’s forest-steppe zone. This was presumably due to a favorable combination of the above changes in land cover/use and climate change.

Implementation of hybrid particle swarm optimization-differential evolution algorithms coupled with multi-layer perceptron for suspended sediment load estimation

River suspended sediment load (SSL) estimation is of importance in water resources engineering and hydrological modeling. In this study, a novel hybrid approach is recommended for SSL estimation in which multi-layer perceptron (MLP) is hybridized with particle swarm optimization (PSO) and then, integrated with differential evolution algorithm (DE) called as MLP-PSODE. The hybrid MLP-PSODE model is implemented to model the SSL of Mahabad river located at northwest of Iran. For the sake of examination of the MLP-PSODE model performance, several techniques including multi-layer perceptron (MLP), multi-layer perceptron integrated with particle swarm optimization (MLP-PSO), radial basis function (RBF) and support vector machine (SVM) are selected as benchmarks. For this purpose, five different scenarios are considered for the modeling. The results indicated that the new hybrid model of MLP-PSODE is successful in estimating SSL by considering single input of discharge (Q) with high accuracy as compared to its alternatives with RMSE = 1794.4 ton·day−1, MAPE = 41.50% and RRMSE = 107.09%, which were much lower than those of MLP based model with RMSE = 3133.7 ton·day−1, MAPE = 121.40% and RRMSE = 187.03%. The developed MLP-PSODE model, not only outperforms its counterparts in terms of accuracy in extreme values estimation, but also it is found as a parsimonious model that incorporates lower number of input parameters in its structure for SSL estimation.

Iterative classifier optimizer-based pace regression and random forest hybrid models for suspended sediment load prediction.

Suspended sediment load is a substantial portion of the total sediment load in rivers and plays a vital role in determination of the service life of the downstream dam. To this end, estimation models are needed to compute suspended sediment load in rivers. The application of artificial intelligence (AI) techniques has become popular in water resources engineering for solving complex problems such as sediment transport modeling. In this study, novel integrative intelligence models coupled with iterative classifier optimizer (ICO) are proposed to compute suspended sediment load in Simga station in Seonath river basin, Chhattisgarh State, India. The proposed models are hybridization of the random forest (RF) and pace regression (PR) models with the iterative classifier optimizer (ICO) algorithm to develop ICO-RF and ICO-PR hybrid models. The recommended models are established using the discharge and sediment daily data spanning a 35-year period (1980-2015). The accuracy of the developed models is examined in terms of error; by root mean square error (RMSE) and mean absolute error (MAE); and based on a correlation index of determination coefficient (R2). The proposed novel hybrid models of ICO-RF and ICO-PR have been found to be more precise than their stand-alone counterparts of RF and PR. Overall, ICO-RF models delivered better accuracy than their alternatives. The results of this analysis tend to claim the appropriateness of the implemented methodology for precise modeling of the suspended sediment load in rivers.

A coiflet LDMR and coiflet OB-ELM for river suspended sediment load prediction

The forecast of suspended sediment load in a river is a complicated task due to different parameters such as tropical climate, excessive precipitation, transport, etc. The wavelet transformation strategy helps to investigate time and frequency information for estimating SSL by decomposing data into separate sub-series. More recently, several works were performed for SSL forecasting using several wavelet conjunction models. In this work, two conjunction models are proposed and applied for SSL forecast: coiflet wavelet-based large margin distribution machine-based regression and coiflet wavelet-based optimization method-based extreme learning machine in SSL dataset of Tawang Chu river, India. The results are compared with twin support vector regression, large margin distribution machine-based regression, optimization-based extreme learning machine and very recently proposed coiflet wavelet-based twin support vector regression models. The performance is assessed using the best-fit model using mean absolute, root mean square and symmetric mean absolute percentage error. Experimental outcomes indicate the effectiveness and usability of proposed models.

Monthly suspended sediment load prediction using artificial intelligence: testing of a new random subspace method

ABSTRACT The predictive capability of a new artificial intelligence method, random subspace (RS), for the prediction of suspended sediment load in rivers was compared with commonly used methods: random forest (RF) and two support vector machine (SVM) models using a radial basis function kernel (SVM-RBF) and a normalized polynomial kernel (SVM-NPK). Using river discharge, rainfall and river stage data from the Haraz River, Iran, the results revealed: (a) the RS model provided a superior predictive accuracy (NSE = 0.83) to SVM-RBF (NSE = 0.80), SVM-NPK (NSE = 0.78) and RF (NSE = 0.68), corresponding to very good, good, satisfactory and unsatisfactory accuracies in load prediction; (b) the RBF kernel outperformed the NPK kernel; (c) the predictive capability was most sensitive to gamma and epsilon in SVM models, maximum depth of a tree and the number of features in RF models, classifier type, number of trees and subspace size in RS models; and (d) suspended sediment loads were most closely correlated with river discharge (PCC = 0.76). Overall, the results show that RS models have great potential in data poor watersheds, such as that studied here, to produce strong predictions of suspended load based on monthly records of river discharge, rainfall depth and river stage alone.

A comparative study of artificial intelligence models for predicting monthly river suspended sediment load

A comparative study of artificial intelligence models for predicting monthly river suspended sediment load

River suspended sediment load prediction based on river discharge information: application of newly developed data mining models

ABSTRACTSuspended sediment load (SSL) is one of the essential hydrological processes that affects river engineering sustainability. Sediment has a major influence on the operation of dams and reservoir capacity. This investigation is aimed at exploring a new version of machine learning models (i.e. data mining), including M5P, attribute selected classifier (AS M5P), M5Rule (M5R), and K Star (KS) models for SSL prediction at the Trenton meteorological station on the Delaware River, USA. Different input scenarios were examined based on the river flow discharge and sediment load database. The performance of the applied data mining models was evaluated using various statistical metrics and graphical presentation. Among the applied data mining models, the M5P model gave a superior prediction result. The current and one-day lead time river flow and sediment load were the influential predictors for one-day-ahead SSL prediction. Overall, the applied data mining models achieved excellent predictions of the SSL process.

The Feasibility of Integrative Radial Basis M5Tree Predictive Model for River Suspended Sediment Load Simulation

Accurate suspended sediment transport prediction is highly significant for multiple river engineering sustainability. Conceptually evidenced, sediment load transport is highly stochastic, spatial distributed and redundant pattern due to the incorporation of various hydrological and morphological variables such as river flow discharge and sediment physical properties. The motivation of this study is to explore the feasibility of newly intelligent model called Radial basis M5 model tree (RM5Tree) for suspended sediment load (St) prediction for daily scale information at Trenton hydrological station, Delaware River. Numerous input combination attributes are formulated based on the preceding information of sediment and river flow discharge. The prediction accuracy “based statistical and graphical visualizations” of the proposed model validated against numerous well-established predictive models including response surface method (RSM), artificial neural network (ANN) and classical M5Tree based models. The investigated input combinations behaved differently from one case to another. The optimum input combination attributes are included two months lead times of sediment and discharge information to predict one step ahead St. The attained results of the proposed RM5Tree model exhibited a remarkable prediction accuracy with minimal values of root mean square error (RMSE≈2091 ton/day) and coefficient of determination (R2≈0.86). This presenting a percentage of enhancement in the prediction accuracies by (51.6, 53.1 and 26.3) over (RSM, ANN and M5Tree) optimal models over the testing phase.

A comparison of artificial intelligence models for the estimation of daily suspended sediment load: a case study on the Telar and Kasilian rivers in Iran

Abstract The estimation of the suspended sediment load in rivers is one of the main issues in hydraulic engineering. Different traditional methods such as the sediment rating curve (SRC) can be used to estimate the suspended sediment load of rivers. The main problem with this method is its low accuracy and uncertainty. In this study, the ability of three intelligence models namely: gene expression programming (GEP), artificial neural networks (ANN) and adaptive neuro fuzzy inference system (ANFIS) were compared with the SRC method. The daily flow discharge and sediment discharge at two hydrometric stations of the Kasilian and Telar rivers in the period of 1964–2014 were used to develop intelligence models. The performance of these methods indicated that all intelligence models give reliable results in the estimation of the suspended sediment load and their performance was better than the SRC method. Moreover, results showed that the GEP model with a high coefficient of determination (R2) and a low mean absolute error (MAE) was better than both the ANN and ANFIS models for the estimation of daily suspended sediment load of the two sub-basins of the Kasilian and Telar rivers.

Comparison of River Suspended Sediment Load Estimation, using Regression and GA Methods

Comparison of River Suspended Sediment Load Estimation, using Regression and GA Methods

Great expectations: Flow restoration and sediment transport in the Waimea River, Kaua'i

Conventional and novel observations made in the Waimea River basin between 1960 and 1995 permit the total riverine mass flux to be estimated and the influence that flow restoration will have on sediment dynamics in the river's lower reaches to be assessed. Flows between the threshold for sediment transport (~6.0 m3 s−1) and the most effective flow (80.7 m3 s−1) recur annually and transport ~60% of the Waimea River's suspended sediment load. Discharges of this magnitude essentially were unaffected by plantation era agricultural diversions of 2.3 ± 0.7 m3 s−1. The modern-day mass flux from the Waimea River basin is 155 ± 38 t km−2 y−1, and comparison with an independent cosmogenic nuclide-based estimate implies that it has remained at about this level for the past 10 ky. Previous work indicated that: (i) most of the sand the Waimea River transports to the coast is derived from steep, rapidly eroding, sparsely vegetated, bedrock-dominated hillslopes; and (ii) the sediment transport regime of the Waimea River is supply-limited at very high discharges (recurrence interval > 2.5 years). Consequently, major floods tend to remove sand from the estuary. Climate change has caused a statewide decline in heavy rainfall, and a commensurate decline in the magnitude of peak flows in the basin's pristine, undiverted headwaters over the past 97 years. The effect this secular change in climate presently is having on streamflow was foreshadowed in the late 1970s by a naturally occurring, warm Pacific Decadal Oscillation phase reduction in the magnitude of flows with low exceedance probabilities. Additionally, the controlling base level at the river mouth has risen and been displaced seaward. Simple proportionality approximations show that, for a constant sediment supply, aggradation will occur if either the magnitude of flows with a low exceedance probability declines and/or base level rises. Thus, anthropogenic stresses on Waimea River's lower reaches are not derived from the within-basin influence agricultural diversions exert on the flow regime and will not be resolved by restoring flow to the river. These stresses primarily accrue from extrinsic factors that will continue to influence the river's hydrologic and sediment transport regimes until global, offsetting, climate-ameliorating measures are implemented.

Evaluation of different types of artificial intelligence methods to model the suspended sediment load in Tigris River

Modeling of suspended sediment load in rivers has a major role in a proper management of water resources. Artificial intelligence has been identified as an efficient way to model the complex nonlinear hydrological relationship. In this study, Adaptive Neuro Fuzzy Inference System (ANFIS), in addition to two different kinds of Artificial Neural Network (ANN) i.e. feedforward and radial basis networks were used and compared to model the suspended sediment load (SSL) in Tigris River-Baghdad using the streamflow discharge as input. To this end, an intermittent data of SSL and streamflow were collected over the period 1962-1981 from Sarai station in Baghdad. 70 % of these data was used to calibrate (train) the networks and the remaining 30% for the validation (test). The coefficient of determination (R2), root mean square error (RMSE), and Nash and Sutcliffe model efficiency coefficient (NSE) were used to judge whether the observed and modelled data belong to the same distribution. Results revealed that the ANFIS model outperform the other methods. R2, RMSE, and NSE of ANFIS during the calibration phase were equal to 0.58, 75617, and 0.58, respectively and during the validation were 0.72, 27944, and 0.59, respectively. Therefore, ANFIS approach is recommended to estimate the river suspended sediment load.

Impact of Normalization and Input on ARMAX-ANN Model Performance in Suspended Sediment Load Prediction

The suspended sediment load in rivers is an important parameter in watershed planning and management. Since daily suspended sediment time series contain linear and nonlinear components, existing prediction models are associated with limitations. Therefore, this study introduces a new hybrid model comprising two commonly used stochastic and nonlinear models. The sediment load is first modeled by an autoregressive-moving average with exogenous terms (ARMAX) model. Subsequently, the ARMAX residuals are modeled with an artificial neural network (ANN). For this purpose, discharge (Q) and sediment (S) are considered as model input parameters. Three modeling scenarios are defined to investigate the impact of data normalization on the hybrid model. The exponential and Box-Cox transformation methods are combined into a new data normalization method called mixed transformation. The performance of these methods is then compared. In addition, the impact of the type and number of input combinations on ARMAX-ANN model accuracy is evaluated. To this end, 12 input combinations and 1331 ARMAX and ANN models are verified. The ARMAX model inputs include S, Q and the white noise disturbance term (e), while the ANN model inputs include the ARMAX model results and residuals. Moreover, the hybrid model’s accuracy is compared with the ARMAX and ANN models.

A reassessment of the suspended sediment load in the Madeira River basin from the Andes of Peru and Bolivia to the Amazon River in Brazil, based on 10 years of data from the HYBAM monitoring programme

The Madeira River is the second largest tributary of the Amazon River. It contributes approximately 13% of the Amazon River flow and it may contribute up to 50% of its sediment discharge to the Atlantic Ocean. Until now, the suspended sediment load of the Madeira River was not well known and was estimated in a broad range from 240 to 715Mtyr−1. Since 2002, the HYBAM international network developed a new monitoring programme specially designed to provide more reliable data than in previous intents. It is based on the continuous monitoring of a set of 11 gauging stations in the Madeira River watershed from the Andes piedmont to the confluence with the Amazon River, and discrete sampling of the suspended sediment concentration every 7 or 10days. This paper presents the results of the suspended sediment data obtained in the Madeira drainage basin during 2002–2011. The Madeira River suspended sediment load is estimated at 430Mtyr−1 near its confluence with the Amazon River. The average production of the Madeira River Andean catchment is estimated at 640Mtyr−1 (±30%), the corresponding sediment yield for the Andes is estimated at 3000tkm−2yr−1 (±30%), and the average denudation rate is estimated at 1.20mmyr−1 (±30%). Contrary to previous results that had mentioned high sedimentation rates in the Beni River floodplain, we detected no measurable sedimentation process in this part of the basin. On the Mamoré River basin, we observed heavy sediment deposition of approximately 210Mtyr−1 that seem to confirm previous studies. But while these studies mentioned heavy sedimentation in the floodplain, we showed that sediment deposition occurred mainly in the Andean piedmont and immediate foreland in rivers (Parapeti, Grande, Pirai, Yapacani, Chimoré, Chaparé, Secure, Maniqui) with discharges that are not sufficiently large to transport their sediment load downstream in the lowlands.

Ensemble Wavelet-Support Vector Machine Approach for Prediction of Suspended Sediment Load Using Hydrometeorological Data

Explicit prediction of the suspended sediment loads in rivers or streams is very crucial for sustainable water resources and environmental systems. Suspended sediments are a governing factor for the design and operation of hydraulic structures, like canals, diversions and dams. In recent decades, to model hydrological phenomena which are complex in nature the machine learning models are used commonly. In the present study, support vector machine (SVM) with wavelet transform (WASVM) has been employed for prediction of daily suspended sediment load (SL) for two south Indian watersheds (Marol and Muneru) using hydrometeorological data. A 40-year daily observed data (1972–2011) have been used for the analysis, where past SL, streamflow (Q), and rainfall (R) data were used as the model inputs, and SL was the model output. Using conventional correlation coefficient analysis between input and output variables, the best input of WASVM model was identified. The reliability of SVM and WASVM models were evaluated on the basis of different performance criteria, i.e., coefficient of determination (R2), root mean square error (RMSE), normalized mean square error (NMSE), and Nash-Sutcliffe coefficient (NS). Initially, 1-day ahead SL prediction was performed using the best WASVM model. The results showed that, 1-day predictions were very precise, showing a close agreement with the observed SL data (R2=0.94, NS=0.94 for the Marol watershed, and R2=0.77, NS=0.77 for the Muneru watershed) in the testing period. The same WASVM model was then used for the prediction of SL for the higher lead periods. The NMSE value for the Marol watershed was found as low as 0.06 for 1-day ahead prediction, and increases subsequently as 0.29, 0.46, and 0.70 for 3-, 6-, and 9-day higher leads, respectively. Likewise, for the Muneru watershed, the NMSE value was found as low as 0.21 for 1-day ahead prediction, and increases subsequently as 0.42, 0.53, and 0.68 for 3-, 6-, and 9-day higher leads, respectively. Further, the model was evaluated on the basis of its capability of predicting peak SL and cumulative SL for 1- to 6-day leads. The statistical analysis shows that the developed WASVM model can predict the target value successfully up to a 6-day lead and is not suitable for higher lead specifically in the selected watersheds having similar hydroclimatic conditions like the ones selected in this study. Predictions by the WASVM model were found significantly superior to the ones obtained by the conventional SVM model. The results revealed that the WASVM model provides a very good accuracy in predicting SL and can be used as an effective forecasting tool for hydrological applications.

A combined use of acoustic and optical devices to investigate suspended sediment in rivers

The use of acoustic and optic devices has become more and more common for estimating suspended sediment loads in rivers. The echo intensity levels (EIL) recorded by means of an Acoustic Doppler Current Profiler (ADCP) have been applied in different methods, which provided relationships between scattering particles features derived from samples (i.e., concentration and grain size) and corresponding backscattering strength and sound attenuation. At the same time, the laser diffraction was applied by an in-stream sampler (LISST-SL) to measure suspended sediment concentration and the corresponding particle size distribution (PSD). These two techniques exhibited different limitations in terms of the measured range of concentration, sensitivity to a certain spectrum of particle sizes, and instruments deploy feasibility especially in large rivers, in a way that the use of sampled PSD by LISST-SL to validate ADCP methods may not be trivial. The aim of this study was to combine the vertical profiling of EIL by an ADCP with results from LISST-SL, eventually demonstrating the possibility of using moving ADCP measurements to detect different suspended matters along a Danube River section characterized by a small tributary junction. At the same time, this work elucidates optical to acoustic method deviations that hinders an actual validation of ADCP methods based on LISST-SL rather than with physical samplings.

Prediction of suspended sediment load using ANN GA conjunction model with Markov chain approach at flood conditions

Development of cities, destruction of forests and pastures, population growth and other factors have increased suspended sediment load in rivers of developing countries. Measurement of suspended sediment load is a challenging issue for engineers at flood conditions. The case study of this research is Idenak hydrometric station on the Marun River in the south west of Iran. The used data consists of 42 years (1968 to 2009) flood discharge. A perceptron artificial neural network is trained and validated by observed data. For training of Artificial Neural Network (ANN), momentum and Levenberg-Marquardt training methods are applied. For decreasing of Normalized Mean Square Error (NMSE) and increasing of correlation coefficient (R), parameters of ANN are optimized by Genetic Algorithm (GA) method. GA method optimizes the number of nodes of hidden layers of ANN that is trained by Levenberg-Marquardt training method while it optimizes the number of nodes and momentum of ANN that is trained by momentum training method. GA method can reduce NMSE to 80% while GA method doesn’t increase R significantly. In order to predict flood condition, the Markov chain method is applied. The results show that suspended sediment load may be increased almost from 400000 ton/day to 800000 ton/day at future.