Suspended Sediment Estimation Research Articles

A brief review of recent global trends in suspended sediment estimation studies

A brief review of recent global trends in suspended sediment estimation studies

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.

Advanced machine learning models development for suspended sediment prediction: comparative analysis study

Accurate estimation of suspended sediment (SS) is very essential for planning and management of hydraulic structures. The study investigates the accuracy of four machine learning methods, dynamic evolving neural-fuzzy inference systems (DENFIS), fuzzy c-means based adaptive neuro fuzzy system (ANFIS-FCM), multivariate adaptive regression spline (MARS) and M5 model tree (M5Tree), in estimating suspended sediments. Several input scenarios including streamflow (Q) and sediment (S) data obtained from Ain Hamara Station in Wadi Abd basin, Algeria were constructed to find the most effective one. The research results indicate that the DENFIS model with current streamflow (Qt) and 1 previous sediment (St-1) values performs superior to the other alternatives in SS estimation; it increases the efficiency of the best ANFIS-FCM, MARS and M5Tree by 1.6%, 15.7% and 9.6% with respect to RMSE (root mean square error), respectively. Variation of Q and S data on models’ estimation ability was also investigated and it was found that the variation input considerably increase the prediction ability of MARS method; increments in RMSE and MAE (mean absolute error) are by 10.8 and 4.9% and decrement in NSE (Nash-Sutcliffe efficiency) is by 12.9%.

Suspended Sediment Modeling Using a Heuristic Regression Method Hybridized with Kmeans Clustering

The accurate estimation of suspended sediments (SSs) carries significance in determining the volume of dam storage, river carrying capacity, pollution susceptibility, soil erosion potential, aquatic ecological impacts, and the design and operation of hydraulic structures. The presented study proposes a new method for accurately estimating daily SSs using antecedent discharge and sediment information. The novel method is developed by hybridizing the multivariate adaptive regression spline (MARS) and the Kmeans clustering algorithm (MARS–KM). The proposed method’s efficacy is established by comparing its performance with the adaptive neuro-fuzzy system (ANFIS), MARS, and M5 tree (M5Tree) models in predicting SSs at two stations situated on the Yangtze River of China, according to the three assessment measurements, RMSE, MAE, and NSE. Two modeling scenarios are employed; data are divided into 50–50% for model training and testing in the first scenario, and the training and test data sets are swapped in the second scenario. In Guangyuan Station, the MARS–KM showed a performance improvement compared to ANFIS, MARS, and M5Tree methods in term of RMSE by 39%, 30%, and 18% in the first scenario and by 24%, 22%, and 8% in the second scenario, respectively, while the improvement in RMSE of ANFIS, MARS, and M5Tree was 34%, 26%, and 27% in the first scenario and 7%, 16%, and 6% in the second scenario, respectively, at Beibei Station. Additionally, the MARS–KM models provided much more satisfactory estimates using only discharge values as inputs.

Superiority of Hybrid Soft Computing Models in Daily Suspended Sediment Estimation in Highly Dynamic Rivers

Estimating sediment flow rate from a drainage area plays an essential role in better watershed planning and management. In this study, the validity of simple and wavelet-coupled Artificial Intelligence (AI) models was analyzed for daily Suspended Sediment (SSC) estimation of highly dynamic Koyna River basin of India. Simple AI models such as the Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were developed by supplying the original time series data as an input without pre-processing through a Wavelet (W) transform. The hybrid wavelet-coupled W-ANN and W-ANFIS models were developed by supplying the decomposed time series sub-signals using Discrete Wavelet Transform (DWT). In total, three mother wavelets, namely Haar, Daubechies, and Coiflets were employed to decompose original time series data into different multi-frequency sub-signals at an appropriate decomposition level. Quantitative and qualitative performance evaluation criteria were used to select the best model for daily SSC estimation. The reliability of the developed models was also assessed using uncertainty analysis. Finally, it was revealed that the data pre-processing using wavelet transform improves the model’s predictive efficiency and reliability significantly. In this study, it was observed that the performance of the Coiflet wavelet-coupled ANFIS model is superior to other models and can be applied for daily SSC estimation of the highly dynamic rivers. As per sensitivity analysis, previous one-day SSC (St-1) is the most crucial input variable for daily SSC estimation of the Koyna River basin.

Estimation of behavioral change of SSC of bed profile in the river using ADCP

Suspended sediment concentration (SSC) is one of the remarkable parameters for sediment transport calculation and their estimation. In another hand, the use of the conventional method comes with lots of limitations as compared to acoustic Doppler current profiler (ADCP). It is frequently used for velocity measurement and concentration of suspended sediment estimation (in dB) with the help of acoustic backscatter intensity. In present studying ADCP of 1200 kHz is used along with water sampler. A study area of river Ganga along Varanasi (length 10 km) is divided into six cross-sections for analysis. Suspended samples have been collected for SSC calculation in terms of mg/l. These samples were categorized into two parts; the first part was utilized for calibrating the backscatter and attributing the intensity to suspended particle concentration using a linear regression method. The second part was used for validation of acoustic intensity. Six years of observation data were used from year 2012 to 2017. As a result of backscatter intensity, it was visible that there is an increase in suspended sediment concentration load year by year along the river cross-section. When the bed profile was created, it was found that the bed profile of study cross-section has drastically changed at Raj Ghat cross-section (CS 6). This type of study is essential where river passing near any city because of the high rate of erosion and deposition may change the bed profile; this change can invite natural disaster. Also, this data can be further utilized for developing significant measures for existing Ghats and other hydraulic structures for present and future sustainability.

Comparison and Evaluation of Support Vector Machine and Gene Programming in River Suspended Sediment Estimation (Case Study: Kashkan River)

Comparison and Evaluation of Support Vector Machine and Gene Programming in River Suspended Sediment Estimation (Case Study: Kashkan River)

Prediction of Suspended Sediment Load Using Data-Driven Models

Estimation of suspended sediments carried by natural rivers is essential for projects related to water resource planning and management. This study proposes a dynamic evolving neural fuzzy inference system (DENFIS) as an alternative tool to estimate the suspended sediment load based on previous values of streamflow and sediment. Several input scenarios of daily streamflow and suspended sediment load measured at two locations of China—Guangyuan and Beibei—were tried to assess the ability of this new method and its results were compared with those of the other two common methods, adaptive neural fuzzy inference system with fuzzy c-means clustering (ANFIS-FCM) and multivariate adaptive regression splines (MARS) based on three commonly utilized statistical indices, root mean square error (RMSE), mean absolute error (MAE), and Nash–Sutcliffe efficiency (NSE). The data period covers 01/04/2007–12/31/2015 for the both stations. A comparison of the methods indicated that the DENFIS-based models improved the accuracy of the ANFIS-FCM and MARS-based models with respect to RMSE by 33% (32%) and 31% (36%) for the Guangyuan (Beibei) station, respectively. The NSE accuracy for ANFIS-FCM and MARS-based models were increased by 4% (36%) and 15% (19%) using DENFIS for the Guangyuan (Beibei) station, respectively. It was found that the suspended sediment load can be accurately estimated by DENFIS-based models using only previous streamflow data.

Two calibration methods for modeling streamflow and suspended sediment with the swat model

The proper estimation of streamflow (Q) and suspended sediment (SS) have important implications for sustainable water management. The Soil and Water Assessment Tool (SWAT) is a distributed, physically-based and dynamic model that integrates water quantity and quality routines. SWAT is considered an effective tool for assessing water and soil resources problems in a worldwide range of environmental conditions; however every hydrological model application is limited by the choices made in the calibration process. The aim of this paper was to assess the differences between the sequential and simultaneous calibration methods when simulating streamflow and suspended sediment with SWAT. We used the Sequential Uncertainty Fitting (SUFI-2) combined with SWAT for: (i) sensitivity analysis; (ii) parameter calibration using Q and SS data with a combined multi-site and multi-objective approaches; and (iii) evaluation of the differences in the estimated uncertainty of both calibration methods. Our results suggest that the simultaneous calibration was more accurate, especially for SS values with King-Gupta Efficiency (KGE) objective function. The simultaneous calibration was less time consuming and the sensitivity analysis indicated that it needed less parameters in the calibration process. The multi-site calibration method improved the model results in 3 out of 4 simulations of suspended sediment in the basin outlet.

Estimation of suspended sediment and dissolved solid load in a Mediterranean semiarid karst stream using log-linear models

Abstract Many models have been developed to predict the sediment transport in watercourses. This paper attempts to test the effectiveness of log-linear models (LLM) to estimate the suspended (S-LMM), dissolved (D-LLM), and total suspended (T-LLM) load into a Mediterranean semiarid karst stream (the Argos River basin, in southeast Spain). An assessment of the supposed validity of each model and a leave-one-out cross-validation were carried out to determine their degree of statistical robustness. The T-LLM model showed higher prediction accuracy (R2 = 0.98, RMSE = 0.15, and PE = ±5.4–6.6%) than the D-LLM model (R2 = 0.97, RMSE = 0.16, and PE = ±5.5–6.8%) or the D-LLM model (R2 = 0.77, RMSE = 0.71, and PE = ±101–493%). In addition, different model variants, according to two flow patterns (FP1 = base flow and FP2 = rising water level), were developed. The FP2-SLLM model provided a very good fit (R2 = 0.94, RMSE = 0.34, and PE = ±25.3–61.5%), substantially improving the results of the S-LLM model.

Multi-depth suspended sediment estimation using high-resolution remote-sensing UAV in Maumee River, Ohio

ABSTRACTSatellite remote-sensing has been widely used to map suspended sediment concentration (SSC) in waterbodies. Current development of the unmanned aerial vehicle (UAV) technology allows mapping of SSC at finer spatial resolution providing high flexibility in terms of cost and acquisition time. However, the technology is immature and transfer of empirical algorithms from existing remote-sensing technologies to UAV still has to be explored. This study uses the MicaSense Sequoia sensor with four bands (green, red, red edge, and near-infrared [NIR]) mounted on-board a fixed-wing UAV to map SSC within the Maumee River in Ohio, USA, at multiple depth intervals (15, 61, 91, and 182 cm). The simple linear and stepwise regression models show the advantage of multiple bands and band ratios over single bands in mapping SSC. The findings show a limited performance of the Sequoia sensor when compared to field spectroradiometer measurements. In all cases but one, the adjusted coefficient of determination () values is lower for the UAV data. The regression equations become similar at and below a depth of 0–61 cm, and become constant at and below a depth of 0–91 cm. While the spectroradiometer-related equations are sensitive to a wider spectral range (from green at the surface to NIR wavelength at 182 cm depth), the UAV-related equations are insensitive to green spectrum and they include a narrower spectral range (from red to NIR) over all depth increments. Field spectroradiometer measurements exhibit a strong relationship with cumulative SSC at 182 cm depth (0–182 cm) () whereas UAV reflectance data show the best relationship with SSC at 91 cm (0–91 cm) () suggesting that ~91 cm may be an optimal depth for UAV under given conditions. The results show that UAVs can be a practical but somewhat limited tool to monitor SSC in small- to medium-sized rivers.

Evaluation of neuro-fuzzy and Bayesian techniques in estimating suspended sediment loads

Sediment is considered the largest surface water pollutant by volume, which is crucial for surface water planning and management. Different management scenario evaluations require multiple in-stream suspended sediment forecasts and estimations. Physically-based models are considered to be good modeling techniques for suspended sediment estimation; nevertheless, they require a large number of parameters and intensive calculations. This study aims to enhance suspended sediment predicting techniques using efficient fusion modeling that can be used for evaluations by watershed managers and stakeholders. Adaptive neuro-fuzzy inference system (ANFIS) and Bayesian regression models were tested to find the best alternative to a calibrated and validated Soil and Water Assessment Tool (SWAT) model to predict suspended sediment loads in the Saginaw River watershed. For both methods, four different method-types were tested, namely General, Temporal, Spatial and Spatiotemporal. Results of the study showed that both methods can be used as good alternatives to the SWAT model at the global level for watershed estimations. The best suspended sediment replicating models, the Bayesian Spatiotemporal and ANFIS Spatial, produced results with Nash–Sutcliffe model efficiency values of 0.95 and 0.94, respectively. For the subbasin level, Bayesian and ANFIS techniques showed satisfactory results for 84 and 77 subbasins, respectively, out of 155 subbasins in the watershed. Box-Cox transformation of suspended sediment load values, made the use of the Bayesian model feasible and improved the prediction of the ANFIS models. However, suspended sediment data exhibited a bimodal distribution after transformation, making the modeling process challenging and complex.

Suspended sediment estimation using regression and artificial neural network models: Kebir watershed, northeast of Algeria, North Africa

Suspended sediment estimation using regression and artificial neural network models: Kebir watershed, northeast of Algeria, North Africa

Suspended sediment estimation using regression and artificial neural network models: Kebir watershed, northeast of Algeria, North Africa

The focus of this research was to identify potential equivalences between artificial neural networks and statistical regression and to verify these equivalences when applied to modelling sediment loads in the Kebir river. The use of feed-forward backpropagation neural networks such as MLP and LM were studied by applying relationship stream flow-sediment discharge data and geomorphology watershed parameters. Daily based water and sediment discharge were used as inputs for sediment rating curve and ANNs. In the present study the models were adopted by changing numbers of neuron in hidden layers and epoch. Results have shown that the ANN models were superior in reproducing sediment discharge compared to SRC. The findings further have suggested that LM could provide the most accurate estimates of sediment discharge, (R2 and EF of 0.94) compared to SRC had lower values of R2 and EF (0.89, 0.88), and resulted in underestimations of sediment discharge (−15%).

Remote Sensing Studies of Suspended Sediment Concentration Variation in Barito Delta

The dynamic of suspended sediment concentration in Barito Delta depend on the process in upstream. Agriculture, mining, and illegal logging in Barito River upstream has an effect for suspended sediment concentration in Barito Delta. The objective of research is to estimate the variation of suspended sediment concentration in Barito Delta. The data of research consist of Landsat 7 in year 2011 and measurement result data of suspended sediment concentration both in wet season and dry season in year 2011. Data analysis is regression analysis to estimates the variation of suspended sediment concentration in Barito Delta. The method of research compares three types of spectral transformation for suspended sediment that is Normalized Suspended Material Index (NSMI), Normalized Differences Suspended Sediment Index (NDSSI), and band ratio (green/blue). The result of the transformation is compared with the value of the field measurement. Based on the result of the comparison can be known the suitable type of transformation for the suspended sediment estimation in Barito Delta. The result of research explains that NSMI has the highest value to estimate the variation of suspended sediment concentration in Barito Delta.

A hybrid method for forecasting river-suspended sediments in Iran

ABSTRACTEstimation of sediment mass carried by rivers is an important issue in Hydrological Sciences. The main purpose of this research was to find an appropriate method to compute sediment discharge. Some machine-learning approaches have been used to forecast river-suspended sediments, correctly. One of the most effective and traditional approaches for forecasting events is to use artificial neural networks (ANNs). So, we are going to improve the performance of ANNs in estimation of suspended sediments, upon a data of Baba Aman basin in Iran. We first apply a typical neural network and obtain the root-mean-square-error of and the correlation coefficient of . Then, to improve the prediction ability of ANNs, we hybridize this method with cuckoo optimization algorithm (COA). Combination of ANNs with COA causes reduction in root-mean-square-error to , increasing in correlation coefficient to and also proposing a better model.

Comparison of three persulfate digestion methods for total phosphorus analysis and estimation of suspended sediments

As a result of impairments to fresh surface water quality due to phosphorus enrichment, substantial research effort has been put forth to quantify agricultural runoff phosphorus as related to on-field practices. While the analysis of runoff dissolved phosphorus is well prescribed and leaves little room for variability in methodology, there are several methods and variations of sample preparation reagents as well as analysis procedures for determining runoff total phosphorus. Due to the variation in methodology for determination of total phosphorus and an additional laboratory procedure required to measure suspended solids, the objectives of the current study are to i. compare the performance of three persulfate digestion methods (Acid Persulfate, USGS, and Alkaline Persulfate) for total phosphorus percent recovery across a wide range of suspended sediments (SS), and ii. evaluate the ability of using Al and/or Fe in digestion solution to predict SS as a surrogate to the traditional gravimetric method. Percent recovery of total phosphorus was determined using suspensions prepared from soils collected from 21 agricultural fields in Ohio. The Acid Persulfate method was most effective, with an average total phosphorus percent recovery of 96.6%. The second most effective method was the USGS with an average total phosphorus recovery of 76.1%. However, the Alkaline Persulfate method performed poorly with an average 24.5% total phosphorus recovery. As a result application of Alkaline Persulfate digestion to edge of field monitoring may drastically underestimated runoff total phosphorus. In addition to excellent recovery of total phosphorus, the Acid Persulfate method combined with analysis of Al and Fe by inductively coupled plasma atomic emission spectrometry provides a robust estimate of total SS. Due to the large quantity of samples that can result from water quality monitoring, an indirect measure of total SS could be very valuable when time and budget constraints limit the number of procedures that can be run on a single water sample.

A New Approach for Modeling Sediment-Discharge Relationship: Local Weighted Linear Regression

Accurate estimation of suspended sediment is important for water resources projects. The accuracy of local weighted linear regression (LWLR) technique is investigated in this study for modeling streamflow-suspended sediment relationship. Daily data from two stations on the Eel River in California were used in the applications. In the first part of the study, the LWLR results were compared with those of the least square support vector machine (LSSVM), artificial neural networks (ANNs) and sediment rating curve (SRC) for modeling sediment data of upstream and downstream stations, separately. Root mean square errors (RMSE), mean absolute errors (MAE) and determination coefficient (R2) statistics were used for comparison of the applied models Comparison results indicated that the LWLR model performed better than the LSSVM, ANN and SRC models. Accuracies of the sediment modeling increased by the LWLR model compared with the LSSVM model: 14 % (60 %) and 33 % (42 %) decrease in the RMSE (MAE) values for the upstream and downstream stations, respectively. The second part of the study focused on the comparison of the models in estimating downstream suspended sediment data by using data from both stations. LWLR was found to be better than the LSSVM, ANN and SRC models. The RMSE accuracy of the LSSVM model was increased by 39 % using the LWLR model.

A semi-physical sediment yield model for estimation of suspended sediment in loess region

Sediment yield is a complex function of many environmental factors including climate, hydrology, vegetation, basin topography, soil types, and land cover. We present a new semi-physical watershed sediment yield model for the estimation of suspended sediment in loess region. This model is composed by three modules in slope, gully, and stream phases. For slope sediment yield, a balance equation is established based on the concept of hydraulic erosion capacity and soil erosion resistance capacity. According to the statistical analysis of watershed characteristics, we use an exponential curve to approximately describe the spatial variability of watershed soil erosion resistance capacity. In gully phase, the relationship between gully sediment concentration and flow velocity is established based on the Bagnold׳ stream power function. In the stream phase, we assume a linear dependence of the sediment volume in the reach on the weighted sediment input and output. The proposed sediment yield model is operated in conjunction with a conceptual hydrologic model, and is tested over 16 regions including testing grounds, and small, medium and large watersheds in the loess plateau region in the mid-reach of Yellow River. Our results indicate that the model is reasonable in structure and is able to provide a good simulation of sediment generation and transportation processes at both flood event scale and inter-annual time scale. The proposed model is generally applicable to the watersheds with soil texture similar to that of the loess plateau region in the Yellow River basin in China.

Comparative Study of MLP and RBF Neural Networks for Estimation of Suspended Sediments in Pari River, Perak

Estimation of suspended sediments in rivers using soft computing techniques has been extensively performed around the world since 1990’s. However, accuracy in the results was always found to be highly desired and a profound crucial task. This study presents a thorough comparison between the performances of best basis function of Radial Basis Functions (RBF) and the best training algorithm in Multilayer Perceptron (MLP) neural networks for prediction of suspended sediments in Pari River, Perak, Malaysia. Time series data of water discharge and suspended sediments was used to develop MLP and RBF models. A comparison between six basis functions was performed to identify the most appropriate and best basis function for the selected time series of the river’s data. The performance of the models was compared using several statistical measures including coefficient of determination, coefficient of efficiency and mean absolute error. The performance of the best RBF function was compared with the previously identified best training algorithm of MLP neural networks. The results showed that comparison of various basis functions is always advantageous to achieve the most appropriate basis function for the accurate prediction of the time series data. The results also showed that the performances of both particular RBF and MLP models were close to each other and capable to capture the exact pattern of the sediment data in the river. However, the RBF model showed some inconsistency while predicting the time series data. Furthermore, RBF modeling required more investigation to choose appropriate value for the predefined parameters as compared to MLP modeling.