This study presents a sediment rating curve (SRC), multiple regression (MR), and long short-term memory (LSTM) model for estimating daily suspended sediment concentration (SSC). The data of daily SSC at Yen Thuong and daily flow at five locations in the Ca River Basin, Vietnam are used to demonstrate multiple approaches. Using the daily flow and SSC data in the period from 2009 to 2019, appropriate coefficients in each method are identified carefully using five popular criteria. The results showed that SRC and MR approaches reproduced acceptably the observed values, with the values of RMSE, MAE, and ME of daily SSC being less than 5% of daily SSC magnitude observed at the station, while NSE ranges from 0.47 to 0.63 and r coefficient varies between 0.69 and 0.80. The LSTM model represented the observed values of daily SSC very well. The values of two dimensionless criteria are greater than 0.94 and its values of three-dimensional criteria are smaller than 2.0% of the observed magnitude of daily SSC in both training and validation steps. The LSTM model is found to be the best among the three investigated approaches. Then, the model is applied to estimate daily SSC values for the period from 1969 to 2008 and the year 2020.

  • Multiple approaches were implemented for estimating daily suspended sediment concentration.

  • Sediment rating curve and multiple regression reproduced acceptably the observed values of daily SSC.

  • A very good reproduction of the observed values of daily SSC was obtained when using the LSTM model.

Suspended sediment (SS), generally consisting of fine-grained sediment particles, is an inherent component and important variable in the aquatic environment of rivers. This is because SS can lead to water quality degradation due to the adsorption of different substances (Elskens et al. 2014) and affect riverbed evolution, river navigability, hydraulic structures, and ecological habitats (Walling 1974). The transport of SS inherently indicates complicated process because (i) flow dynamics vary, (ii) there are different sediment sources (e.g., sediments originating from terrestrial erosion in river basins, riverbeds, and riverbanks, as well as sediments re-mobilized from river basins), and (iii) non-linear relationships exist between related variables, geomorphological characteristics of river basins and sediment transport process (Winterwerp 2013; Rajaee & Jafari 2020). Calculation of suspended sediment concentration (SSC) associated with SS transport is essential for environmental protection by promoting water quality, identifying pollution sources, controlling erosion, preserving habitats as well and ensuring the safety and sustainability of infrastructure (Zounemat-Kermani et al. 2016). Moreover, the estimation of SSC is still one of the most difficult issues in hydraulic engineering and water resources management (Afan et al. 2016). Therefore, accurate estimation of SSC associated with SS considering the above sources and physical processes still remains a challenge, although much attention (e.g., Winterwerp 2013; Pham Van et al. 2016; Yilmaz et al. 2018) has been paid to the study and calculation of SSC at different time scales (daily or monthly).

Since the transport of SS is a complex physical process, SSC can be estimated using either physical-based or data-driven models with different levels of complexity and efficiency (e.g., Paniconi & Putti 2015; Pham Van et al. 2016; AlDahoul et al. 2021; Nourani & Behfar 2021; Wai et al. 2022). Physical-based models for sediment transport are complex and time-consuming, often limited in their ability to predict SSC accurately in river basins due to the non-linear nature of sediment transport (Winterwerp 2013; Paniconi & Putti 2015). These models rely on reliable data and require calibration of numerous parameters, making them challenging for practical applications (Winterwerp 2013; Pham Van et al. 2016) as well as resulting in restricted use in numerous river basins worldwide. Therefore, robust and automated methods should be considered as alternatives to address these limitations.

Regarding practical application aspects, where a reduction in the complexity of the problem under consideration is always expected rather than requiring an exact solution, a sediment rating curve (SRC) describing a relationship between water discharge (Q) and SSC is widely used to estimate daily SSC from given flow values (Harrington & Harrington 2013). As reported in many previous studies (e.g., Asselman 2000; Lohani et al. 2007; Kisi et al. 2008; Liu et al. 2013; Zounemat-Kermani et al. 2016; Malik et al. 2017; Yilmaz et al. 2018), SRC is successfully applied to calculate daily SSC in various river basins around the world. With respect to the Ca River Basin, previous studies (e.g., Phuong et al. 2019, 2023) also use the SRC for preliminary investigation of temporal variability of SSC at two locations along the river in dry, wet, and transitional (between dry and wet) seasons from August 2017 to July 2018. It should be noted, however, that the SSC data used to determine the SRC's coefficients are not yet fully characteristic of the variation in Q and SSC over a long period of time because samples were collected only 4–6 times per month in the wet season and 1–4 times per month in the dry season. The use of separate SRC for each season of a hydrological year is indeed a difficult issue, both in terms of use and practical applications.

Multiple regression (MR), which assumes daily SSC at the location of interest as a function of daily flow at related locations in linear or non-linear form, is also used to compute daily SSC in river basins. Aytek & Kisi (2008) used MR in the linear form to evaluate daily SSC at two stations on the Tongue River in Montana, USA. Rajaee et al. (2011) also used MR in the linear form to predict daily SSC at Wapello station in the Iowa River, USA. Ulke et al. (2009) applied MR in both linear and non-linear forms to predict daily SSC and missing data in the Gediz River, Turkey. Malik et al. (2017) simulated daily SSC at the Tekra location on the Pranhita River, India. Recently, Stoichev et al. (2019) conducted an assessment of the spatial distribution of SSC in Aveiro Lagoon, Portugal. In a related study, Wang et al. (2022) also employed the MR to evaluate SSC reduction in the Yellow River, China, considering the influence of climate change and anthropogenic activities. These examples suggest that MR in the linear or non-linear form can be used to evaluate daily SSC in the river basin of interest.

It is interesting to note that SRC and MR are unable to evaluate daily SSC under extreme conditions because they are basically linear or non-linear forms determined based on an assumption, i.e., data are stationary (Rajaee & Jafari 2020). These methods also have a limited ability to capture the noise in SSC data. Moreover, SRC and MR often differ from one location to another and from one river basin to another in terms of the coefficients of SRC and MR (Walling 1974; Ferguson 1987; Asselman 2000; Quilbé et al. 2006; Harrington & Harrington 2013). Furthermore, inaccuracies in the estimation of daily SSC are related to the statistical method used to fit the SRC and MR, as well as the scatter around the regression curve (Asselman 2000). Thus, considerable efforts are still needed to accurately quantify SRC and MR in order to identify an appropriate method for locations of interest in river basins and to gain a better understanding of SS transport associated with various flow conditions in space and time.

To overcome the non-stationarity of SSC data, artificial intelligence (AI) approaches have been applied widely to water resources predictions in general and SSC in particular over the last two decades because of their accurate prediction capability (Afan et al. 2016; Rajaee & Jafari 2020). Machine learning models, one between two main categories (statistical and machine learning models) of AI approaches, have been used extensively to address non-linear hydrological processes like the transport process of SS, with models less focusing on physical characteristics of sediment transport processes, but on using black box methods to establish optimal mathematical relationships between input datasets and output results. These models include artificial neural network, genetic algorithms, adaptive neuro-fuzzy inference system, support vector machine, classification and regression tree, long short-term memory (LSTM), bidirectional LSTM, convolutional neural network, recurrent neural networks, instance-based learning, artificial bee colony, teaching-learning based optimization, gene programming, gene expression programming, wavelet-ANN, wavelet neuro-fuzzy, reduced error pruning tree, etc. (Rajaee & Jafari 2020). Among these, the LSTM is selected for this study due to several compelling reasons. Firstly, the LSTM is a widely acclaimed data-driven model in the field of AI. Secondly, the LSTM excels at learning temporal dependencies, making it exceptionally well-suited for handling time series data and sequential patterns, as demonstrated in recent studies (AlDahoul et al. 2021; Kim & Sandhu 2022; Pham Van & Le 2022; Latif et al. 2023). Finally, the LSTM offers these advantages without introducing excessive complexity when compared to other models like bidirectional LSTM.

The LSTM model can simulate the non-linear and complicated transport processes of SS with high accuracy (AlDahoul et al. 2021; Huang et al. 2021; Nourani & Behfar 2021; Latif et al. 2023). For instance, AlDahoul et al. (2021) used the LSTM model to forecast SSC in Malaysia's Johor River utilizing only water discharge as input datasets. Huang et al. (2021) applied the LSTM model to improve the predictive accuracy of SSC in the Shihmen Reservoir, China. Nourani & Behfar (2021) employed the LSTM model to study the runoff-sediment process from three gauging stations in the Missouri and upper Mississippi regions at both daily and monthly scales, USA. Li & Vanrolleghem (2022) proposed an influence generator based on the LSTM model to generate daily SSC in Quebec City, Canada. Kim & Sandhu (2022) estimated SSC at various locations within the Sacramento-San Joaquin Delta of California, USA based on the LSTM model. Latif et al. (2023) compared the LSTM model with several distinct AI-based models (e.g., ANN, SVM) in predicting SSC in the Johor river, Malaysia. All these demonstrate that the LSTM model can be used to evaluate daily SSC in the studied river basin. Moreover, transferring the LSTM model from one river basin to another is still a challenge to enrich and inform the model's capabilities.

The main objective of the present study is to investigate SRC, MR under both linear and non-linear forms, and LSTM models that can be used to estimate daily SSC at the Yen Thuong location in the Ca River Basin. Especially, the study aims to (i) determine an appropriate approach among the three studied here and (ii) evaluate SSC in the missing period of 1969–2008 and in the year 2020 at Yen Thuong. Hydrological data (i.e., Q at four upstream locations and at Yen Thuong itself, and SSC with daily scale) in the period from 1969 to 2020 are used to determine the coefficients in each approach and for related calculation purposes. Five common performance criteria such as Nash–Sutcliffe efficiency (NSE), Pearson's correlation coefficient (r), root mean square error (RMSE), mean error (ME), and mean absolute error (MAE) are implemented to quantitatively assess the performance of each approach in comparison with the observed data.

The Ca River Basin

Ca River Basin, which is located in the territory of Vietnam and the Lao People's Democratic Republic, covers an area of about 27,200 km2 (Pham Van & Le 2022). The Ca River Basin in Vietnam accounts for about 65% of the basin area. The river originates from the Phulaileng mountain in Lao PDR, then flows in a part of Lao PDR before entering Vietnam at Keng Du village and joining the Bien Dong at Cua Hoi estuary (Figure 1). The river has a length of 514 km (Phuong et al. 2023), of which 360 km flows in the territory of Vietnam and the rest flows in Laos (Figure 1). The river includes several tributaries such as Nam Mo, Hieu, Ngan Sau, and Ngan Pho. The river plays a particularly important role in socio-economic development and national waterway security due to its extremely diverse and abundant natural resources.
Figure 1

Map of the river basin, together with meteorological and hydrological stations.

Figure 1

Map of the river basin, together with meteorological and hydrological stations.

Close modal

In the Ca River Basin, the rainy season occurs from May to October in the upstream region and from June to November in the downstream area. Rainfall in a year often has two peaks, with the greatest value occurring in late September or early October, while the second rainfall peak appears in late May or early June (Pham Van et al. 2022). Monthly precipitation is usually the highest in May and June, while decreasing slightly in July and August. The total rainfall in May and June reaches up to 20% of the annual rainfall. Total precipitation in September and October is high, reaching from 40 to 50% of the annual rainfall. In the dry season, total seasonal precipitation is very low and is only about 15–20% of annual precipitation. The lowest precipitation is usually recorded in February and March, with the total precipitation of these two months being only about 2% of the annual precipitation amount. The meteo-hydrological characteristics in the river basin are also affected by climate change.

Various reservoirs (e.g., Ban Ve, Ban Mong, Khe Bo, and Ngan Truoi, etc.) have been built to address difficult problems of water supply, flood control, inundation, drought, and environment in the Ca River Basin. These multiple-purpose reservoirs have significant impacts on sediment transport and geochemical properties between upstream and downstream of the reservoirs. Measured data of SS at several locations along the Ca River and its tributaries show significant discrepancies in SSC between flood and dry seasons (Phuong et al. 2019; Pham Van et al. 2022). For instance, at the Yen Thuong location (see Figure 1), daily SSC varies in a wide range from 0.26 to 6,560 mg/L. The assessment of SSC will help to quantitatively evaluate the change and trend of sediment in the river basin.

Data collection

Daily time series of water discharge were collected in the long period from 1969 to 2020 at five gauging stations (named Muong Xen, Quy Chau, Nghia Khanh, Dua, and Yen Thuong as listed in Table 1), while datasets of daily SSC are collected in the period from 2009 to 2019 at Yen Thuong station. Figure 2 shows the probability density of water discharge at all collected stations as well as of SSC at Yen Thuong. Note that these data are provided by the North Central Regional Hydro-meteorological Center (NCRHE).
Table 1

Collected data of water discharge and suspended sediment concentration at different locations in the Ca river

No.NameLocations
RiverVariableData collected periodStatistical properties
Unit
Longitude (o)Latitude (o)RangeMeanStd.SkewnessKurtosisCorrelation coefficient, r
Muong Xen 104°07′00″ 19°24′00″ Nam Mo 1969–2020 7.37–1,840 77.44 95.38 6.26 73.16 0.524 m3/s 
Quy Chau 105°10′00″ 19°34′00″ Hieu 1969–2020 10.6–3,370 74.27 130.45 10.87 190.31 0.498 
Nghia Khanh 105°12′00″ 19°26′00″ Hieu 1969–2020 8.01–4,290 115.29 227.89 8.38 97.80 0.605 
Dua 105°02′00″ 18°59′00″ Ca 1969–2020 41.4–5,570 427.14 569.80 4.14 25.30 0.735 
Yen Thuong 105°23′00″ 18°41′00″ Ca 1969–2020 72.9–5,890 479.57 636.36 4.15 24.12 0.761 
SSC 2009–2019 0.26–6,560 91.16 270.90 9.14 136.51 1.0 mg/L 
No.NameLocations
RiverVariableData collected periodStatistical properties
Unit
Longitude (o)Latitude (o)RangeMeanStd.SkewnessKurtosisCorrelation coefficient, r
Muong Xen 104°07′00″ 19°24′00″ Nam Mo 1969–2020 7.37–1,840 77.44 95.38 6.26 73.16 0.524 m3/s 
Quy Chau 105°10′00″ 19°34′00″ Hieu 1969–2020 10.6–3,370 74.27 130.45 10.87 190.31 0.498 
Nghia Khanh 105°12′00″ 19°26′00″ Hieu 1969–2020 8.01–4,290 115.29 227.89 8.38 97.80 0.605 
Dua 105°02′00″ 18°59′00″ Ca 1969–2020 41.4–5,570 427.14 569.80 4.14 25.30 0.735 
Yen Thuong 105°23′00″ 18°41′00″ Ca 1969–2020 72.9–5,890 479.57 636.36 4.15 24.12 0.761 
SSC 2009–2019 0.26–6,560 91.16 270.90 9.14 136.51 1.0 mg/L 
Figure 2

Probability density of water discharge, at (a) Muong Xen, (b) Quy Chau, (c) Nghia Khanh, (d) Dua, (e) Yen Thuong and of SSC at (f) Yen Thuong.

Figure 2

Probability density of water discharge, at (a) Muong Xen, (b) Quy Chau, (c) Nghia Khanh, (d) Dua, (e) Yen Thuong and of SSC at (f) Yen Thuong.

Close modal

SRC with single expression for both rising and falling climbs

The first option to estimate SSC at the location of interest is to use a single SRC that describes the average relationship between Q and SSC. The power function, typically represented as Equation (1), is the most frequently employed type of SRC (e.g., Walling 1974; Ferguson 1987; Asselman 2000; Pham Van et al. 2022):
formula
(1)
where a and b are rating and exponent coefficients, respectively.

As shown in Equation (1), a non-linear regression of the SRC is depicted if the exponent coefficient is different from unity. Otherwise, a linear regression of the SRC is obtained. In this study, different values for the exponent coefficient b are tested to determine an appropriate value for the location of interest when the same available datasets for flow and SSC are used. In other words, both linear and non-linear forms for the power function of the single SRC are examined.

SRC with different expressions for rising and falling climbs

The relationship between Q and SSC has an apparent and significant scatter, showing that there is a hysteresis of SSC with different values for the rising and falling climbs of the discharge-sediment relationship (Asselman 2000; Harrington & Harrington 2013). In this case, different coefficients are used for the rising and falling climbs of the SRC. In other words, the power function under the form of Equation (1) is also applied with different values for the rating and exponent coefficients of the rising and falling climbs. Detailed results using SRC with different expressions for rising and falling climbs at the location of interest are presented in Section 4.

MR between SSC and discharge

SSC at the location of interest is assumed to be a function of water discharge at various upstream locations and at the location of interest itself under multiple regression Equation (2).
formula
(2)
where αi and Qi are the regression coefficient and water discharge at location number i, respectively, α0 is the regression constant, and β is the exponential coefficient of the regression. Note that Qi consists of the water discharge at Muong Xen, Quy Chau, Nghia Khanh, Dua, and Yen Thuong, while SSC denotes the SSC at the location of interest (i.e., Yen Thuong). Note that MR, which derives the value of SSC at the location of interest from the simultaneous combination of water discharges at the above locations, is examined to assess how and to what extent the water discharges affect a certain outcome of SSC. The appropriate values of α0, αi and β are determined based on the available datasets of Q and SSC collected in the period between 1/1/2009 and 31/12/2019.

The LSTM model

Daily SSC at Yen Thuong can be also computed by using the LSTM model which is a well-known alternative network of recurrent neural networks. The LSTM model (Hochreiter & Schmidhuber 1997) uses a memory cell to represent essentially the hidden layer and to overcome vanishing and exploding gradient problems. The architecture of the model mainly consists of input, forget, and output gates that allow respectively for updating the cell state, resetting the cell state without growing indefinitely, and deciding how to update the values of the hidden unit. Further information on the LSTM model can be found in relevant references (e.g., AlDahoul et al. 2021; Huang et al. 2021; Kim & Sandhu 2022; Li & Vanrolleghem 2022; Pham Van & Le 2022; Latif et al. 2023).

In terms of hyper-parameters, there are three dominant hyper-parameters, i.e., the number of epochs, the number of hidden units, and the learning rate in the LSTM model. These hyper-parameters are determined by the trial-and-error method and based on five performance criteria. In detail, hyper-parameters are first calibrated using 70% of the datasets in the training step. The model is then validated using 30% of the remaining datasets. Two types of input datasets (consisting of water discharge at: (i) Yen Thuong only and (ii) five stations named Muong Xen, Quy Chau, Nghia Khanh, Dua, and Yen Thuong) are examined to evaluate the effects of input datasets on output results when the LSTM model is applied.

Evaluation criteria

To evaluate the performance of each approach, five common performance criteria, i.e., NSE, Pearson's correlation coefficient (r), RMSE, ME, and MAE are implemented. The NSE, r, RMSE, ME, and MAE are calculated using Equations (3)–(7), respectively, for quantitatively assessing the agreement between estimated and observed values of daily SSC at the location of interest.
formula
(3)
formula
(4)
formula
(5)
formula
(6)
formula
(7)
where and are the observed and estimated values of daily SSC at point number j in a time series, respectively; and are the mean value of estimating and observing daily SSC, respectively, and N is the length or total number of points in the considered time series.

Dimensional and dimensionless errors are used to evaluate the quality performance of each method. Three-dimensional criteria (i.e., RMSE, ME, and MAE) are valuable indicators since they indicate the error in the units, which is helpful in analyzing the results. Two-dimensionless criteria (i.e., NSE and r), which determine the relative magnitude of residual variance (or noise) compared to the variance of observations, are used to provide comprehensive information on comparisons between observed and estimated values (Pham Van & Le 2022).

Results of SRC with single expression

Using the collected datasets of the flow and SSC, various combinations of rating and exponent coefficients were systematically tested using a trial-and-error approach to pinpoint the optimal values when using a single linear or non-linear SRC. Finally, the selection of the appropriate coefficients was based on an evaluation using five performance metrics. Among different testing values, three selected pairs of coefficients a and b are summarized in Table 2, while the detail values of estimate errors (i.e., NSE, r, RMSE, ME, and MAE) of daily SSC corresponding to the abovementioned coefficients are synthesized in Table 3. Note that the notations Est. and Obs. refer to the estimated and observed values of SSC magnitude, respectively. Figure 3 shows the observed values of daily SSC as well as three sediment rating curves (that are associated with the three selected pairs of coefficients a and b). The best estimation of the coefficients is finally found as a = 0.0022 and b = 1.605 (denoted SRC2). The dimensional errors (i.e., RMSE, ME, and MAE) of SSC vary in a range between 18 and 178 mg/L (corresponding from 0.3 to 2.7% of the observed magnitude of daily SSC). The coefficients r and NSE are equal to 0.76 and 0.57, respectively. These reveal that estimated values of daily SSC are accepted in comparison with the observations at the location of interest.
Table 2

Estimated values of coefficients when using different SRC with single expression for both rising and falling climbs

No.Sediment rating curveCoefficients
Abbreviation
ab
Linear SRC 0.32 1.0 SRC1 
Non-linear SRC 0.0022 1.605 SRC2 
Non-linear SRC 8.40 × 10−5 2.0 SRC3 
No.Sediment rating curveCoefficients
Abbreviation
ab
Linear SRC 0.32 1.0 SRC1 
Non-linear SRC 0.0022 1.605 SRC2 
Non-linear SRC 8.40 × 10−5 2.0 SRC3 
Table 3

Estimated errors of SSC when using SRC with single expression for both rising and falling climbs

AbbreviationRMSE
MAE
ME
rNSESSC magnitude (mg/L)
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
SRC1 187.07 2.85 96.72 1.47 −64.21 −0.98 0.761 0.523 1,908 6,560 
SRC2 177.36 2.70 50.53 0.77 17.98 0.27 0.759 0.571 2,500 
SRC3 186.40 2.84 57.90 0.88 37.54 0.57 0.737 0.531 2,914 
AbbreviationRMSE
MAE
ME
rNSESSC magnitude (mg/L)
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
SRC1 187.07 2.85 96.72 1.47 −64.21 −0.98 0.761 0.523 1,908 6,560 
SRC2 177.36 2.70 50.53 0.77 17.98 0.27 0.759 0.571 2,500 
SRC3 186.40 2.84 57.90 0.88 37.54 0.57 0.737 0.531 2,914 
Figure 3

Estimated results of daily SSC when using linear and non-linear regressions for SRC with single expression for both rising and falling climbs.

Figure 3

Estimated results of daily SSC when using linear and non-linear regressions for SRC with single expression for both rising and falling climbs.

Close modal

As shown in Table 3, SRC2 outperformed all other sediment rating curves in four of five criteria (namely RMSE, MAE, ME, and NSE). Among the three selected pairs of coefficients a and b, SRC1 stands out as the best performer according to the r criterion. However, it's worth mentioning that the difference in the correlation coefficient r between SRC1 and SRC2 is quite small and insignificant, with r being 0.761 for SRC1 and 0.759 for SRC2. When considering the magnitude of SSC, the estimated value of SSC in SRC3 (2,914 mg/L) is the closest to the observed value (6,560 mg/L). This inconsistency in results may arise from various factors, including data distribution and the use of varying exponent coefficient b.

Both linear and non-linear SRC are investigated, resulting in a slight improvement of estimated values of daily SSC if the non-linear SRC is applied. On the other hand, the plot of observed values of Q versus SSC (in the period from 2009 to 2019) illustrates apparent and significant scatters (see Figure 3), revealing that there is a hysteresis of the SSC with different values for the rising and falling climbs of the hydrographs. This complicated hydrograph of SSC versus Q consists of the results obtained in the dry and rainy seasons of 2017 in the previous studies (Phuong et al. 2019, 2023). Different values of coefficients a and b should be tested for the rising and falling climbs of the SRC.

Results of SRC with different expressions

In order to identify coefficients a and b for rising and fall climbs of the SRC, the time series of collected data of daily SSC in the period from 2009 to 2019 are firstly divided into two datasets separately, i.e., one dataset for the rising climb and the other one for the falling climb. The latter is performed using the differences and approximate derivatives function in MATLAB. Then, coefficients a and b for either rising or falling climb are determined similarly to the single SRC. Finally, appropriate values of coefficients a and b are found for each climb of the hydrography as summarized in Table 4, depicting the exponent coefficient b is more or less the same for falling and rising climbs while the significant discrepancy of the rating coefficient a between climbs is obtained. In addition, the exponent coefficient is also similar when using single or multiple sediment rating curves (see Tables 3 and 4).

Table 4

Estimated values of coefficients when using different coefficients for falling and rising climbs of the SRC

No.StateSediment rating curveCoefficients
Abbreviation
ab
Falling climb Non-linear 0.0032 1.59 SRC (fall) 
Rising climb Non-linear 0.0018 1.60 SRC (rise) 
No.StateSediment rating curveCoefficients
Abbreviation
ab
Falling climb Non-linear 0.0032 1.59 SRC (fall) 
Rising climb Non-linear 0.0018 1.60 SRC (rise) 

Figure 4 shows the estimated results of daily SSC when using different coefficients of a and b for falling and rising climbs. The dimensional errors of daily SSC for the falling climb are equal to 210.46, 64.93, and 17.15 mg/L for RMSE, MAE, and ME, respectively, while these errors for the rising climb are 105.88, 31.55, 10.80 mg/L (see Table 5). The values of dimensionless errors r = 0.793 and NSE = 0.625 are obtained for the falling climb. A value of r = 0.759 as well as NSE = 0.56 are obtained for the rising climb. Thus, there is only a slight improvement in the estimated values of daily SSC in the falling climb, whereas performance worsens during the rising climb when compared to the results obtained from using the single SRC.
Table 5

Error estimates of daily SSC when using different coefficients for falling and rising climbs of the SRC

AbbreviationRMSE
MAE
ME
rNSESSC magnitude (mg/L)
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
SRC (fall) 210.46 3.21 64.93 0.99 17.15 0.26 0.793 0.625 2,714 6,560 
SRC (rise) 105.88 4.64 31.55 1.38 10.80 0.47 0.759 0.560 1,871 2,280 
AbbreviationRMSE
MAE
ME
rNSESSC magnitude (mg/L)
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
SRC (fall) 210.46 3.21 64.93 0.99 17.15 0.26 0.793 0.625 2,714 6,560 
SRC (rise) 105.88 4.64 31.55 1.38 10.80 0.47 0.759 0.560 1,871 2,280 
Figure 4

Estimated results of daily SSC when using different coefficients for (a) falling and (b) rising climbs of the SRC.

Figure 4

Estimated results of daily SSC when using different coefficients for (a) falling and (b) rising climbs of the SRC.

Close modal

Results of MR

When MR is applied, different values of the exponent coefficient (e.g., β = 1.0, 1.6, and 2.0 which were obtained using an SRC with a single expression) are tested to investigate the impacts of water discharges at different upstream locations and at Yen Thuong itself on estimated values of daily SSC. In each tested value of β, appropriate values of coefficients α0 and αi are determined by using a multiple linear regression function, resulting in detailed values of coefficients as summarized in Table 6. The detailed values of five estimated errors of daily SSC are reported in Table 7 and the time series of estimated values of daily SSC versus observations during the whole collected period are shown in Figure 5.
Table 6

Estimated values of coefficients when using MR of water discharge for estimating SSC at Yen Thuong

βαoα1α2α3α4α5Abbr.
Muong XenQuy ChauNghia KhanhDuaYen Thuong
1.0 −70.98 27.15 × 102 −15.39 × 102 14.36 × 102 4.05 × 102 24.75 × 102 MRQ1 
1.6 11.17 5.87 × 10−3 0.12 × 10−3 0.015 × 10−3 0.57 × 10−3 1.73 × 10−3 MRQ2 
2.0 35.48 3.24 × 10−4 0.25 × 10−4 −0.107 × 10−4 0.25 × 10−4 0.60 × 10−4 MRQ3 
βαoα1α2α3α4α5Abbr.
Muong XenQuy ChauNghia KhanhDuaYen Thuong
1.0 −70.98 27.15 × 102 −15.39 × 102 14.36 × 102 4.05 × 102 24.75 × 102 MRQ1 
1.6 11.17 5.87 × 10−3 0.12 × 10−3 0.015 × 10−3 0.57 × 10−3 1.73 × 10−3 MRQ2 
2.0 35.48 3.24 × 10−4 0.25 × 10−4 −0.107 × 10−4 0.25 × 10−4 0.60 × 10−4 MRQ3 
Table 7

Estimate errors of daily SSC when using the MR of Q

Abbr.RMSE
MAE
ME
rNSESSC magnitude (mg/L)
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
MRQ1 172.53 2.63 57.29 0.87 −5.30 −0.08 0.771 0.594 1,737 6,560 
MRQ2 171.68 2.62 52.80 0.80 0.00 0.00 0.773 0.598 2,314 
MRQ3 196.83 3.00 80.32 1.22 0.00 0.00 0.687 0.472 3,287 
Abbr.RMSE
MAE
ME
rNSESSC magnitude (mg/L)
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
MRQ1 172.53 2.63 57.29 0.87 −5.30 −0.08 0.771 0.594 1,737 6,560 
MRQ2 171.68 2.62 52.80 0.80 0.00 0.00 0.773 0.598 2,314 
MRQ3 196.83 3.00 80.32 1.22 0.00 0.00 0.687 0.472 3,287 
Figure 5

Time series of daily SSC when using the MR, with (a) β = 1.0, (b) β = 1.6, and (c) β = 2.0.

Figure 5

Time series of daily SSC when using the MR, with (a) β = 1.0, (b) β = 1.6, and (c) β = 2.0.

Close modal

It can be observed that the MR reproduces similar results of daily SSC when the exponent coefficient β = 1.0 or β = 1.6 is used (Table 7). The values of three-dimensional errors vary in a range from 0 to 172.5 mg/L (approximated from 0 to 2.6% of the observed magnitude of SSC at Yen Thuong). The value of NSE is about 0.60, while the coefficient r equals 0.77. In the case β = 2.0, larger values are obtained for three-dimensional errors and smaller values are obtained for two-dimensionless errors (Table 7). In addition, the value β = 1.6 is found to be the best one among different tested values.

When delving into the estimated results in depth, it becomes evident that MRQ2 excelled in all five criteria (i.e., NSE, r, RMSE, MAE, and ME) among the three multiple regressions under investigation (Table 7). However, when assessing the magnitude of SSC, the estimated value in MRQ3 (3,287 mg/L) closely approximates the observed value (6,560 mg/L). Once again, this inconsistency in results may be attributed to variations in data distribution and the use of different exponent coefficient b.

As shown in Figures 5 and 6, an underestimation of estimated values of daily SSC is also observed in high flow conditions in flood seasons whether using a small or large value of the coefficient β. This due to the fact that daily SSC at the location of interest results from different processes and impact factors, e.g., land-use change in the river basin, local erosion or deposition in riverbed and riverbank, mixing process of SS in water column which are not fully taken into account in the calculation when using an MR.
Figure 6

Observed data (SSCObs.) versus estimated values (SSCEst.) of SSC when using the MR, with (a) β = 1.0, (b) β = 1.6, and (c) β = 2.0.

Figure 6

Observed data (SSCObs.) versus estimated values (SSCEst.) of SSC when using the MR, with (a) β = 1.0, (b) β = 1.6, and (c) β = 2.0.

Close modal

Results of the LSTM

In terms of the LSTM model, the hyper-parameters named learning rate, number of hidden units, and number of epochs are determined using the available observed data of flow and SSC in the period from 1/1/2009 to 31/12/2019. In detail, 70% of datasets (corresponding to the period from 1/1/2009 to 12/9/2016) were used for the training step, while the remaining 30% of datasets (from 13/9/2016 to 31/12/2019) were applied for the validation phase as in many previous studies (e.g., Klemes 1986; Kisi et al. 2012; Buyukyildiz & Kumcu 2017; Choubin et al. 2018; Khosravi et al. 2018; Pham Van & Le 2022; Pham Van & Nguyen-Van 2022). Two kinds of input data are considered when using the LSTM model. The first one uses only water discharge at the Yen Thuong location as the input data, while the second one utilizes the flow datasets at whole five collected locations. Similar to SRC and MR, appropriate values of hyper-parameters are also determined by trial-and-error method using five common performance criteria, resulting in learning rate = 0.001, number of hidden units = 128, and number of epochs = 350.

Figure 7 shows the time series of estimated and observed values of daily SSC when using only water discharge at the location of interest as input data in the LSTM model. As can be seen in Figures 7 and 8, the model represents very well the observations in both training and validation steps. The values of dimensional errors are less than 2% of the observed magnitude of SSC (Table 8). The correlation coefficient r between estimated and observed values of SSC is greater than 0.97, revealing that the LSTM model reproduces the observed variable trend of SSC very well. The value of NSE is equal to 0.956 and 0.94 for the training and validation steps, respectively. In the training step, the estimated SSC magnitude was 6,265 mg/L compared to the observed value of 6,560 mg/L (see Table 8). This reveals a discrepancy of less than 295 mg/L, which is approximately only about 4.5% of the observed SSC magnitude at the location. Additionally, the estimated value of SSC magnitude closely matches the observation in the validation step.
Table 8

Error estimates of daily SSC when using water discharge at Yen Thuong as input data in the LSTM model

StepRMSE
MAE
ME
rNSESSC magnitude (mg/L)
Abbr.
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
Training 61.74 0.94 29.89 0.46 −1.80 −0.03 0.978 0.956 6,265 6,560 LSTM (T,1) 
Validation 50.00 1.92 28.06 1.08 3.88 0.15 0.970 0.940 2,636 2,610 LSTM (V,1) 
StepRMSE
MAE
ME
rNSESSC magnitude (mg/L)
Abbr.
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
Training 61.74 0.94 29.89 0.46 −1.80 −0.03 0.978 0.956 6,265 6,560 LSTM (T,1) 
Validation 50.00 1.92 28.06 1.08 3.88 0.15 0.970 0.940 2,636 2,610 LSTM (V,1) 
Figure 7

Time series of SSC, for (a) training and (b) validation steps when using only Q at Yen Thuong as input datasets in the LSTM model.

Figure 7

Time series of SSC, for (a) training and (b) validation steps when using only Q at Yen Thuong as input datasets in the LSTM model.

Close modal
Figure 8

Observed data (SSCObs.) versus estimated values (SSCEst.) of daily SSC for (a) training and (b) validation steps when using only Q at Yen Thuong as input data in the LSTM model.

Figure 8

Observed data (SSCObs.) versus estimated values (SSCEst.) of daily SSC for (a) training and (b) validation steps when using only Q at Yen Thuong as input data in the LSTM model.

Close modal
Figures 9 and 10 depict the results for the case of using water discharges at five collected locations as input data in the LSTM model. The values of RMSE, MAE, and ME range from −0.84 to 19.4 mg/L in both training and validation steps, and these values are less than 0.61% of the observed magnitude of SSC (see Table 9). The values of coefficients r and NSE are close to unity, showing that the LSTM model represents very well both variable trend and instantaneous values of observed SSC. In comparison with the case using only water discharge at the location of interest as input data, a slight improvement of the model performance is also observed when using the flow at whole five collected locations as input datasets.
Table 9

Error estimates of daily SSC when using water discharge at five stations as input data in the LSTM model

StepRMSE
MAE
ME
rNSESSC magnitude (mg/L)
Abbr.
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
Training 19.38 0.30 11.58 0.18 −0.84 −0.01 0.998 0.996 6,561 6,560 LSTM (T,5) 
Validation 16.02 0.61 11.15 0.43 1.45 0.06 0.997 0.994 2,610 2,610 LSTM (V,5) 
StepRMSE
MAE
ME
rNSESSC magnitude (mg/L)
Abbr.
(mg/L)(%)(mg/L)(%)(mg/L)(%)Est.Obs.
Training 19.38 0.30 11.58 0.18 −0.84 −0.01 0.998 0.996 6,561 6,560 LSTM (T,5) 
Validation 16.02 0.61 11.15 0.43 1.45 0.06 0.997 0.994 2,610 2,610 LSTM (V,5) 
Figure 9

Time series of daily SSC, for (a) training and (b) validation steps when using flow at five stations as input datasets in the LSTM model.

Figure 9

Time series of daily SSC, for (a) training and (b) validation steps when using flow at five stations as input datasets in the LSTM model.

Close modal
Figure 10

Observed data (SSCObs.) versus estimated values (SSCEst.) of daily SSC for (a) training and (b) validation steps when using Q at five stations as input data in the LSTM model.

Figure 10

Observed data (SSCObs.) versus estimated values (SSCEst.) of daily SSC for (a) training and (b) validation steps when using Q at five stations as input data in the LSTM model.

Close modal
Figure 11 shows the radar plot for all five performance criteria of daily SSC when using different approaches such as (i) a single SRC under the linear or non-linear form, (ii) different regressions for falling and rising climbs of rating curve under the non-linear form, (iii) MR, and (iv) LSTM model with different input datasets. It is clearly seen that the LSTM model is finally found to be the best choice (among different investigated approaches) for simulating observed values of SSC at the location of interest. For instance, if sediment rating curves are used, the insignificant discrepancy of estimate errors of SSC is observed, with the range from 0 to 210 mg/L and from 0.47 to 0.79 for dimensional and dimensionless errors, respectively. On the other hand, the magnitude of RMSE, MAE, and ME of SSC is less than 2% and its value of r and NSE is greater than 0.94 when the LSTM model is applied.
Figure 11

Radar plots for (a) dimensional and (b) dimensionless performance criteria of daily SSC when applying different methods.

Figure 11

Radar plots for (a) dimensional and (b) dimensionless performance criteria of daily SSC when applying different methods.

Close modal

Application of the LSTM model to estimate daily SSC

To estimate daily SSC in the period from 1969 to 2008 and in the year 2020, it is assumed that daily SSC is the function of daily flow at different upstream locations and at the location of interest itself, without considering direct impacts of the erosion or deposition of riverbed and riverbank. Using the LSTM model with appropriate values of hyper-parameters that were determined carefully in the training and validation steps, values of daily SSC in the period mentioned above are calculated from the available flow datasets. Figure 12 shows the time series of daily SSC in the long considered period. As shown in the figure, the variable trend of estimated values of SSC consists of the variable trend of the flow, e.g., large values of daily SSC are observed in flood seasons while small values of daily SSC are presented in dry seasons. Further information related to statistical properties (e.g., range, mean, standard deviation, covariance, skewness, and kurtosis) of Q and SSC in different periods can be found in Table 10 (in which the word Obs. refers to the observed data).
Table 10

Statistical properties of Q and SSC in different periods

ApproachRangeMeanStandard deviationCovarianceSkewnessKurtosisPeriod
Water discharge (m3/s) 
Obs. 72.9–5,890 479.57 636.36 404,959.12 4.15 24.12 2009–2019 
42.7–9,030 529.48 694.19 481,901.41 3.90 24.40 1969–2008, 2020 
Suspended sediment concentration (mg/L) 
Obs. 0.26–6,560 91.16 270.90 73,385.36 9.14 136.51 2009–2019 
LSTM 0.29–9,228 238.95 581.02 337,585.04 6.47 60.38 1969–2008, 2020 
ApproachRangeMeanStandard deviationCovarianceSkewnessKurtosisPeriod
Water discharge (m3/s) 
Obs. 72.9–5,890 479.57 636.36 404,959.12 4.15 24.12 2009–2019 
42.7–9,030 529.48 694.19 481,901.41 3.90 24.40 1969–2008, 2020 
Suspended sediment concentration (mg/L) 
Obs. 0.26–6,560 91.16 270.90 73,385.36 9.14 136.51 2009–2019 
LSTM 0.29–9,228 238.95 581.02 337,585.04 6.47 60.38 1969–2008, 2020 
Figure 12

Daily time series of (a) water discharge and (b) SSC using the LSTM model at the location of interest in the period from 1969 to 2020.

Figure 12

Daily time series of (a) water discharge and (b) SSC using the LSTM model at the location of interest in the period from 1969 to 2020.

Close modal

Discussion

Impact of rise and falling direction of SRC

As mentioned previously (see Figure 3), the plot of Q versus SSC at the location of interest shows clearly apparent and significant scatters, even when collected data are divided into two sub-datasets corresponding to the falling and rising climbs. To adopt that issue, different values of rating and exponent coefficients are investigated for each climb, showing that using a separate SRC for the falling and rising climbs represents better-observed values of SSC than those obtained from a single SRC. For instance, instead of adopting a value of 0.571 for NSE when using the single SRC (denoted SRC1 in Table 3), the coefficient NSE = 0.625 is achieved in the falling climb. This result is consistent with the results reported in different previous studies (e.g., Duan et al. 2013; Phuong et al. 2023). In addition, a slight improvement in estimating daily SSC is also obtained when using SRC with different expressions for falling and rising climbs of the discharge-sediment hydrograph. As shown in Figure 4, the datasets for each climb inherently present significant scatters. The latter results from the non-linear variation of the flow as well as from excluding related impact factors (e.g., bed evolution, sediment transport processes, the interaction between suspended and bedload sediments) in calculations when the SRC was applied.

Previous studies (e.g., Phuong et al. 2019) investigated the impact of climate change and reservoirs on the SSC at Dua and Yen Thuong locations, revealing that different sediment rating curves are carried out for dry and rainy seasons as well as for transition time between dry and rainy seasons based on the collected data in the period from August 2017 to July 2018. Again, the abovementioned data were collected 4–6 times per month in the rainy season and 1–4 times per month in the dry season. Such collected data, however, are not yet fully characteristic of the variation in Q and SSC over a long period of time. On the contrary, large values of NSE and r coefficients are obtained, especially when using the LSTM model (e.g., NSE and r coefficients are greater than 0.94 for both the training and validation steps) in comparison with a value of 0.63 for the determination coefficient reported by Phuong et al. (2023). This means that a significant improvement in estimated values of daily SSC was obtained for the studied location. Thus, the present results of daily SSC strongly believed to be useful for investigating temporal variations of SSC not only in daily but also yearly scales.

Impact of input data in LSTM model

Two kinds of input data of the LSTM model were used in calculations, showing that the model simulates much better the observed values of daily SSC at the location of interest when flow datasets at whole five locations are considered in input data. It is not a surprise that the more input datasets, the more accurate the model. In addition, the LSTM model also represented observed values of daily SSC much better than those obtained from the single or multiple SRC when using the same input datasets (i.e., time series of water discharge at Yen Thuong location only). In the case of using water discharge at all five locations, the LSTM model also reproduced observations of SSC better than those achieved from the SRC and MR. These suggest that the LSTM model is more suitable than the SRC and MR at the location of interest. The use of the LSTM model is also flexible, in terms of the input datasets, which makes the model to be applicable tool for other locations in river basins as well as for practical applications.

Three approaches named SRC, MR under linear and non-linear forms, and LSTM model are implemented to evaluate daily SSC at Yen Thuong location in the Ca River Basin, Vietnam. The dominant remarks of the present study can be summarized as:

  • Using the daily data of Q and SSC in the period from 1/1/2009 to 31/12/2019, both linear and non-linear forms of the single SRC were examined, resulting in the best estimated-observed data comparisons found to the power function with the values of 0.0022 and 1.605 for the rating and exponent coefficients. The values of the three popular performance errors (i.e., MAE, ME, and RMSE) were smaller than 3% of the observed magnitude of the daily SSC. Indeed, the values of 0.76 and 0.57 were also obtained for the r and NSE coefficients.

  • Different forms of the SRC were investigated separately for rising and falling climbs of the discharge-sediment hydrography. An improvement of estimated values of daily SSC was obtained, especially for the falling climbs as r = 0.80, NSE = 0.63, and the values of three-dimensional criteria were less than 5% of the observed SSC magnitude at the gauging station.

  • In terms of the MR, daily SSC at the location of interest was found to have a close relationship with the water discharge at five locations under the linear (the exponent coefficient equals unity) or power functions (the exponent coefficient equals 1.60). For both cases, the values of dimensional criteria are less than 3% of the observed magnitude of the daily SSC, while NSE and r were equal to 0.60 and 0.77, respectively.

  • If the LSTM model was applied, a very good reproduction of the observed values of daily SSC was obtained. The values of ME, MAE, and RMSE were less than 2% of the observed magnitude of daily SSC. The values of r and NSE varied between 0.94 and 0.99 when datasets of the flow at either one or five related locations were used as input in the LSTM model.

  • Among the three investigated methods, the LSTM model is found to be a more suitable approach for evaluating daily SSC from available datasets of the flow at the studied location. This model uses only datasets of the flow for input, which makes the model to be a useful tool for calculating daily SSC in river basins.

The authors would like to thank the North Central Regional Hydro-meteorological Center for sharing data used for different calculations in the present study. The authors would like to thank the editor and five anonymous reviewers for their fruitful suggestions and valuable comments.

Data cannot be made publicly available; readers should contact the corresponding author for details.

The authors declare there is no conflict.

Afan
H. A.
,
El-shafie
A.
,
Mothar
W. H. M. W.
&
Yaseen
Z. M.
2016
Past, present and prospect of an artificial intelligence (AI) based model for sediment transport prediction
.
Journal of Hydrology
541
,
902
913
.
https://doi.org/10.1016/j.jhydrol.2016.07.048
.
AlDahoul
N.
,
Essam
Y.
,
Kumar
P.
,
Ahmed
A. N.
,
Sherif
M.
,
Sefelnasr
A.
&
Elshafie
A.
2021
Suspended sediment load prediction using long short-term memory neural network
.
Scientific Reports
11
,
7826
.
https://doi.org/10.1038/s41598-021-87415-4
.
Asselman
N. E. M.
2000
Fitting and interpretation of sediment rating curves
.
Journal of Hydrology
234
,
228
248
.
https://doi.org/10.1016/S0022-1694(00)00253-5
.
Aytek
G.
&
Kisi
O.
2008
A genetic programming approach to suspended sediment modelling
.
Journal of Hydrology
351
,
288
298
.
https://doi.org/10.1016/j.jhydrol.2007.12.005
.
Choubin
B.
,
Darabi
H.
,
Rahmati
O.
&
Sajedi-Hosseini
F.
2018
River suspended sediment modelling using the CART model: A comparative study of machine learning techniques
.
Science of The Total Environment
615
,
272
281
.
https://doi.org/10.1016/j.scitotenv.2017.09.293
.
Duan
W.
,
Takara
K.
,
Luo
P.
,
Nover
D.
&
Yamashikir
Y.
2013
Spatial and temporal trends in estimates of nutrient and suspended sediment loads in the Ishikari River, Japan, 1985 to 2010
.
Science of the Total Environment
499
508
.
https://doi.org/10.1016/j.scitotenv.2013.05.022
.
Elskens
M.
,
Gourgue
O.
,
Baeyens
W.
,
Chou
L.
,
Deleersnijder
E.
,
Leermakers
M.
&
de Brauwere
A.
2014
Modelling metal speciation in the Scheldt Estuary: Combining a flexible-resolution transport model with empirical functions
.
Science of the Total Environment
476–477
,
346
358
.
https://doi.org/10.1016/j.scitotenv.2013.12.047
.
Ferguson
R. I.
1987
Accuracy and precision of methods for estimating river loads
.
Earth Surface Processes and Landforms
12
,
95
104
.
https://doi.org/10.1002/esp.3290120111
.
Harrington
S. T.
&
Harrington
J. R.
2013
An assessment of the suspended sediment rating curve approach for load estimation on the Rivers Bandon and Owenabue, Ireland
.
Geomorphology
185
,
27
38
.
https://doi.org/10.1016/j.geomorph.2012.12.002
.
Hochreiter
S.
&
Schmidhuber
J.
1997
Long short–term memory
.
Neural Computation
9
,
1735
1780
.
https://doi.org/10.1162/neco.1997.9.8.1735
.
Huang
C. C.
,
Chang
M. J.
,
Lin
G. F.
,
Wu
M. C.
&
Wang
P. H.
2021
Real-time forecasting of suspended sediment concentrations reservoirs by the optimal integration of multiple machine learning techniques
.
Journal of Hydrology: Regional Studies
34
,
100804
.
1–15, https://doi.org/10.1016/j.ejrh.2021.100804
.
Khosravi
K.
,
Mao
L.
,
Kisi
O.
,
Yaseen
Z. M.
&
Shahid
S.
2018
Quantifying hourly suspended sediment load using data mining models: Case study of a glacierized andean catchment in Chile
.
Journal of Hydrology
567
,
165
179
.
https://doi.org/10.1016/j.jhydrol.2018.10.015
.
Kim
H. S.
,
He
M.
&
Sandhu
P.
2022
Suspended sediment concentration estimation in the Sa Sacramento-San Joaquin Delta of California using long short-term memory networks
.
Hydrological Processes
36
(
10
),
1
17
.
https://doi.org/10.1002/hyp.14694
.
Kisi
O.
,
Yuksel
I.
&
Dogan
E.
2008
Modeling daily suspended sediment of rivers in Turkey using several data-driven techniques
.
Hydrological Sciences Journal
53
(
6
),
1270
1285
.
https://doi.org/10.1623/hysj.53.6.1270
.
Kisi
O.
,
Dailr
A.
,
Cimen
M.
&
Shiri
J.
2012
Suspended sediment modeling using genetic programming and soft computing techniques
.
Journal of Hydrology
450–451
,
48
58
.
https://doi.org/10.1016/j.jhydrol.2012.05.031
.
Klemes
V.
1986
Operational testing of hydrological simulation models
.
Hydrological Sciences Journal
31
(
1
),
13
24
.
doi:10.1080/02626668609491024
.
Latif
S. D.
,
Chong
K. L.
,
Ahmed
A. N.
,
Huang
Y. F.
,
Sherif
M.
&
Ahmed
E. S.
2023
Sediment load prediction in Johor river: Deep learning versus machine learning models
.
Applied Water Science
13
,
79
.
https://doi.org/10.1007/s13201-023-01874-w
.
Li
F.
&
Vanrolleghem
P. A.
2022
An influent generator for WRRF design and operation based on a recurrent neural network with multi-objective optimization using a genetic algorithm
.
Water Science & Technology
85
(
5
),
1444
1453
.
https://doi.org/10.2166/wst.2022.048
.
Liu
Q.-J.
,
Shi
Z.-H.
,
Fang
N.-F.
,
Zhu
H.-D.
&
Ai
L.
2013
Modeling the daily suspended sediment concentration in a hyper concentrated river on the Loess Plateau, China, using the Wavelet–ANN approach
.
Geomorphology
186
,
181
190
.
https://doi.org/10.1016/j.geomorph.2013.01.012
.
Lohani
A. K.
,
Goel
N. K.
&
Bhatia
K. K. S.
2007
Deriving stage–discharge–sediment concentration relationships using fuzzy logic
.
Hydrological Sciences Journal
52
(
4
),
793
807
.
https://doi.org/10.1623/hysj.52.4.793
.
Malik
A.
,
Kumar
A.
&
Piri
J.
2017
Daily suspended sediment concentration simulation using hydrological data of Pranhita River Basin. India
.
Computers and Electronics in Agriculture
138
,
20
28
.
https://doi.org/10.1016/j.compag.2017.04.005
.
Nourani
V.
&
Behfar
N.
2021
Multi-station runoff-sediment modeling using seasonal LSTM models
.
Journal of Hydrology
601
,
126672
.
1–14, https://doi.org/10.1016/j.jhydrol.2021.126672
.
Paniconi
C.
&
Putti
M.
2015
Physically based modeling in catchment hydrology at 50: Survey and outlook
.
Water Resources Research
51
(
9
),
7090
7129
.
https://doi.org/10.1002/2015WR017780
.
Pham Van
C.
&
Nguyen-Van
G.
2022
Three different models to evaluate water discharge: An application to a river section at Vinh Tuy location in the Lo river basin, Vietnam
.
Journal of Hydro-Environment Research
40
,
38
50
.
https://doi.org/10.1016/j.jher.2021.12.002
.
Pham Van
C.
,
Gourgue
O.
,
Sassi
M.
,
Hoitink
A. J. F.
,
Deleersnijder
E.
&
Soares-Frazao
S.
2016
Modeling fine-grained sediment transport in the Mahakam land-sea continuum, Indonesia
.
Journal of Hydro-Environmental Research
13
,
103
120
.
https://doi.org/10.1016/j.jher.2015.04.005
.
Pham Van
C.
,
Le
H.
&
Nguyen-Ngoc
D.
2022
Estimation of suspended sediment rating curves in the Ca river basin, Vietnam
. In:
The 11th International Conference on Fluvial Hydraulics
,
8–10 November 2022
,
Kingston and Ottawa, Canada
, pp.
1
6
.
Phuong
H. T.
,
Okubo
K.
&
Uddin Md
A.
2019
Geochemistry and sediment in the main stream of the Ca River basin, Vietnam: Weathering process, solute-discharge relationships, and reservoir impact
.
Acta Geochimica
38
(
4
),
627
641
.
https://doi.org/10.1007/s11631-019-00327-z
.
Phuong
H. T.
,
Ha
T. K. T.
,
Le
T. H.
&
Saito
M.
2023
Spatial and temporal variabilities of suspended sediment and dissolved nutrients in the Ca River basin, North Central Vietnam
.
Water Practice & Technology
18
(
2
),
408
418
.
https://doi.org/10.2166/wpt.2023.016
.
Quilbé
R.
,
Rousseau
A. N.
,
Duchemin
M.
,
Poulin
A.
,
Gangbazo
G.
&
Villeneuve
J.
2006
Selecting a calculation method to estimate sediment and nutrient loads in streams: Application to the Beaurivage River (Québec, Canada)
.
Journal of Hydrology
326
,
295
310
.
https://doi.org/10.1016/j.jhydrol.2005.11.008
.
Rajaee
T.
&
Jafari
H.
2020
Two decades on the artificial intelligence models advancement for modeling river sediment concentration: state-of-the-art
.
Journal of Hydrology
588
,
125011
.
1–23, https://doi.org/10.1016/j.jhydrol.2020.125011
.
Rajaee
T.
,
Nourani
V.
,
Zounemat-Kermani
M.
&
Kisi
O.
2011
River suspended sediment load prediction: Application of ANN and Wavelet conjunction model
.
Journal of Hydrologic Engineering
6
(
8
),
613
627
.
https://doi.org/10.1061/(ASCE)HE.1943-5584.000034
.
Stoichev
T.
,
Tessier
E.
,
Coelho
J. P.
,
Lobos Valenzuela
M. G.
,
Pereira
M. E.
&
Amouroux
D.
2019
Multiple regression analysis to assess the spatial distribution and speciation of mercury in surface sediments of a contaminated lagoon
.
Journal of Hazardous Materials
367
,
715
724
.
https://doi.org/10.1016/j.jhazmat.2018.12.109
.
Ulke
A.
,
Tayfur
G.
&
Ozkul
S.
2009
Predicting suspended sediment loads and missing data for Gediz River, Turkey
.
Journal of Hydrologic Engineering
14
(
9
),
954
965
.
doi:10.1061/(ASCE)HE.1943-5584.0000060
.
Wai
K. P.
,
Chia
M. Y.
,
Koo
C. H.
,
Huang
Y. F.
&
Chong
W. C.
2022
Applications of deep learning in water quality management: A state-of-the-art review
.
Journal of Hydrology
613
,
128332
.
https://doi.org/10.1016/j.jhydrol.2022.128332
.
Walling
D. E.
,
1974
Suspended sediment and solute yields from a small catchment prior to urbanization
. In:
Fluvial Processes in Instrumented Watersheds
(
Gregory
K. J.
&
Walling
D. E.
, eds).
Institute of British geographer's special publication 6
,
London, UK
, pp.
169
192
.
Wang
Z.
,
Xu
M.
,
Liu
X.
,
Singh
D. K.
&
Fu
X.
2022
Quantifying the impact of climate change and anthropogenic activities on runoff and sediment load reduction in a typical Loess Plateau watershed
.
Journal of Hydrology: Regional Studies
39
,
100992
.
https://doi.org/10.1016/j.ejrh.2022.100992
.
Winterwerp
J. C.
2013
The physical analysis of muddy sedimentation processes
.
Treatise on Estuarine and Coastal Science
2
,
311
360
.
Yilmaz
B.
,
Aras
E.
,
Nacar
S.
&
Kankal
M.
2018
Estimating suspended sediment load with multivariate adaptive regression spline, teaching-learning based optimization, and artificial bee colony models
.
Science of the Total Environment
639
,
826
840
.
https://doi.org/10.1016/j.scitotenv.2018.05.153
.
Zounemat-Kermani
M.
,
Kişi
O.
,
Adamowski
J.
&
Ramezani-Charmahineh
A.
2016
Evaluation of data driven models for river suspended sediment concentration modeling
.
Journal of Hydrology
535
,
457
472
.
https://doi.org/10.1016/j.jhydrol.2016.02.012
.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (CC BY-NC-ND 4.0), which permits copying and redistribution for non-commercial purposes with no derivatives, provided the original work is properly cited (http://creativecommons.org/licenses/by-nc-nd/4.0/).