Comparative study of multilayer perceptron-stochastic gradient descent and gradient boosted trees for predicting daily suspended sediment load: The case study of the Mississippi River,U.S.

Monitoring sediment transport is essential for managing and maintaining rivers.Estimation of the sediment load in rivers is fundamental for the study of sediment movement,erosion,and flood control.In the current study,three machine learning models-multi-layer perceptron(MLP),multi-layer perceptron-stochastic gradient descent(MLP-SGD),and gradient boosted tree(GBT)-were utilized to estimate the suspended sediment load(SSL)at the St.Louis(SL)and Chester(CH)stations on the Mississippi River,U.S.Four evaluation criteria including the Correlation Coefficient(CC),Nash Sutcliffe Efficiency(NSE),Scatter Index(SI),and Willmott’s Index(WI)were utilized to evaluate the performance of the used models.A sensitivity analysis of the models to the input variables revealed that the current day discharge variable had the most effect on the SSL at both stations,but in the absence of current-day discharge data(Qt),a combination of input parameters including SSL_t-3,SSL_t-2,SSL_t-1,Q_t-3,Q_t-2,Q_t-1 can be used to estimate the SSL.The comparative outcomes indicated the high accuracy of MLP-SGD-5 model with a CC of 0.983,SI of 0.254,WI of 0.991,and NSE of 0.967 at station CH and the MLP-SGD-6 model with a CC of 0.933,SI of 0.576,WI of 0.961,and NSE of 0.867,respectively,at station SL.The results of MLP models were improved by SGD optimization.Therefore,the MLP-SGD method is recommended as the most accurate model for SSL estimation.     

A study of suspended sediment concentration in Yangshan deep-water port in Shanghai,China

Suspended sediment concentration (SSC) plays an important role in the estuarine environment.Its spatial or temporal variations in coastal zones and estuaries indicate that sediments are suspended,trans...     

A simple and inexpensive turbidity meter for the estimation of suspended sediment concentrations

The relatively high cost of commercially available turbidity meters has inhibited detailed and intensive research on spatiotemporal patterns of suspended sediment transport. We describe here the electronic and physical design of an inexpensive turbidity sensor which is easy to construct, simple to interface with portable millivolt meters, dataloggers, computers, or chart recorders, consumes exceptionally small currents, and is robust and reliable. the very low individual cost allows a large number of sensors to be distributed throughout the water body of interest to facilitate turbidity mapping. Turbidity profilers to detect vertical or lateral turbidity changes in rivers, lakes, estuaries, or near-shore zones are also shown to be feasible. Test data are presented from a highly turbid glacial river in southern Iceland.     

A comparison of instrumental dewatering methods for the separation and concentration of suspended sediment for subsequent trace element analysis

A comparison involving both field and laboratory trials was performed to evaluate the utility of two continuous-flow centrifuges and a tangential-flow filtration system for dewatering suspended sediments for subsequent trace element analysis. Although recovery efficiencies for the various devices differ, the analytical results from the separated suspended sediments indicate that any of the tested units can be used effectively and precisely for dewatering. Further, the three devices appear to concentrate and dewater suspended sediments in such a manner as to be equivalent to that which could be obtained by in-line filtration. Only the tangential-flow filtration system appears capable of providing both a dewatered sediment sample and a potentially usable effluent, which can be analysed for dissolved trace elements. The continuous-flow centrifuges can process whole water at an influent feed rate of 41 per minute; however, when suspended sediment concentrations are low (<30mg^?1), when small volumes of whole water are to be processed (30 to 401), or when suspended sediment mean grain size is very fine (<10 μm), influent feed rates of 21 per minute may be more efficient. Tangential-flow filtration can be used to process samples at the rate of 11 per minute.     

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

ABSTRACT

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

A comparative study of extensive machine learning models for predicting long-term monthly rainfall with an ensemble of climatic and meteorological predictors

Rainfall prediction is of vital importance in water resources management. Accurate long-term rainfall prediction remains an open and challenging problem. Machine learning techniques, as an increasingly popular approach, provide an attractive alternative to traditional methods. The main objective of this study was to improve the prediction accuracy of machine learning-based methods for monthly rainfall, and to improve the understanding of the role of large-scale climatic variables and local meteorological variables in rainfall prediction. One regression model autoregressive integrated moving average model (ARIMA) and five state-of-the-art machine learning algorithms, including artificial neural networks, support vector machine, random forest (RF), gradient boosting regression, and dual-stage attention-based recurrent neural network, were implemented for monthly rainfall prediction over 25 stations in the East China region. The results showed that the ML models outperformed ARIMA model, and RF relatively outperformed other models. Local meteorological variables, humidity, and sunshine duration, were the most important predictors in improving prediction accuracy. 4-month lagged Western North Pacific Monsoon had higher importance than other large-scale climatic variables. The overall output of rainfall prediction was scalable and could be readily generalized to other regions.