Predicting suspended sediment load in Peninsular Malaysia using support vector machine and deep learning algorithms

High loads of suspended sediments in rivers are known to cause detrimental effects to potable water sources, river water quality, irrigation activities, and dam or reservoir operations. For this reason, the study of suspended sediment load (SSL) prediction is important for monitoring and damage mitigation purposes. The present study tests and develops machine learning (ML) models, based on the support vector machine (SVM), artificial neural network (ANN) and long short-term memory (LSTM) algorithms, to predict SSL based on 11 different river data sets comprising of streamflow (SF) and SSL data obtained from the Malaysian Department of Irrigation and Drainage. The main objective of the present study is to propose a single model that is capable of accurately predicting SSLs for any river data set within Peninsular Malaysia. The ANN3 model, based on the ANN algorithm and input scenario 3 (inputs consisting of current-day SF, previous-day SF, and previous-day SSL), is determined as the best model in the present study as it produced the best predictive performance for 5 out of 11 of the tested data sets and obtained the highest average RM with a score of 2.64 when compared to the other tested models, indicating that it has the highest reliability to produce relatively high-accuracy SSL predictions for different data sets. Therefore, the ANN3 model is proposed as a universal model for the prediction of SSL within Peninsular Malaysia.

Impact of land use-land cover change on spatio-temporal trends in seasonal stream flow and suspended sediment load of Godavari basin from 1969 to 2019

Assessment of long-term trend in stream flow and sediment load is important for adopting soil and water conservation measures and for predicting morphological changes in rivers. In the present study, detailed quantification of the nature of trend in stream flow and suspended sediment load of Godavari basin, India is reported for the period of 1969 to 2019. The Mann–Kendall test is used to check trend of stream flow and sediment load for different seasons, namely, spring, monsoon, post-monsoon and winter. The land use-land cover of the whole basin is prepared for four decades (1980–2020). The maximum and minimum water and sediment discharge is detected in monsoon and winter season, respectively. The stream flow is found significantly decreased during monsoon and post-monsoon season. The sediment load is significantly decreased for monsoon and spring season. The nature of trend in sediment load is attributed to the land use and land cover change of the basin. The significant reduction suspended sediment load is mainly due to increase in water bodies and planned agricultural area. The findings of the research would help to manage water resources as well as sustainable development in the Godavari basin.

Suspended Sediment Load Simulation during Flood Events Using Intelligent Systems: A Case Study on Semiarid Regions of Mediterranean Basin

Sediment transport in rivers is a nonlinear natural phenomenon, which can harm the environment and hydraulic structures and is one of the main reasons for the dams’ siltation. In this paper, the following artificial intelligence approaches were used to simulate the suspended sediment load (SSL) during periods of flood events in the northeastern Algerian river basins: artificial neural network combined with particle swarm optimization (ANN-PSO), adaptive neuro-fuzzy inference system combined with particle swarm optimization (ANFIS-PSO), random forest (RF), and long short-term memory (LSTM). The comparison of the prediction accuracies of such different intelligent system approaches revealed that ANN-PSO, RF, and LSTM satisfactorily simulated the nonlinear process of SSL. Carefully comparing the results, the ANN-PSO model showed a slight superiority over the RF and LSTM models, with RMSE = 67.2990 kg/s in the Chemourah basin and RMSE = 55.8737 kg/s in the Gareat el tarf basin.

Contemporary Trends in River Flow, Suspended Sediment Load, and Soil/Gully Erosion in the South of the Boreal Forest Zone of European Russia: The Vyatka River Basin

Recent decades in the north of the East European Plain have been characterized by significant changes in climate and land use/cover, especially after the collapse of the USSR in 1991. At the same time, the hydrological consequences of these changes, especially changes in erosion processes and river sediment load, have been studied insufficiently. This paper partially covers this existing knowledge gap using the example of the Vyatka River basin. Draining an area of 129,000 km2, the Vyatka River is among the largest rivers in the boreal forest zone of European Russia. Cultivated land occupies about one-fifth of the river basin area; about three-fourths is covered by taiga forest vegetation. The results of state long-term hydrometeorological monitoring and information on land use/cover made it possible to reveal contemporary (since the 1960s) hydrological and erosion-intensity trends and their drivers within the greater (96%) part of the river basin. There has been a statistically insignificant increase in water discharge in the Vyatka River basin during recent decades. This is due to a statistically insignificant increase (for the entire basin studied) in the spring snowmelt-induced floodwater flow and a statistically significant rise in the discharge in the year’s warm and cold seasons. The main reason for the detected trends is increased precipitation, including heavy rainfall during the warm season. In contrast to this, the total annual suspended sediment load of the river (especially that which was snowmelt-induced) and, consequently, soil/gully erosion intensity have experienced a significant decrease in recent decades (up to 58% between 1960–1980 and 2010–2018). Land-use/-cover changes (a reduction of cultivated land area and agricultural machinery, a decline of livestock in pastures) following the collapse of the Soviet Union are considered the main reasons for this decrease. The most noticeable changes in water discharge, suspended sediment load, and erosion intensity were observed in the most agriculturally developed southwest and south parts of the Vyatka River basin. All the above trends may be considered with a high probability to be representative for the south sector of the taiga zone of the East European Plain.

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.

Prediction of river suspended sediment load using machine learning models and geo-morphometric parameters

Estimating sediment load of rivers is one of the major problems in river engineering that has been using various data mining algorithms and variables. It is desirable to obtain accurate estimates of sediment load while using techniques that limit computational intensity when datasets are large. This study investigates the usefulness of geo-morphometric factors and machine learning (ML) models for predicting suspended sediment load (SSL) in several river basins in Lorestan and Gilan, Iran. Six ML models, namely, multiple linear regression (MLR), artificial neural networks (ANN), K-nearest neighbor (KNN), Gaussian processes (GP), support vector machines (SVM), and evolutionary support vector machines (ESVM), were evaluated for estimating minimum and average SSL for the study regions. Geo-morphometric parameters and river discharge data were utilized as the main predictors in modeling process. In addition, an attribute reduction technique was applied to decrease the algorithm complexity and computational resources used. The results showed that all models estimated both target variables well. However, the optimal models for predicting average sediment load and minimum sediment load were the GP and ESVM models, respectively.