Seyed Ahmad Hosseini; Ahmad Tabatabaei
Abstract
Introduction
Simulating suspended sediment in hydrological systems has always been challenging due to inherent complexities and uncertainties. This issue has led to the use of intelligent models such as Artificial Neural Networks (ANNs) as a suitable approach for predicting suspended sediment load. ...
Read More
Introduction
Simulating suspended sediment in hydrological systems has always been challenging due to inherent complexities and uncertainties. This issue has led to the use of intelligent models such as Artificial Neural Networks (ANNs) as a suitable approach for predicting suspended sediment load. Therefore, the use of intelligent models like ANNs has expanded in this field. However, determining the optimal network structure (including the number of neurons, layers, weights, and biases) is usually done through trial and error, which is both time-consuming and inefficient. In this study, a multilayer perceptron neural network was used to simulate the daily suspended sediment load in the Qarasu Sarab watershed (Quri Chay and Hir Chai rivers) located in Ardabil province, Iran.
Materials and methods
In this research, an Artificial Neural Network (ANN) of the Multilayer Perceptron (MLP) type was utilized to simulate the daily suspended sediment load in the Sarab Qareh Su watershed (including the Quri Chay and Hir Chay rivers) in Ardabil province. The neural network models were trained not only whit the conventional backpropagation algorithm but also using the Particle Swarm Optimization (PSO) algorithm to optimize the weights and biases of the neurons. Furthermore, to increase the models' generalization capability, a Self-Organizing Map (SOM) clustering was employed. In addition to the backpropagation algorithm, the Particle Swarm Optimization (PSO) algorithm was also employed to optimize the network weights and biases. Furthermore, to enhance the model's generalization power, SOM clustering was used. The use of evolutionary algorithms such as PSO in training neural networks is an effective approach to improve the accuracy of intelligent models, especially in simulating river suspended sediment and applications related to water resources and watershed management structures.
Results and discussion
Using SOM clustering and the Davies-Bouldin index, the optimal number of clusters was determined as 12 for Koozeh Toupraqi station and 15 for Hir Chai station. Statistical analysis and the Kolmogorov-Smirnov (KS) test showed that data distributions across training, validation, and testing sets were similar, which enhances the generalization capability of the models. Training the neural network models with PSO yielded better performance and lower prediction errors compared to backpropagation. The ANN-PSO-Sig and ANN-PSO-Tan models achieved the best results at Koozeh Toupraqi and Hir Chai stations, respectively. Bias analysis further confirmed that PSO-trained models had lower errors in total sediment load estimation. Overall, results showed that PSO-based training outperforms pure backpropagation training. At Koozeh Toupraqi station, the hybrid ANN-PSO model with sigmoid activation function (ANN-PSO-Sig), and at Hir-Hirchai Topraghi station, the hybrid model with hyperbolic tangent activation function (ANN-PSO-Tan) were selected as optimal models, showing biases of +5.25% and -19.2% and RMSE values of 86.28 and 89.2 tons per day, respectively. These findings demonstrate the improvement in suspended sediment load prediction accuracy by using PSO in neural network training.
Conclusion
The use of the PSO metaheuristic algorithm in training neural network models improved their performance in simulating suspended sediment load. This method outperformed gradient-based error algorithms and provided more accurate weight optimization. The improved bias accuracy in PSO-trained models is crucial for designing hydraulic structures and water resource management. Furthermore, SOM clustering helped select homogeneous and representative datasets for model training, enhancing model generalizability. Overall, considering the complexities and uncertainties in hydrological systems, employing intelligent models combined with evolutionary optimization algorithms like PSO is an effective approach for simulating and monitoring suspended sediment loads. The obtained results can be applied in planning and implementing watershed engineering measures and water resource management.
Seyed Ahmad Hosseini
Abstract
Sediment dams are built with multi-purpose goals including flood control, erosion, sedimentation and aquifer feeding. These dams, with the aim of controlling the sediment from transferring part of it to the reservoirs of the dams in the downstream, and by causing a delay in the surface runoff, they control ...
Read More
Sediment dams are built with multi-purpose goals including flood control, erosion, sedimentation and aquifer feeding. These dams, with the aim of controlling the sediment from transferring part of it to the reservoirs of the dams in the downstream, and by causing a delay in the surface runoff, they control a part of the flood and feed the aquifer of the area. Improper design or lack of optimal implementation of these structures causes the reduction of useful life and sometimes premature destruction of these structures. Evaluating the function and technical performance of such plans with the aim of improving and managing the system is of special importance. For this reason, in this article, a number of sediment dams implemented in Abdanan City of Ilam Province were investigated and evaluated. This research was conducted in the form of hydraulic simulation and comparison of the current situation with the conditions before the implementation of the project, in a section of the waterway about seven kilometers long. It should be mentioned that six stone and mortar dams have been built during the last decade. The results of the hydraulic simulation of the flooding of waterways and constructed structures showed that, based on the discharge with a return period of 100 years, the average overflow width of the construction dams is about 25% larger than the required value and the length of the stilling basin is about 40% less than the required value. In general, in all construction dams, the length of the stilling pond is not chosen correctly, so that the short length of the stilling pond has caused the hydraulic jump to leave the pond or to form at its end. Due to the high flow speed in the area of the hydraulic jump, erosion and destruction in the end zone of the calm pond has intensified, which has been extended to the upstream side and the main structure of the sediment dam. Based on the hydraulic simulation of the flood and the relative comparison of the results in the conditions before and after the construction of the dams, it was found that the constructed dams have a positive effect on the parameters of flow speed, flow strength and flow shear stress, which are all factors that aggravate erosion in the waterway. So that for discharge with a return period of 25 years, the speed, power and shear stress parameters of the flow have decreased by 23, 29 and 27%, respectively, during the research period. Therefore, the average reduction of these parameters locally and at the construction site of the six dams was estimated as 73, 85 and 82%, respectively. In general, according to the field visits and investigations, the implementation of the plan has been effective in controlling floods and sediments, and in case of annual protection and repair, its effects will be doubled.
Mansour Jahantigh; Seyed Ahmad Hosseini
Abstract
Aim of this research was Studying and Recognition of lithology and Erosion Rivers in Sistan region. To done this research distinct situation of rivers according of basin and collected inform about basin of Sistan and review different parts of them such as type of erosion in river banks by using available ...
Read More
Aim of this research was Studying and Recognition of lithology and Erosion Rivers in Sistan region. To done this research distinct situation of rivers according of basin and collected inform about basin of Sistan and review different parts of them such as type of erosion in river banks by using available reports and filed works. We have used available scale of 1:50,000, 1:250,000, Geologic maps, field observation and global positioning system (GPS). We found erodible area of river banks according to scale of 1:250,000 erodible Geologic maps. The data show that’s the main factor of cause to erosion is effect geologic conditions. The main parts of the basin covered with sediment of quaternary which is very sensitive to water erosion.The sistan rivers classification shows that stone, alluvium and other are 20.7, 38.1 and 41.2 percentage of rivers length, respectively. 7.2 percentages of area rivers occur erosion that bed and banks erosion are 85.1 and 14.9%, respectively.
Seyed Ahmad Hosseini; Mahmoud Raeini; Foroud Sharifi; Mohammadali Gholami
Abstract
One of the important reasons of soil erosion and sediment production in irrigation and drainage canal networks is the soil instability. Erosion mechanism in this type of channel starts with the impact of raindrops and soil aggregation, so that broken fine particles lead to blockage the pores. In this ...
Read More
One of the important reasons of soil erosion and sediment production in irrigation and drainage canal networks is the soil instability. Erosion mechanism in this type of channel starts with the impact of raindrops and soil aggregation, so that broken fine particles lead to blockage the pores. In this condition, soil permeability is reduced compared to the initial state and runoff that is increasing. Increased runoff on slopes of moderate to steep, rises shear stress sharply which causes soil destruction and produces sediment production. To overcome this problem, suitable vegetation cover deployment is appropriate, but in some situations, vegetation cover establishment is not possible simply due to special circumstances and it is not the best solution in the short term as well. One of the ways of controlling erosion on slopes is the use of various mechanical structures, commonly used in engineering projects, that is associated with expensive costs. Another solution that was tested in this research, is the use of natural corrective materials such as organic mulch and natural rectifier materials. In this study, by using four types of various organic mulch, soil erosion resistance of various parameters of the drain canal bank was studied using simulated rainfall in the rainfall laboratory of Soil Conservation and Watershed Management Research Institute. In this article, the results of using bio mulch for erosion control, on the drainage channel bank are provided. This study aimed to determine the most appropriate type and density of different mulch on canal bank erosion reduction for irrigation and drainage network channel project that is located in Arayez plain of Khuzestan. With the use of four organic mulch, at least 40 experiments on soil samples were done. For the all laboratory tests, 25 kg soil samples were pressed inside the steel basins, to imply the bulk density of soil in nature. Treatments in the flume with a slope of 1 to 1.25, similar side slope drains, in both 30 and 80 mm per hour rainfall intensity were simulated. Each treatment was applied at three densities. The results showed that all mulch treatments compared with control samples had a significant effect on sediment and it confirmed that the bio mulch are effective in the erosion control of the bank drainage channel. The results showed that the mulch will lead to reduce sediment more than 90 percent. Therefore, the use of mulch 1 and 4 in the highest density, have the greatest impact on the rate of erosion. It was also found that by increasing density of mulch, the amount of sediment reduced significantly.
Ebrahim Borooshke; Seyed Ahmad Hosseini
Abstract
Construction activities on the river branches and the middle areas of the watersheds can lead to changes on the river bed morphology of down streams. Understanding the river bed morphology changes and its effects on the lands next to river is essential to rehabilitate and stabilize the bed and banks. ...
Read More
Construction activities on the river branches and the middle areas of the watersheds can lead to changes on the river bed morphology of down streams. Understanding the river bed morphology changes and its effects on the lands next to river is essential to rehabilitate and stabilize the bed and banks. This study aim to identify the river bed morphology changes over the past five decades in Zarrinehrud River. In this research a range of 25 km at the end of Zarrinehrud River in West Azerbaijan province was studied using aerial photos of year 1334 and 1346, topographic maps of year 1375 and SPOT satellite image of year 1382. Results showed that morphological changes of the river bed and the surface area of adjacent lands were reduced from 561.1 ha to 221.3 ha. The sand dam area at river bed in 1346 was 13.8 ha and at 1382 was 2.7 ha, this result represents a large discharge fluctuations and changes in the hydrological and hydraulic conditions of the river. Meander form of River morphology also has been changed. Number of Meanders reduced from 4 to 3. The effective factors on the morphological changes were, changes in the hydrological regime due to dam construction, runoff reduction and sediment deposition in the river bed.
