Modeling the Role of Hydrogeomorphological Factors in Estimation of Suspended Sediment Load Using Artificial Neural Network and Regression Methods

Abolfathi, Dariush (2017) Modeling the Role of Hydrogeomorphological Factors in Estimation of Suspended Sediment Load Using Artificial Neural Network and Regression Methods. Doctoral thesis, University of Mohaghegh Ardabili.

Text Final.pdf Download (977kB)

Abstract

Soil erosion by water is the most serious form of land degradation in many parts of the world, especially in arid and semi-arid regions, where soil formation is usually less than soil erosion due to rapid soil erosion, impacts of human abuse and use. Incorrect of soils. Sedimentation over the Vanai and Golrood rivers in Silakhor Boroujerd Basin causes high erosion in the eastern and northeast lands of the studied basin and causes high sediment behind the lower dams and also damages hydraulic installations and aquatic structures and changes the riverbed. It has been deposited. In this study, 341 flood data from the statistical period of 1356-1395 were used.To predict and model the sediment in the watersheds, artificial neural network and multivariate regression were used. The findings of this study show that after calculating the RMSE and MAE indices, the lower the indices, the closer the predicted value to the actual values, so the MLP model is better than The other two models show the sedimentation rate of the area. On the other hand, with respect to the R2 index value calculated for the three models, the accuracy of the model is estimated to be 90.44 for the MLP model and the R2 value for this model is 0.88 Following the MLP artificial neural network model, the RBF artificial neural network model provides better results.In this model, the R2 value is 0.4, which is an estimate of approximately half of the MLP model. Third is multivariate linear regression model with R2 value of 0.3 Evaluation of the results shows that with increasing slope mean, the amount of sediment thickness increases, which is the most important factor in sediment yield after flow discharge. The third factor affecting sediment production in the river is the amount of sedimentation that, although the number of branches, is higher, the rate of sediment production is higher.The fourth factor in the rate of sediment production is the catchment area. In general, the larger the catchment area, the greater the sediment yield. The fifth factor in sediment yield is the average basin elevation, which increases as the slope increases and less vegetation in the area causes erosion. The last factor in sediment production is the basin environment.

Actions (login required)

View Item