Estimation of Suspended Sediment Load based on Physiographic Parameters of the Watershed

Suspended sediment load is one of the most important river elements that, in addition to its impact on water quality, has an effective role in managing water resources and structures on these resources. Therefore, estimating the suspended load can be a great help in increasing the productivity of water resources and improving the efficiency of aquifers. Determining the exact and proper parameters that have an effective factor in the sedimentation rate of the catchment area has an effective role in increasing the accuracy of data mining models. Physiographic parameters that indicate the physical properties of the watershed can be considered as a determining factor in the extent of sedimentation of the catchment area. There are several methods to estimate the suspended load of rivers. One of these methods is the use of data mining models that are very useful in solving hydrologic problems. Therefore, in this research, by combining data mining models and sediment load physiographic parameters of 30 watersheds in Lorestan province with a statistical period of 33 years, in order to study the effect of different physiographic indices on sediment estimation in the first step of flow flow as the only input of models and in step Next, various field physiographic indices were selected as inputs of different data mining models. In this study, five data mining models including artificial neural network, evolutionary support vector machine, decision tree, Gaussian process and regression were used. All models have been well received.