چکیده:
Erosion and sedimentation are the most complicated problems in hydrodynamic which are very important in water-related projects of arid and semi-arid basins. For this reason, the presence of suitable methods for good estimation of suspended sediment load of rivers is very valuable. Solving hydrodynamic equations related to these phenomenons and access to a mathematical-conceptual model is very difficult and in most cases, necessary data for these models are not available. On the other hand, most of the widely-used experimental methods are not accurateenough. The principles of wise method are: using the hidden knowledge in the data; effort to extract intrinsic relations
between data; and generalizing them to other situations. Artificial neural network is one of the most important methods of artificial intelligence in which by inspiring from the model of human brain while performing training process, data-related information are stored into weights of network. The aim of this research is using MLP (Multi- Layer Perceptron) neural network to obtain sediment rating curve. After entering input patterns into the network and defining a neuron for input and a neuron for output layers and performing repeated trial and error, optimum architecture (topology) of MLP network was defined as a network with 5 neuron for hidden layers and Hyperbolic
tangent activation function for the first and second hidden layers and Linear function for the third hidden layer.
خلاصه ماشینی:
Estimating river suspended sediment yield using MLP neural network in arid and semi-arid basins Case study: Bar River, Neyshaboor, Iran Abstract Erosion and sedimentation are the most complicated problems in hydrodynamic which are very important in water-related projects of arid and semi-arid basins.
Although the results indicated optimum operation of multi- layer perceptron neural network, but this method is not applicable when a continuous series of water discharge and sediment concentration are not available (Kumorjain, 2001).
In another research that has been done on water and sediment discharges of Jajrood River, Iran, the results obtained from MLP neural network have been reported to be satisfactory (Avarideh et al.
Despite of counter propagation of Grassberg network, multi-layer perceptron network produces ascending mapping which with sigmoid function in the first hidden layer and linear function in the second hidden and output layers, is able to do better estimation of high sediment discharges and can be used in sediment rating curve preparation.
In the present article, sediment yield of Bar River at Ariyeh hydrometric station has been estimated by MLP neural network and the effect of sigmoid threshold function and hyperbolic tangent in model operation have been evaluated.
(view the image of this page) Created mapping by MLP network on the basis of training data, with hyperbolic tangent threshold function for all layers and for the first and second hidden layers and linear function for the third hidden and output layers are shown in figure 7.