Computation of subsurface drain spacing in the unsteady conditions using Artificial Neural Networks (ANN)

• Published in: Applied water science 2021-02, Vol.11 (2), p.1-9, Article 21
• Main Authors: Ostad-Ali-Askari, Kaveh, Shayannejad, Mohammad
• Format: Article
• Language: English
• Subjects: Aquatic Pollution; Artificial neural networks; Artificial neural networks (ANN); Comparative Law; Computation; Dependent variables; Drain space; Drain spacing; Drains; Earth and Environmental Science; Earth Sciences; Groundwater table; Hydraulic conductivity; Hydrogeology; Independent variables; Industrial and Production Engineering; International & Foreign Law; Modelling; Nanotechnology; Neural networks; Neurons; Nonlinear systems; Original Article; Private International Law; Soil properties; Specific yield; Subsurface drains; System effectiveness; Unsteady state; Waste Water Technology; Water depth; Water Industry/Water Technologies; Water Management; Water Pollution Control; Water table
• ISSN: 2190-5487; 2190-5495
• DOI: 10.1007/s13201-020-01356-3

Artificial neural networks are a tool for modeling of nonlinear systems in various engineering fields. These networks are effective tools for modeling the nonlinear systems. Each artificial neural network includes an input layer, an output layer between which there are one or some hidden layers. In each layer, there are one or several processing elements or neurons. The neurons of the input layer are independent variables of the understudy issue, and the neurons of the output layer are its dependent variables. Artificial neural system, through exerting weight on inputs and by suing an activation function attempts to achieve a desirable output. In this research, in order to calculate the drain spacing in an unsteady state in a region situated in the north east of Ahwaz, Iran with different soil properties and drain spacing, the artificial neural networks have been used. The neurons in the input layer were: Specific yield, hydraulic conductivity, depth of the impermeable layer, height of the water table in the middle of the interval between the drains in two-time steps. The neurons in output layer were drain spacing. The network designed in this research was included a hidden layer with four neurons. The distance of drains computed via this method had a good agreement with real values and had a high precision in compare with other methods.