Monthly Runoff Estimation Using Artificial Neural Networks.

Runoff estimation is one of the main challenges encountered in water and watershedmanagement. spatial and temporal changes of factors which influence runoff due to heterogeneityof the basins explain the complicacy of relations. artificial neural network(ann) is one of the intelligence techniques which is flexible and doesn’t call for any muchphysically complex processes. these networks can recognize the relation between inputand output. in this study ann model was employed for runoff estimation in plaszjan riverbasin in the central part of iran. the models used are multiple perceptron (mlp) andrecurrent neural network (rnn). inputs include data obtained from 5 rain gauges aswell as from 2 temperature recording gauges, the output of the model being the monthlyflow in eskandari hydrometric station. preprocessing of the data as well as the sensitivityanalysis of the model were carried out. different topologies of neural networks were createdwith change in input layers, nodes as well as in the hidden layer. the best architecturewas found as 7.4.1. recurrent neural network led to better results than multilayerperceptron network. also results indicated that ann is an appropriate technique formonthly runoff estimation in the selected basin with these networks being also of the capabilityto show basin response to rainfall events.