dam seepage prediction using rbf and gff models of artificial neural network; case study: boukan shahid kazemi’s dam

Dams have been always considered as the important infrastructures and their critical values measured. hence, evaluation and avoidance of dams’ destruction have a specific importance. in this study seepage of the embankmentof boukan shahid kazemi’s dam in iran has been analyzed via rbf (radial basis function network) and gff (feed-forward neural networks) models of artificial neural network (ann). rbf and gff of ann models were trained and verified using each piezometer’s data and the water levels difference of the dam. to achieve this goal,based on the number of data and inputs,864piezometric data set were used, of which 80% (691 data) was used for the training and 20% (174 data) for the testing the network.the results showed good agreement between observed and predicted values and concluded the rbf model has high potential in estimating seepage with levenberg marquardt training and 4 hidden layers. also the values of statistical parameters r² and rmse were 0.81 and the 33.12.