NOVATECH 2010,7th international conferenc on sustainable techniques and strategiesin urban water management , 2010-06-27

Title : ( Prédiction de Précipitation mensuelle par réseau de neurones artificiel (Étude de cas: station synoptique de Mashhad) )

Authors: Saeed Reza Khodashenas , Najmeh Khalili , Kamran Davary ,

Access to full-text not allowed by authors

Citation: BibTeX | EndNote

Abstract

Several ANN models were developed for prediction of monthly precipitation data in a period of 53 years in Mashhad synoptic station. From the total 636 monthly precipitation data, 580 data has been used for training networks and the rest selected randomly has been used for validation of the models. The used ANN model is a new approach of three-layer feed-forward perceptron network with back propagation algorithm that employs the gradient decent algorithm for its training it. The sensitivity of the prediction accuracy to the content and length of input layer has investigated. Based on the most suitable parameters and after trial and error, two structures M531 and M741 have been selected. Statistical properties have calculated to examine the performance of the models and it found that in the best model of monthly prediction, the correlation coefficient (R), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are 0.92, 1.00 mm and 5.13 mm, respectively.

Keywords

, artificial neural networks, precipitation, prediction
برای دانلود از شناسه و رمز عبور پرتال پویا استفاده کنید.

@inproceedings{paperid:1015409,
author = {Khodashenas, Saeed Reza and Khalili, Najmeh and Davary, Kamran},
title = {Prédiction de Précipitation mensuelle par réseau de neurones artificiel (Étude de cas: station synoptique de Mashhad)},
booktitle = {NOVATECH 2010,7th international conferenc on sustainable techniques and strategiesin urban water management},
year = {2010},
location = {Lyon, french},
keywords = {artificial neural networks; precipitation; prediction},
}

[Download]

%0 Conference Proceedings
%T Prédiction de Précipitation mensuelle par réseau de neurones artificiel (Étude de cas: station synoptique de Mashhad)
%A Khodashenas, Saeed Reza
%A Khalili, Najmeh
%A Davary, Kamran
%J NOVATECH 2010,7th international conferenc on sustainable techniques and strategiesin urban water management
%D 2010

[Download]