期刊名称:Journal of Environmental Hydrology (ältere Jahrgänge)
印刷版ISSN:1058-3912
电子版ISSN:1996-7918
出版年度:2011
卷号:19
出版社:IAEH
摘要:The need for precipitation data and the importance of its duration in hydrological and climatic phenomena motivate investigators to develop reconstruction methods. Four methods are artificial neural network, normal ratio, inverse distance weighting, and geographical coordinate. These methods are compared in this study using monthly precipitation data of three stations, Dolat-Abad, Kabootar-Abad and Refinery plant around the city of Esfahan, Iran. Mean absolute error and coefficient of correlation of the results are compared to select the most appropriate method. The neural network approach shows the best performance compared with the other methods.