A comparison between artificial neural network method and nonlinear regression method to estimate the missing hydrometric data

摘要

Missing values are a common problem faced in the analysis of hydrometric data. The need forncomplete hydrological data, especially hydrometric data for planning, development and designingnhydraulic structures, has become increasingly important. Reasonably estimating these missingnvalues is significant for the complete analysis and modeling of the hydrological cycle. The majornobjective of this paper is to estimate the missing annual maximum hydrometric data by usingnartificial neural networks (ANN). Sixteen stations, with 28 years of measurements, in thencatchment area of the Sefidroud watershed in the north of Iran were selected for thisninvestigation. Comparison between the results of ANN and the nonlinear regression method (NLR)nillustrated the efficiency of artificial neural networks and their ability to rebuild the missing data.nAccording to the coefficient of determination (R 2n) and the root mean squared value of errorn(RMSE), it was concluded that ANN provides a better estimation of the missing data.