Effects of Data Pre-processing on the Prediction Accuracy of Artificial Neural Network Model in Hydrological Time Series

Abstract

The accurate prediction of hydrological behaviour in both urban and rural watershed can provide valuable information for the urban planning, land use, design of civil project and water resources management. Hydrology system is influenced by many factors such as weather, land cover, infiltration, evapotranspiration, so it includes the good deal of stochastic dependent component, multi-time scale and highly nonlinear characteristics. Hydrologic time series are often nonlinear. In spite of high flexibility of Artificial Neural Network (ANN) in modelling hydrologic time series, sometimes signals exhibit seasonal irregularity. In such situation, ANN may not be able to cope with such data if pre-processing of input and/or output data is not performed. Pre-processing data refers to analysing and transforming input and output variables in order to detect trends, minimise noise, underline important relationship and flatten the variables distribution in a time series. These analysis and transformations help the model learn relevant patterns. Pre-processing techniques, which facilitates stabilisation of the mean and variance, and seasonality removal, are often applied to remove irregularities in data used to build soft computing models. In this study, different data pre-processing techniques are presented to deal with irregularity components existing in a hydrologic time series data of the Brahmaputra basin within India at the Pandu gauging station near Guwahati city using daily time unit and their properties are evaluated by performing one step ahead flow forecasting using ANN. The model results were evaluated using root mean square error (RMSE) and mean absolute percentage error (MAPE) and found that logarithmic-based pre-processing techniques provide better forecasting performance among various pre-processing techniques. The results indicate that detecting irregularities and selecting an appropriate pre-processing technique is highly beneficial in improving the prediction performance of ANN model.