An Integration of Stationary Wavelet Transform and Nonlinear Autoregressive Neural Network with Exogenous Input for Baseline and Future Forecasting of Reservoir Inflow

For effective water resources management and planning, an accurate reservoir inflow forecast is essential not only in training and testing phases but also in particular future periods. The objective of this study is to develop a reservoir inflow integrated forecasting model, relying on nonlinear autoregressive neural network with exogenous input (NARX) and stationary wavelet transform (SWT), namely SWT-NARX. Due to the elimination of down-sampling operation, SWT provides influential reinforcement of efficiently extracting the hidden significant, temporal features contained in the nonstationary inflow time series without information loss. The decomposed SWT sub-time series are determined as input-output for NARX forecaster; where a multi-model ensemble global mean (MMEGM) of downscaled precipitation based on nine global climate models (GCMs) represents as a climate-change exogenous input. Two major reservoirs in Thailand, Bhumibol and Sirikit ones are focused. Pearson’s correlation coefficient (r) and root mean square error (RMSE) are employed for performance evaluation. The achieved results indicate that the SWT-NARX explicitly outperforms the comparable forecasting approaches regarding a historical baseline period (1980–1999). Therefore, such SWT-NARX is further employed for future projection of the reservoir inflow over near (2010–2039) -, mid (2040–2069) - and far (2070–2099) - future periods against the inflow of the baseline one.