Zhenghao Zhang, Qiang Zhang, Vijay P. Singh
[Zhenghao Zhang]. Department of Water Resources and Environment, Sun Yatsen University, Guangzhou 510275, China.
[Qiang Zhang]. Key Laboratory of Environmental Change and Natural Disaster, Ministry of Education, Beijing Normal University, Beijing 100875, China.
[Qiang Zhang]. Faculty of Geographical Science, Academy of Disaster Reduction and Emergency Management, Beijing Normal University, Beijing 100875, China.
[Qiang Zhang]. State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing 100875, China.
[Vijay P. Singh]. Department of Biological and Agricultural Engineering and Zachry Department of Civil Engineering, Texas A&M University, College Station, Texas, USA.
ABSTRACT: Eight data-driven models and five data pre-processing methods were summarized; the multiple linear regression (MLR), artificial neural network (ANN) and wavelet decomposition (WD) models were then used in short-term streamflow forecasting at four stations in the East River basin, China. Five-fold cross-validation was used to divide the training dataset into non-stationary and stationary datasets for the periods 1955–1979 and 1980–2004. Besides, non-stationary monthly data for the period 1954–2009 were analysed at Longchuan station (LS). The wavelet-artificial neural network (W-ANN) method was used to predict 1-month-ahead monthly streamflow at LS. The results indicate better performance of MLR and wavelet- multiple linear regression (W-MLR) in analysing the stationary trained dataset. Four models showed similar performance in 1-day-ahead streamflow forecasting, while W-MLR and W-ANN performed better in 5-day-ahead forecasting. Three reservoirs were shown to have more influence on downstream than upstream streamflow and models had the worst performance at Boluo station. Furthermore, the W-ANN model performed well for 1-month-ahead streamflow forecasting at LS with consideration of a deterministic component.
Published in Hydrological Sciences Journal, 2018, https://doi.org/10.1080/02626667.2018.1469756.
