A Probabilistic Wavelet–Support Vector Regression Model for Streamflow Forecasting with Rainfall and Climate Information Input*

Abstract

It is essential to explore reliable streamflow forecasting techniques for water resources management. In this study, a Bayesian wavelet–support vector regression model (BWS model) is developed for one- and multistep-ahead streamflow forecasting using local meteohydrological observations and climate indices including El Niño–Southern Oscillation (ENSO) and the Indian Ocean dipole (IOD) as potential predictors. To accomplish this, a two-step strategy is applied. In the first step, the discrete wavelet transform is coupled with a support vector regression model for streamflow prediction. The three key factors of mother wavelets, decomposition levels, and edge effects are considered in the wavelet decomposition phase when using the hybrid wavelet–support vector regression model (WS model). Different combinations of these factors form a variety of WS models with corresponding forecasts. The second step combines multiple candidate WS models with “good” performance via Bayesian model averaging. This integrates the predictive strengths of different candidate WS models, giving a realistic assessment of the predictive uncertainty. The new ensemble model is used to forecast daily and monthly streamflows at two sites in Dongjiang basin, southern China. The results show that the proposed BWS model consistently generates more reliable predictions for daily (lead times of 1–7 days) and monthly (lead times of 1–3 months) forecasts as compared with the best single-member WS models and the adaptive neuro-fuzzy inference system (ANFIS). Furthermore, the proposed BWS model provides detailed information about the predictive uncertainty.

A probabilistic prediction network for hydrological drought identification and environmental flow assessment

“…The first watershed (WS I) is part of the Glan River Basin located in southwestern Germany, which has a size of 1092 km² [ Hellebrand et al ., ]. The second watershed (WS II) is the Dongjiang Basin in southern China and has an area of 27,040 km² [ Liu et al ., ]. The third watershed (WS III) is the Upper Colorado River Basin in western U.S. with a drainage area of approximately 284,900 km².…”

Dongting Lake Water Level Forecast and Its Relationship with the Three Gorges Dam Based on a Long Short-Term Memory Network

“…Khedun et al [17] used a copula-based model to examine the dependence structure between the large-scale climate indices and average monthly seasonal precipitation and then used it to forecast precipitation anomalies in different climate divisions of Texas, USA. Liu et al [18] developed a Bayesian wavelet-support vector regression model (BWS model) using local meteohydrological observations and climate indices as potential predictors for streamflow forecasting and proved its effectiveness for one-and multistep-ahead streamflow forecasting at two sites in Dongjiang basin, southern China. Also, Coulibaly [19] studied the potential of the echo state network (ESN) to make long-term predictions of lake water levels and applied the ESN to the Great Lakes.…”

A multivariate conditional model for streamflow prediction and spatial precipitation refinement

“…Over the past few decades, considerable efforts have been made to develop and apply data‐driven statistical techniques for the modeling of hydrological systems and forecasting of hydrometeorological variables. These data‐driven models have gained popularity in hydrological modeling and prediction, as they can be quickly developed, are easy to implement in real time, and require less information than physically based hydrological models [ Moradkhani et al , ; Liu et al , ]. Multiple linear regression and autoregressive moving average models are probably the most widely used data‐driven methods for hydrological forecasting [ McKerchar and Delleur , , Noakes et al , ; Adamowski et al , ].…”