Improving Daily Streamflow Forecasting Using Deep Belief Net-Work Based on Flow Regime Recognition

Abstract

Streamflow forecasting is of great significance for water resources planning and management. In recent years, numerous data-driven models have been widely used for streamflow forecasting. However, the traditional single data-driven model ignores the utilization of different streamflow regimes. This study proposed an integrated framework for daily streamflow forecasting based on the regime recognition of flow sequences. The framework integrates self-organizing maps (SOM) for identifying streamflow sub-sequences, the random forests (RF) algorithm to select input variables for different streamflow sub-sequences, and a deep belief network (DBN) for establishing complex relationships between the selected input variables and streamflows for different sub-sequences. Specifically, the integrated framework was applied to forecast daily streamflow at the Xiantao hydrological station in the Hanjiang River Basin, China. The results show that the developed integrated framework has higher streamflow prediction accuracy than the single data-driven model (i.e., the DBN model in this study), with Nash efficiency coefficient (NSE) of 0.91/0.81 and coefficient of determination (R2) of 0.93/0.89 for the integrated framework/DBN model during the validation period, respectively. Additionally, the prediction accuracy of the peak flood was also improved. The relative error of the peak flood derived from the integrated framework was reduced by 4.6%, compared with the single DBN model. Overall, the constructed integration framework, considering the complex characteristic of different flow regimes, could improve the accuracy for daily streamflow forecasting.

Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review

“…Hydrological studies typically divide streamflow into baseflow and excess flow, but streamflow generation is a complex process involving multiple stages, including the ascending and descending limbs of a hydrograph and its baseflow [152,153]. The distinct segments of a flow hydrograph are generated by a range of physical watershed mechanisms [154].…”

“…They used pattern recognition to build ANN and SVM models. Furthermore, Shen et al [153] segmented a hydrograph into baseflow, rising limb, and falling limb using the self-organizing map (SOM) and then grouped the hydro-meteorological data accordingly to improve flow prediction. [153] Improved peak values and higher accuracy.…”