Developing a Distributed Real-time Streamflow Forecasting Framework for Use in Highly Regulated Basins

As a non-engineering measure for flood control, real-time forecasting provides valuable information like the magnitude and occurrence time of flood peak, which is essential for decision-making. In China, many reservoirs are built and operated in major river including ChangJiang River Basin. Operations of reservoirs pose new challenges for real-time forecasting. For example, (1) its difficult to calibrate model parameters due to human-impaired streamflow series, (2) the leading time of real-time forecasting is much shorter. To address these challenges, we propose a distributed real-time streamflow forecasting framework using the Xinanjiang (XAJ) hydrological model. We evaluate different scale of computational units of the XAJ model to better characterize the runoff processes, land surface characteristics, and meteorology factors. We then develop a set of models to calculate model parameters from land surface characteristics, which reduce the calibration requirement. We also develop an algorithm to correct the bias of precipitation forecasts, which is coupled with real-time forecasting framework. This helps to extend the leading time of real-time forecasting. Our proposed framework is tested and validated at Upper Changjiang River Basin and get promising feedbacks.