A C-Vine Copula-Based Quantile Regression Method for Streamflow Forecasting in Xiangxi River Basin, China

In this study, a C-vine copula-based quantile regression (CVQR) model is proposed for forecasting monthly streamflow. The CVQR integrates techniques vine copulas and into framework that can effectively establish relationships between the multidimensional response-independent variables as well capture upper tail or asymmetric dependence (i.e., extreme values). applied to Xiangxi River basin located in Three Gorges Reservoir area China streamflow forecasting. Multiple linear (MLR) artificial neural network (ANN) are also compared illustrate applicability of CVQR. results show performs best calibration period prediction. indicate MLR has worst effects (flood events) confidence interval predictions. Moreover, performance ANN tends be overestimated process peak Notably, most effective at capturing dependences among hydrometeorological floods). These findings very helpful decision-makers hydrological identification water resource management practices.