Evaluation of ocean-atmospheric indices as predictors for summer streamflow of the Yangtze River based on ROC analysis

Antecedent anomalies of sea surface temperature and atmospheric circulationare important signals for making long-term streamflowforecasts. In this study, four groups of ocean-atmospheric indices, i.e, El Nino Southern Oscillation(ENSO), the Northern Hemisphere atmospheric circulation, the Southern Hemisphere atmospheric circulation(SAC), and the Western Pacific and Indian Ocean SST (WPI), are evaluated for forecasting summer streamflowof the Yangtze River. The gradient boostingregression tree (GBRT) is used to forecast streamflowbased on each group of indices. The score based on receiver operating characteristics (ROC) curves, i.e., area under the ROC curve (AUC), is used to evaluate skills of models for identifying the high category and the low category of summer streamflow. It is found that the ENSO group and the SAC group show higher AUC values. Furthermore, both AUC values of GBRT models and individual indices show that the low flow years are easier to be identified than the high flow years. The result of this study highlights the skill from the Southern Hemispherecirculation systems for forecasting summer streamflowof the Yangtze River. Results of relative influences of predictors in GBRT models and AUC of individual indices indicate some key ocean-atmospheric indices, such as the Multivariate ENSO Indexand the 500-hPa height of the east of Australia.