A long lead time forecast model applying an ensemble approach for managing the great Karun multi-reservoir system

Abstract Flow prediction is regarded as a major computational process in strategic water resources planning. Prediction’s lead time has an inverse relationship with results’ accuracy and certainty. This research studies the impact of climate-atmospheric indices on surface runoff predictions long time. To this end, correlation 36 long-distance climate was examined at 10 key nodes Great Karun multi-reservoir system Iran, higher are divided into 4 different groups. Then, using Artificial Neural Network (ANN) Ensemble Learning to combine input variables, flow predicted 6-month horizons, results compared observed values. assess extending time, from proposed model those monthly model. The performed comparison shows that ensemble approach improves final significantly. Moreover, Tropical Pacific SST EOF, Caribbean SST, Nino1 + 2 found be influential parameters basin’s inflow. It performance varies hydrological conditions best obtained for dry seasons.