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