Assessment of model fusion strategy for increasing the accuracy of autumn rainfall forecasting

Autumn precipitation forecasting plays a key role in agricultural planning especially rainfed farming feasibility studies. andnbsp;In this study, model fusion technique has been used in order to increase the accuracy of autumn precipitation forecast. Based on two teleconnection signals of SOI and NINO 3.4 as predictors, five models including; Artificial Neural Network (ANN), Generalized Regression Neural Network (GRNN), Support Vector Regression (SVR), K-Nearest Neighbor (KNN), and Linear Regression (LR) with optimized structure have been implemented as individual rainfall forecasting models (IPFMs)in Seimareh subbasin of Karkheh basin, IRAN.In order to combine the IPFMs, the ordered weighted aggregation strategy (OWA) has been performed in which, two weighting methods including Orness and Orlike methods have been used and assessed for determining the weights of IPFMs. The results of this study showed that the forecasted rainfall obtained from two methods of OWA model fusion strategy has more accuracy comparing to individual forecasting models. Moreover, application of the Orlike method did a quite better job than Orness method. Besides, comparing the results of the OWA strategy methods with two other strategies viz model fusion with artificial neural network and selecting the best IPFM revealed that both Orness and Orlike methods are performing more precisely than two other strategies in forecasting rainfall.