We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
River flow prediction using hybrid PSOGSA algorithm based on feed-forward neural network.
- Authors
Meshram, Sarita Gajbhiye; Ghorbani, Mohmmmad Ali; Shamshirband, Shahaboddin; Karimi, Vahid; Meshram, Chandrashekhar
- Abstract
River flow modeling plays an important role in water resources management. This research aims at developing a hybrid model that integrates the feed-forward neural network (FNN) with a hybrid algorithm of the particle swarm optimization and gravitational search algorithms (PSOGSA) to predict river flow. Fundamentally, as the precision of a FNN model is essentially dependent upon the assurance of its model parameters, this review utilizes the PSOGSA for ideal preparing of the FNN model and gives the likelihood of boosting the execution of FNN. For this purpose, monthly river flow time series from 1990 to 2016 for Garber station of the Turkey River located at Clayton County, Iowa, were used. The proposed FNN-PSOGSA was applied in monthly river flow data. The results indicate that the FNN-PSOGSA model improves the forecasting accuracy and is a feasible method in predicting the river flow.
- Subjects
IOWA; STREAMFLOW; PARTICLE swarm optimization; SEARCH algorithms; WATER supply; WATER management
- Publication
Soft Computing - A Fusion of Foundations, Methodologies & Applications, 2019, Vol 23, Issue 20, p10429
- ISSN
1432-7643
- Publication type
Article
- DOI
10.1007/s00500-018-3598-7