Development of a Hybrid Data Driven Model for Hydrological Estimation

• Published in: Water resources management Vol. 32; no. 11; pp. 3737 - 3750
• Main Authors: Araghinejad, Shahab, Fayaz, Nima, Hosseini-Moghari, Seyed-Mohammad
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.09.2018; Springer Nature B.V
• Subjects: Artificial neural networks; Atmospheric Sciences; Civil Engineering; Drought; Earth and Environmental Science; Earth Sciences; Environment; Forecasting; Geotechnical Engineering & Applied Earth Sciences; Hydrogeology; Hydrologic models; Hydrology; Hydrology/Water Resources; Modelling; Multilayers; Neural networks; Resources; Statistical analysis; Stream discharge; Stream flow; Streamflow forecasting; Water resources; Probabilistic neural network; Generalized regression neural network; Streamflow forecasting; Hybrid models; Multi-layer perceptron
• ISSN: 0920-4741; 1573-1650
• DOI: 10.1007/s11269-018-2016-3

High and low stremflow values forecasting is of great importance in field of water resources in order to mitigate the impacts of flood and drought. Most of water resources models deal with the problem of not being flexible for modeling maximum and minimum flows. To overcome that shortcoming, a combination of artificial neural network (ANN) models is developed in this study for monthly streamflow forecasting. A probabilistic neural network (PNN) is used to classify each of the input-output patterns and afterward, the classified data are forecasted using a modified multi-layer perceptron (MMLP). In addition, the performance of the MLP and generalized regression neural network (GRNN) in streamflow forecasting are investigated and compared to the proposed method. The findings indicate that the R 2 associated with the suggested model is 46 and 80% higher compared to MLP and GRNN models, respectively.