57
Tecnología y Ciencias del Agua
, vol. VIII, núm. 2, marzo-abril de 2017, pp. 51-60
Kan
et al.
,
Daily streamflow simulation based on improved machine learning method
ISSN 2007-2422
•
Figure 3. Observed and simulated hydrographs of the PKEK model: (a) Calibration; (b) Validation.
autoregressive characteristic of the ANN mod-
els. The ANN models place a higher weighting
to the latest simulated discharge value utilized
as inputs to the model. As a result, the model
follows the general trend as prescribed by the
simulated discharge.
Conclusions
An improved hybrid data-driven model, named
PKEK, is proposed in this paper to overcome
the disadvantages of the previously proposed
NU-PEK model in daily RR simulation. For the
