Applying recurrent fuzzy neural network to predict the Runoff of Srepok River

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F14%3A86093037" target="_blank" >RIV/61989100:27240/14:86093037 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-662-45237-0_7" target="_blank" >http://dx.doi.org/10.1007/978-3-662-45237-0_7</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-662-45237-0_7" target="_blank" >10.1007/978-3-662-45237-0_7</a>

Result language
angličtina
Original language name
Applying recurrent fuzzy neural network to predict the Runoff of Srepok River
Original language description
Recurrent fuzzy neural network (RFNN) is proven to be a great method for modeling, characterizing and predicting many kinds of nonlinear hydrological time series data such as rainfall, water quality, and river runoff. In our study, we employed RFNN to find out the correlation between the climate data and the runoff of Srepok River in Vietnam and then to model and predict the runoff of Srepok River in the current, as well as in the future. In order to prove the advantage of RFNN, we compare RFNN with anenvironmental model called SWAT on the same dataset. We conduct experiments using the climate data and the daily river's runoff data that have been collected in 22 years, ranging from 1900 to 2011. The experiment results show that the relative error of RFNN is about 0.35 and the relative error of SWAT is 0.44. It means that RFNN outperforms SWAT. Moreover, the most important advantage of RFNN when comparing with SWAT is that RFNN does not need much data as SWAT does. IFIP International F
Czech name
—
Czech description
—

Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)