The possibility of short-term water flow forecasting in a karst region is presented in this paper. Four state-of-the-art machine learning algorithms are used for the one day ahead forecasting: multi-layer perceptron neural network, radial basis function neural network, support vector machines for regression (SVR), and adaptive neuro fuzzy inference system (ANFIS). The results show that the ANFIS model outperforms other algorithms when the root mean square error and mean absolute error are used as quality indicators.
Keywords:
artificial neural network / SVR / ANFIS / rainfall-runoff ratio in karst areas
TY - JOUR
AU - Kovacević, Miljan
AU - Ivanišević, Nenad
AU - Dašić, Tina
AU - Marković, Ljubo
PY - 2018
UR - https://grafar.grf.bg.ac.rs/handle/123456789/968
AB - The possibility of short-term water flow forecasting in a karst region is presented in this paper. Four state-of-the-art machine learning algorithms are used for the one day ahead forecasting: multi-layer perceptron neural network, radial basis function neural network, support vector machines for regression (SVR), and adaptive neuro fuzzy inference system (ANFIS). The results show that the ANFIS model outperforms other algorithms when the root mean square error and mean absolute error are used as quality indicators.
PB - Union of Croatian Civil Engineers and Technicians
T2 - Građevinar
T1 - Application of artificial neural networks for hydrological modelling in karst
EP - 10
IS - 1
SP - 1
VL - 70
DO - 10.14256/JCE.1594.2016
ER -
@article{
author = "Kovacević, Miljan and Ivanišević, Nenad and Dašić, Tina and Marković, Ljubo",
year = "2018",
abstract = "The possibility of short-term water flow forecasting in a karst region is presented in this paper. Four state-of-the-art machine learning algorithms are used for the one day ahead forecasting: multi-layer perceptron neural network, radial basis function neural network, support vector machines for regression (SVR), and adaptive neuro fuzzy inference system (ANFIS). The results show that the ANFIS model outperforms other algorithms when the root mean square error and mean absolute error are used as quality indicators.",
publisher = "Union of Croatian Civil Engineers and Technicians",
journal = "Građevinar",
title = "Application of artificial neural networks for hydrological modelling in karst",
pages = "10-1",
number = "1",
volume = "70",
doi = "10.14256/JCE.1594.2016"
}
Kovacević, M., Ivanišević, N., Dašić, T.,& Marković, L.. (2018). Application of artificial neural networks for hydrological modelling in karst. in Građevinar
Union of Croatian Civil Engineers and Technicians., 70(1), 1-10.
https://doi.org/10.14256/JCE.1594.2016
Kovacević M, Ivanišević N, Dašić T, Marković L. Application of artificial neural networks for hydrological modelling in karst. in Građevinar. 2018;70(1):1-10.
doi:10.14256/JCE.1594.2016 .
Kovacević, Miljan, Ivanišević, Nenad, Dašić, Tina, Marković, Ljubo, "Application of artificial neural networks for hydrological modelling in karst" in Građevinar, 70, no. 1 (2018):1-10,
https://doi.org/10.14256/JCE.1594.2016 . .
