Archive

Published: Građevinar 70 (2018) 8
Paper type: Original scientific paper
Download article (Croatian): PDF
Download article (English): PDF
View count: 0

Comparison of supervised learning methods for prediction of monthly average flow

Jadran Berbić, Eva Ocvirk, Gordon Gilja

Abstract

Long-term planning of water engineering systems requires knowledge of long-term availability of water, most often in the form of monthly average flow information. Knowledge from stochastic hydrology is most often applied, although possible scenarios also involve generation of synthetic flow. The use of climatic models imposes the possibility of modelling based on future scenarios, and it is assumed in the paper that supervised learning can be applied for this purpose. The paper analyses accuracy of three supervised learning models in three approaches and the autoregressive model in the first approach, for predicting monthly average flow as related to the length of a historic dataset.

Keywords
long-term planning, monthly average flow, autoregressive model, supervised learning

HOW TO CITE THIS ARTICLE:

Berbić, J., Ocvirk, E., Gilja, G.: Comparison of supervised learning methods for prediction of monthly average flow, GRAĐEVINAR, 70 (2018) 8, pp. 643-656, doi: https://doi.org/10.14256/JCE.2102.2017

OR:

Berbić, J., Ocvirk, E., Gilja, G. (2018). Comparison of supervised learning methods for prediction of monthly average flow, GRAĐEVINAR, 70 (8), 643-656, doi: https://doi.org/10.14256/JCE.2102.2017

LICENCE:

Creative Commons License
This paper is licensed under a Creative Commons Attribution 4.0 International License.
Authors:
Foto Berbic WEB
Jadran Berbić
Croatian Meteorological and Hydrological Service
Ocvirk WEB
Eva Ocvirk
University of Zagreb,
Faculty of Civil Engineering
Foto Gilja
Gordon Gilja