Using artificial neural networks to solve problems of channel flow interpolation (on the example of the Kazanka river)
DOI:
https://doi.org/10.24852/2411-7374.2023.2.45.48Keywords:
river flow, modeling, water costs, neural networks, Kazanka riverAbstract
The possibilities of using an artificial neural network based on the multilayer perceptron paradigm for interpolating the values of channel water discharges along the length of the Kazanka River are analyzed. The experiment demonstrated the high efficiency of the obtained neural network model, which turned out to be more accurate than linear and polynomial approximators traditionally used to solve such problems. The resulting model can be used in assessing the normatively permissible discharges in any part of the river
References
Butch G. Ob"ektno-orientirovannoe proektirovanie s primerami primeneniya [Object-oriented design with examples of application]. Moscow: Concord, 1992. 519 p.
Kruglov V.V., Borisov V.V. Iskusstvennye nejronnye seti. Teoriya i praktika [Artificial neural networks. Theory and practice]. Moscow: Hotline-Telecom, 2002. 382 p.
Khaikin S. Nejronnye seti: polnyj kurs [Neural networks: a complete course]. Moscow: Williams, 2006. 1104 p.
Yasnitsky L.N. Vvedenie v iskusstvennyj intellekt [Introduction to artificial intelligence]. Moscow: Publishing Center «Academy», 2008. 176 p.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.