USING THE METHODS OF NEURAL NETWORK LEARNING FOR PEAK WATER LEVEL PREDICTION: A CASE STUDY FOR THE RIVERS IN THE DVINA-PECHORA BASIN

Standard

USING THE METHODS OF NEURAL NETWORK LEARNING FOR PEAK WATER LEVEL PREDICTION: A CASE STUDY FOR THE RIVERS IN THE DVINA-PECHORA BASIN. / Сумачев, Александр Эдуардович; Банщикова, Л.С.; Грига, Семен Алексеевич.

In: Russian Meteorology and Hydrology, Vol. 49, No. 4, 01.04.2024, p. 354-362.

Research output: Contribution to journal › Article › peer-review

BibTeX

@article{49f2aa808a39411385b9a26fd5a9a10f,

title = "USING THE METHODS OF NEURAL NETWORK LEARNING FOR PEAK WATER LEVEL PREDICTION: A CASE STUDY FOR THE RIVERS IN THE DVINA-PECHORA BASIN",

abstract = "Abstract: The paper examines the implementation of neural network methods for predicting peak water levels during the period of spring ice drift by the example of the Sukhona, Northern Dvina, and Pechora rivers. All considered neural network methods have shown high efficiency according to the criteria recommended by the Hydrometcenter of Russia and surpassed regression dependencies in the skill of forecasts. When using the method of training artificial neural networks, the standard error of prediction is reduced by approximately 10–20% as compared with regression dependencies.",

keywords = "Dvina-Pechora basin, neural networks, peak water levels, prediction",

author = "Сумачев, {Александр Эдуардович} and Л.С. Банщикова and Грига, {Семен Алексеевич}",

year = "2024",

month = apr,

day = "1",

doi = "10.3103/s1068373924040095",

language = "English",

volume = "49",

pages = " 354--362",

journal = "Russian Meteorology and Hydrology",

issn = "1068-3739",

publisher = "Allerton Press, Inc.",

number = "4",

}

RIS

TY - JOUR

T1 - USING THE METHODS OF NEURAL NETWORK LEARNING FOR PEAK WATER LEVEL PREDICTION: A CASE STUDY FOR THE RIVERS IN THE DVINA-PECHORA BASIN

AU - Сумачев, Александр Эдуардович

AU - Банщикова, Л.С.

AU - Грига, Семен Алексеевич

PY - 2024/4/1

Y1 - 2024/4/1

N2 - Abstract: The paper examines the implementation of neural network methods for predicting peak water levels during the period of spring ice drift by the example of the Sukhona, Northern Dvina, and Pechora rivers. All considered neural network methods have shown high efficiency according to the criteria recommended by the Hydrometcenter of Russia and surpassed regression dependencies in the skill of forecasts. When using the method of training artificial neural networks, the standard error of prediction is reduced by approximately 10–20% as compared with regression dependencies.

AB - Abstract: The paper examines the implementation of neural network methods for predicting peak water levels during the period of spring ice drift by the example of the Sukhona, Northern Dvina, and Pechora rivers. All considered neural network methods have shown high efficiency according to the criteria recommended by the Hydrometcenter of Russia and surpassed regression dependencies in the skill of forecasts. When using the method of training artificial neural networks, the standard error of prediction is reduced by approximately 10–20% as compared with regression dependencies.

KW - Dvina-Pechora basin

KW - neural networks

KW - peak water levels

KW - prediction

UR - https://www.elibrary.ru/item.asp?id=68410141

UR - https://www.mendeley.com/catalogue/7fd4ec0b-ceaa-31e9-8439-bd897f0385b1/

U2 - 10.3103/s1068373924040095

DO - 10.3103/s1068373924040095

M3 - Article

VL - 49

SP - 354

EP - 362

JO - Russian Meteorology and Hydrology

JF - Russian Meteorology and Hydrology

SN - 1068-3739

IS - 4

ER -

ID: 125278722