Longer Period Runoff Forecasts by Mean of Multilayer Perceptron Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F44555601%3A13520%2F09%3A00005107" target="_blank" >RIV/44555601:13520/09:00005107 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Longer Period Runoff Forecasts by Mean of Multilayer Perceptron Neural Networks

Popis výsledku v původním jazyce

The article addresses the modelling of runoff based on precipitation data collected in the Sázava River and Ploučnice River basins. Knowledge acquired in previous research in the Ploučnice River basin was found to be useful in this study. Rainfall and runoff data (both with a 1 hour time step) were obtained from the Czech Hydrometeorological Institute (CHMI). The time period of Aug.1?Sept.11, 2002 was selected, mainly because of the flood event on the 14th of Aug., 2002 in the Sázava River basin. Calculations were performed with feed-forward neural networks, namely multi-layer perceptron networks trained by back propagation. Network architectures were tested on 1-hour predictions first and then compared with the 6-hour predictions. The role of the accumulated runoff input has been also studied.

Název v anglickém jazyce

Longer Period Runoff Forecasts by Mean of Multilayer Perceptron Neural Networks

Popis výsledku anglicky

The article addresses the modelling of runoff based on precipitation data collected in the Sázava River and Ploučnice River basins. Knowledge acquired in previous research in the Ploučnice River basin was found to be useful in this study. Rainfall and runoff data (both with a 1 hour time step) were obtained from the Czech Hydrometeorological Institute (CHMI). The time period of Aug.1?Sept.11, 2002 was selected, mainly because of the flood event on the 14th of Aug., 2002 in the Sázava River basin. Calculations were performed with feed-forward neural networks, namely multi-layer perceptron networks trained by back propagation. Network architectures were tested on 1-hour predictions first and then compared with the 6-hour predictions. The role of the accumulated runoff input has been also studied.

Druh

D - Stať ve sborníku

CEP obor

DA - Hydrologie a limnologie

OECD FORD obor

—

Projekt

<a href="/cs/project/WD-44-07-1" target="_blank" >WD-44-07-1: Modelové oešení revitalizace prumyslových regionu a území po tižbi uhlí na poíkladu Podkrušnohooí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2009

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Environmental Accounting - Sustainable Development Indicators

ISBN

978-80-7414-124-9

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

—

Název nakladatele

Univerzita J. E. Purkyně

Místo vydání

Ústí nad Labem

Místo konání akce

Praha

Datum konání akce

23. 4. 2009

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—