Application of Artificial Intelligence in Operational Hydrology

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F02%3A01079512" target="_blank" >RIV/68407700:21110/02:01079512 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Application of Artificial Intelligence in Operational Hydrology

Popis výsledku v původním jazyce

Disaster floods in 1997, 1998 and 2000 has provoked plenty of studies in field of operational forecasting of river flows, upgrading of traditional hydrological models, and developing of new approaches. Application of theory of fuzzy sets and fuzzy logicfor function approximation, classification and/or for control is often limited by finding leading fuzzy rules. In case of the Adaptive Neuro-Fuzzy Inference System (ANFIS) are rules chosen as all possible permutation of input membership functions. This approach brings exponential growing of the number of rules. The modern rule extraction methods are based on estimating clusters in the data; each cluster obtained corresponds to a fuzzy rule that relates a region in the input space to an output region. The hybrid neural network and ANFIS with rules derived by subtractive clustering were used to evaluate a hydrological model for operational forecasting of river flows in the Zruč nad Sázavou profile in the Sazava river catchment.

Název v anglickém jazyce

Application of Artificial Intelligence in Operational Hydrology

Popis výsledku anglicky

Disaster floods in 1997, 1998 and 2000 has provoked plenty of studies in field of operational forecasting of river flows, upgrading of traditional hydrological models, and developing of new approaches. Application of theory of fuzzy sets and fuzzy logicfor function approximation, classification and/or for control is often limited by finding leading fuzzy rules. In case of the Adaptive Neuro-Fuzzy Inference System (ANFIS) are rules chosen as all possible permutation of input membership functions. This approach brings exponential growing of the number of rules. The modern rule extraction methods are based on estimating clusters in the data; each cluster obtained corresponds to a fuzzy rule that relates a region in the input space to an output region. The hybrid neural network and ANFIS with rules derived by subtractive clustering were used to evaluate a hydrological model for operational forecasting of river flows in the Zruč nad Sázavou profile in the Sazava river catchment.

Druh

D - Stať ve sborníku

CEP obor

JM - Inženýrské stavitelství

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

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

Rok uplatnění

2002

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of Workshop 2002

ISBN

80-01-02511-X

ISSN

—

e-ISSN

—

Počet stran výsledku

2

Strana od-do

1010-1011

Název nakladatele

ČVUT

Místo vydání

Praha

Místo konání akce

Praha

Datum konání akce

11. 2. 2002

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—