Modeling forecast uncertainty using fuzzy clustering

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F13%3A86096970" target="_blank" >RIV/61989100:27240/13:86096970 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-642-32922-7_30" target="_blank" >http://dx.doi.org/10.1007/978-3-642-32922-7_30</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-642-32922-7_30" target="_blank" >10.1007/978-3-642-32922-7_30</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Modeling forecast uncertainty using fuzzy clustering

Popis výsledku v původním jazyce

Numerical Weather Prediction (NWP) systems are state-of-the-art atmospheric models that can provide forecasts of various weather attributes. These forecasts are used in many applications as critical inputs for planning and decision making. However, NWP systems cannot supply any information about the uncertainty of the forecasts as their immediate outputs. In this paper, we investigate the application of Fuzzy C-means clustering as a powerful soft computing technique to discover classes of weather situations that follow similar forecast uncertainty patterns. These patterns are then utilized by distribution fitting methods to obtain Prediction Intervals (PIs) that can express the expected accuracy of the NWP system outputs. Three years of weather forecast records were used in a set of experiments to empirically evaluate the applicability of the proposed approach and the accuracy of the computed PIs. Results confirm that the PIs generated by the proposed post-processing procedure have a h

Název v anglickém jazyce

Modeling forecast uncertainty using fuzzy clustering

Popis výsledku anglicky

Numerical Weather Prediction (NWP) systems are state-of-the-art atmospheric models that can provide forecasts of various weather attributes. These forecasts are used in many applications as critical inputs for planning and decision making. However, NWP systems cannot supply any information about the uncertainty of the forecasts as their immediate outputs. In this paper, we investigate the application of Fuzzy C-means clustering as a powerful soft computing technique to discover classes of weather situations that follow similar forecast uncertainty patterns. These patterns are then utilized by distribution fitting methods to obtain Prediction Intervals (PIs) that can express the expected accuracy of the NWP system outputs. Three years of weather forecast records were used in a set of experiments to empirically evaluate the applicability of the proposed approach and the accuracy of the computed PIs. Results confirm that the PIs generated by the proposed post-processing procedure have a h

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2013

Kód důvěrnosti údajů

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

Název statě ve sborníku

Advances in Intelligent Systems and Computing

ISBN

978-3-642-32921-0

ISSN

2194-5357

e-ISSN

—

Počet stran výsledku

10

Strana od-do

287-296

Název nakladatele

Springer

Místo vydání

Heidelberg

Místo konání akce

Ostrava

Datum konání akce

5. 9. 2012

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—