Post-processing of Wind-speed Forecasts Using the extended Perfect Prog method with Polynomial Neural Networks to elicit PDE models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F18%3A10240159" target="_blank" >RIV/61989100:27240/18:10240159 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27730/18:10240159

Výsledek na webu

<a href="https://www.springer.com/gp/book/9783030143466" target="_blank" >https://www.springer.com/gp/book/9783030143466</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Post-processing of Wind-speed Forecasts Using the extended Perfect Prog method with Polynomial Neural Networks to elicit PDE models

Popis výsledku v původním jazyce

Anomalies in local weather cause inaccuracies in daily predictions using meso-scale numerical models. Statistical methods using historical data can adapt the forecasts to specific local conditions. Differential polynomial network is a recent machine learning technique used to develop post-processing models. It decom-poses and substitutes for the general linear Partial Differential Equation being able to describe the local atmospheric dynamics which is too complex to be mod-elled by standard soft-computing. The complete derivative formula is decom-posed, using a multi-layer polynomial network structure, into specific sub-PDE solutions of the unknown node sum functions. The sum PDE models, using a polynomial PDE substitution based on Operational Calculus, represent spatial da-ta relations between the relevant meteorological inputs-&gt;output quantities. The proposed forecasts post-processing is based on the 2-stage approach of the Per-fect Prog method used routinely in meteorology. The original procedure is ex-tended with initial estimations of the optimal numbers of training days whose lat-est data observations are used to elicit daily prediction models in the 1st stage. De-termination of the optimal models initialization time allows for improvements in the middle-term numerical forecasts of wind speed in prevailing more or less set-tled weather. In the 2nd stage the correction model is applied to forecasts of the training input variables to calculate 24-hour prediction series of the target wind speed at the corresponding time.

Název v anglickém jazyce

Post-processing of Wind-speed Forecasts Using the extended Perfect Prog method with Polynomial Neural Networks to elicit PDE models

Popis výsledku anglicky

Anomalies in local weather cause inaccuracies in daily predictions using meso-scale numerical models. Statistical methods using historical data can adapt the forecasts to specific local conditions. Differential polynomial network is a recent machine learning technique used to develop post-processing models. It decom-poses and substitutes for the general linear Partial Differential Equation being able to describe the local atmospheric dynamics which is too complex to be mod-elled by standard soft-computing. The complete derivative formula is decom-posed, using a multi-layer polynomial network structure, into specific sub-PDE solutions of the unknown node sum functions. The sum PDE models, using a polynomial PDE substitution based on Operational Calculus, represent spatial da-ta relations between the relevant meteorological inputs-&gt;output quantities. The proposed forecasts post-processing is based on the 2-stage approach of the Per-fect Prog method used routinely in meteorology. The original procedure is ex-tended with initial estimations of the optimal numbers of training days whose lat-est data observations are used to elicit daily prediction models in the 1st stage. De-termination of the optimal models initialization time allows for improvements in the middle-term numerical forecasts of wind speed in prevailing more or less set-tled weather. In the 2nd stage the correction model is applied to forecasts of the training input variables to calculate 24-hour prediction series of the target wind speed at the corresponding time.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

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

2018

Kód důvěrnosti údajů

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

Název periodika

Advances in Intelligent Systems and Computing. Volume 923

ISSN

2194-5357

e-ISSN

—

Svazek periodika

923

Číslo periodika v rámci svazku

únor-březen, 2019

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

10

Strana od-do

1-10

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—