Idioma:

The combined use of wavelet transform and black box models in reservoir inflow modeling

Umut Okkan, Balikesir University, Balikesir (Turkey) ; Zafer Ali Serbes, Ege University, Bornova-Izmir (Turkey)

Journal of Hydrology and Hydromechanics, 2013-06, Vol.61 (2), p.112-119 [Periódico revisado por pares]

Bratislava: De Gruyter Poland

Texto completo disponível

Citações Citado por

Enviar para

Título:
The combined use of wavelet transform and black box models in reservoir inflow modeling
Autor: Umut Okkan, Balikesir University, Balikesir (Turkey) ; Zafer Ali Serbes, Ege University, Bornova-Izmir (Turkey)
Assuntos: Algorithms ; Artificial intelligence ; Back propagation ; Black boxes ; DATOS METEOROLOGICOS ; Discrete Wavelet Transform ; DONNEE METEOROLOGIQUE ; feed forward neural networks ; http://www.fao.org/aos/agrovoc#c_29564 ; http://www.fao.org/aos/agrovoc#c_331037 ; http://www.fao.org/aos/agrovoc#c_37467 ; http://www.fao.org/aos/agrovoc#c_4881 ; http://www.fao.org/aos/agrovoc#c_8164 ; hybrid model ; Hydrology ; Least squares method ; least squares support vector machines ; mallows’ cp method ; Methods ; MODELE ; MODELOS ; multiple linear regression ; NEURAL NETWORKS ; Optimization techniques ; Precipitation ; Precipitation (meteorological) ; Propagation ; REDES DE NEURONAS ; Regression ; Regression analysis ; RESEAU DE NEURONES ; reservoir inflow modeling ; Reservoirs ; Support vector machines ; Time series ; TRANSFORMATION ; VECTEUR DE MALADIE ; VECTORES ; VECTORS ; Wavelet transforms ; WEATHER DATA
É parte de: Journal of Hydrology and Hydromechanics, 2013-06, Vol.61 (2), p.112-119
Notas: AI20130151
P10
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Descrição: In the study presented, different hybrid model approaches are proposed for reservoir inflow modeling from the meteorological data (monthly precipitation, one-month-ahead precipitation and monthly mean temperature data) by the combined use of discrete wavelet transform (DWT) and different black box techniques. Multiple linear regression (MLR), feed forward neural networks (FFNN) and least square support vector machines (LSSVM) were considered as the black box methods. In the modeling strategy, meteorological input data were decomposed into wavelet sub-time series at three resolution levels and ineffective sub-time series were eliminated by Mallows Cp based all possible regression method. As a result of all possible regression analyses, 2-months mode of time series of monthly temperature (D1 Tt), 8-months mode of time series (D3 Tt) of monthly temperature and approximation mode of time series (A3 Tt) of monthly temperature were eliminated. Remained effective sub-time series were used as the inputs of MLR, FFNN and LSSVM. When the performances of the training and testing periods were compared, it was observed that the DWTFFNN conjunction model has better results in terms of mean square errors (MSE) and determination coefficients (R2) statistics. The discrete wavelet transform approach also increased the accuracy of multiple linear regression and least squares support vector machines.
Editor: Bratislava: De Gruyter Poland
Idioma: Inglês;Tcheco;Eslovaco

Voltar para lista de resultados

Anterior Resultado 8 Avançar Ir para próxima página

Realização: Logos de Redes Sociais:

The combined use of wavelet transform and black box models in reservoir inflow modeling

Umut Okkan, Balikesir University, Balikesir (Turkey) ; Zafer Ali Serbes, Ege University, Bornova-Izmir (Turkey)

Bratislava: De Gruyter Poland

Buscando em bases de dados remotas. Favor aguardar.