ESTIMATING LATENT HEAT FLUX OVER RESERVOIRS USING AN ARTIFICIAL NEURAL NETWORK
Micrometeorology monitoring has been used in reservoirs for latent heat flux measurements by eddy covariance. It is hard to establish long and continuous measurement datasets due to the complexity involved in this monitoring. When fails occur there is necessary a gap filling procedure to keep the co...
| Autores: | , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2016 |
| País: | Brasil |
| Institución: | Universidade Federal de Santa Maria (UFSM) |
| Repositorio: | Revista Ciência e Natura (Online) |
| Idioma: | portugués |
| OAI Identifier: | oai:ojs.pkp.sfu.ca:article/20264 |
| Acceso en línea: | https://periodicos.ufsm.br/cienciaenatura/article/view/20264 |
| Access Level: | acceso abierto |
| Palabra clave: | Latent heat flux. Lakes. Neural network. Eddy covariance. Micrometeorology. Fluxo de calor latente. Lagos. Redes neurais. Covariâncias turbulentas. Micrometeorologia. |
| Sumario: | Micrometeorology monitoring has been used in reservoirs for latent heat flux measurements by eddy covariance. It is hard to establish long and continuous measurement datasets due to the complexity involved in this monitoring. When fails occur there is necessary a gap filling procedure to keep the continuity of the series. This filling could be performed through statistical techniques and use of model results. In this work we assessed the performance of a backpropagation Artificial Neural Network (ANN) Model to estimatives of latent heat fluxes at Furnas Lake – MG to fill the gaps in 50 days measurement dataset. The ANN was applied using various sets of input parameters, layer structures and trainning time. The performance of ANN estimatives were compared of a classic mass transfer model. The index of agreement are used to evaluate the performance of the models. The ANN Model index of agreement equal to 0.93536 showing better results than transfer model with 0.89681. The results showed that the ANN could be used with great performance to estimate latent heat flux and gap filling. |
|---|