Estimating net radiation at surface using artificial neural networks: a new approach
This study describes the results of artificial neural network (ANN) models to estimate net radiation (Rn), at surface. Three ANN models were developed based on meteorological data such as wind velocity and direction, surface and air temperature, relative humidity, and soil moisture and temperature....
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2011 |
| País: | Brasil |
| Institución: | Universidade Federal do Ceará (UFC) |
| Repositorio: | Repositório Institucional da Universidade Federal do Ceará (UFC) |
| Idioma: | inglés |
| OAI Identifier: | oai:repositorio.ufc.br:riufc/72063 |
| Acceso en línea: | http://www.repositorio.ufc.br/handle/riufc/72063 |
| Access Level: | acceso abierto |
| Palabra clave: | Artificial Neural Network (ANN) Radiation Meteorological parameters Radiação Parâmetros meteorologicos |
| Sumario: | This study describes the results of artificial neural network (ANN) models to estimate net radiation (Rn), at surface. Three ANN models were developed based on meteorological data such as wind velocity and direction, surface and air temperature, relative humidity, and soil moisture and temperature. A comparison has been made between the Rn estimates provided by the neural models and two linear models (LM) that need solar incoming shortwave radiation measurements as input parameter. Both ANN and LM results were tested against in situ measured Rn. For the LM ones, the estimations showed a root mean square error (RMSE) between 34.10 and 39.48 Wm−2 and correlation coefficient (R2 ) between 0.96 and 0.97 considering both the developing and the testing phases of calculations. The estimates obtained by the ANN models showed RMSEs between 6.54 and 48.75 Wm−2 and R2 between 0.92 and 0.98 considering both the training and the testing phases. The ANN estimates are shown to be similar or even better, in some cases, than those given by the LMs. According to the authors’ knowledge, the use of ANNs to estimate Rn has not been discussed earlier, and based on the results obtained, it represents a formidable potential tool for Rn prediction using commonly measured meteorological parameters. |
|---|