A comparison between the application of empirical and ANN methods for estimation of daily global solar radiation in Iran

作者：Jahani, Babak; Mohammadi, Babak^*

来源：Theoretical and Applied Climatology, 2019, 137(1-2): 1257-1269.

DOI：10.1007/s00704-018-2666-3

• ARTIFICIAL NEURAL-NETWORK
• SUPPORT VECTOR MACHINE
• ENERGY BALANCE ALGORITHM
• GENETIC ALGORITHM
• MULTILAYER PERCEPTRON
• METEOROLOGICAL DATA
• SUNSHINE DURATION
• MODEL
• HYBRID
• PREDICTION

The present study generally aims to provide a comparison between the performance and suitability of different types of models for estimation of daily global solar radiation in Iran, based on duration of sunshine hours and diurnal air temperature. These models consist of empirical, ordinary ANN, and ANN models coupled with genetic algorithm (so called coupled ANN models). The models' performance was evaluated and compared based on the error statistics root mean squared error (RMSE), mean bias error (MBE), and coefficient of determination (R-2). The empirical models (median of R-2, MBE, RMSE for AP 0.93, 37.0, and 179.3J/cm(2)/day) could generally perform much better than the ordinary ANN models (median of R-2, MBE, RMSE for MLP(n) 0.90, 55.7, and 243.5J/cm(2)/day). The performance of the ordinary ANN models was improved considerably after being coupled by genetic algorithm (median of R-2, MBE, RMSE for MLP-GA(n) 0.92, 38.4, and 185.5J/cm(2)/day), making them the most accurate models at most of the stations studied. However, the difference between the overall performances of these coupled ANN models and empirical ones was slight. Lastly, despite the coupled ANN models had relatively better accuracy compared to the empirical ones, when taking different metrics such as the required processing time, skill, and equipment into account, the empirical models appear to be the most suitable models for estimation of daily global solar radiation in Iran.

• 出版日期2019-7
• 单位河海大学