Estimation of Daily Global Horizontal Irradiation Using Extreme Gradient Boosting Machines

Empirical models are widely used to estimate solar radiation at locations where other more readily available meteorological variables are recorded. Within this group, soft computing techniques are the ones that provide more accurate results as they are able to relate all recorded variables with solar radiation. In this work, a new implementation of Gradient Boosting Machines (GBMs) named XGBoost is used to predict daily global horizontal irradiation at locations where no pyranometer records are available. The study is conducted with data from 38 ground stations in Castilla-La Mancha from 2001 to 2013. Results showed a good generalization capacity of the model, obtaining an average MAE of 1.63 $$\mathrm{MJ/m}^2$$ in stations not used to calibrate the model, and thus outperforming other statistical models found in the literature for Spain. A detailed error analysis was performed to understand the distribution of errors according to the clearness index and level of radiation. Moreover, the contribution of each input was also analyzed.