Towards downscaling of aerosol gridded dataset for improving solar resource assessment, an application to Spain

Abstract

Solar radiation estimates with clear sky models require estimations of aerosol data. The low spatial resolution of current aerosol datasets, with their remarkable drift from measured data, poses a problem in solar resource estimation. This paper proposes a new downscaling methodology by combining support vector machines for regression (SVR) and kriging with external drift, with data from the MACC reanalysis datasets and temperature and rainfall measurements from 213 meteorological stations in continental Spain.The SVR technique was proven efficient in aerosol variable modeling. The Linke turbidity factor (TL) and the aerosol optical depth at 550nm (AOD 550) estimated with SVR generated significantly lower errors in AERONET positions than MACC reanalysis estimates. The TL was estimated with relative mean absolute error (rMAE) of 10.2% (compared with AERONET), against the MACC rMAE of 18.5%. A similar behavior was seen with AOD 550, estimated with rMAE of 8.6% (compared with AERONET), against the MACC rMAE of 65.6%.Kriging using MACC data as external drift was found useful in generating high resolution maps (0.05 o x0.05 o ) of both aerosol variables. We created high resolution maps of aerosol variables in continental Spain for the year 2008.The proposed methodology was proven to be a valuable tool to create high resolution maps of aerosol variables (TL and AOD 550). This methodology shows meaningful improvements when compared with estimated available databases and therefore, leads to more accurate solar resource estimations. This methodology could also be applied to the prediction of other atmospheric variables, whose datasets are of low resolution.

Generation of daily global solar irradiation with support vector machines for regression

“…http The fact that satellite derived solar irradiation deviation is associated with the spatial resolution of sensors (image's pixel size) and that this resolution generally falls within the range of kilometers implies a high level of uncertainty [18,19]. Other sources of uncertainty are found in the inherent uncertainty of aerosol and water vapor estimations [14,20], which are normally estimated for very low spatial resolutions in the range of the Multi-angle Imaging SpectroRadiometer -MISR 0.5 Â 0.5° [21] and the Moderate Resolution Imaging Spectroradiometer -MODIS 1 Â 1° [22]). …”

Estimation of solar global irradiation in remote areas

“…Then, the second step is to prune the tree in order to obtain a more parsimonious model. In this process, the user typically specifies the minimum number of samples in each leaf M. For more information about M5P, the authors refer to Antonanzas-Torres et al (2014c).…”

“…Fuzzy logic has also been useful in describing solar irradiation (Kisi, 2014). Regression trees such as M5P have also been utilized, achieving relatively low errors (Antonanzas-Torres et al, 2014c). Finally, support vector regression (SVR) has been most recently proposed using sunshine duration and temperatures as inputs (Chen et al, 2013;, detecting a high spatial influence with elevation on the model performance.…”

GA-PARSIMONY: A GA-SVR approach with feature selection and parameter optimization to obtain parsimonious solutions for predicting temperature settings in a continuous annealing furnace

“…Therefore, a user-supplied penalty parameter is unnecessary and the automatic method for generating parsimonious models is simplified. In the last year, this methodology has been applied successfully to other fields [12][13][14].…”