Feature selection for CIE standard sky classification

There are several compilations of sky classifications that refer to Meteorological Indices (MIs) (variables usually recorded at meteorological ground stations), due the scarcity scanner devices can supply experimental data needed apply CIE standard classification. The use one rather than another MI is never justified, because there no standardized criterion for their selection. In this study, forty-three MIs, traditionally used define different conditions, reviewed. Feature Selection (FS) a key step in design sky-classification algorithm using MIs as an alternative from scanners. Four procedural methods FS -Pearson, Permutation Importance, Recursive Elimination, and Boruta- applied extensive set includes classification data, which was reference. procedures significatively reduced original permitting construction trees with high performance case Pearson method, tree only two MIs. advantage method it functions independently machine-learning latter