Quantitative Structure-Property Relationship (QSPR) study was applied to the prediction of the characteristic of Persistent Organic Pollutants (POPs) screening for atmosphere persistence. The mean and maximum half-life estimations for degradation in air of 45 Nations Environment Program (UNEP) POPs and possible POPs were modeled using the parameters from quantum-chemical calculations at density functional theory (DFT) level. It was expected that the main contribution to the degradation rate was given by the EHOMO. Parameter Principal Component Analysis (PCA) method, the Multiple Linear Regression method (MLR), Partial Least Square analysis (PLS) and the Artificial Neural Network (ANN), showed a determination coefficient (R2 ) more than 0,9. The prediction results were in excellent agreement with the experimental value.