Symbolic Regression via Genetic Programming Model for Prediction of Adsorption Efficiency of some Pesticides on MWCNT/PbO۲ Nanocomposite

The present study quantitative structure-property relationship (QSPR) model developed for the adsorption efficiency (AE) of ۷۰ pesticides in water sample on MWCNT/PbO۲ solid phase extraction cartridge. Stepwise-multiple linear regression (SW-MLR) method employed for selection of descriptors. The selected descriptors are MATS۷v, MATS۶c, GATS۳s, ATSC۶i, C۰۴۰, SpMin۸_Bhi, E۲v, JGI۱ and Mor۰۸u. Curiosity at the effective descriptors indicates electronic, topological and geometrical characteristics of studied pesticides are the most effective parameters on their AE on MWCNT/PbO۲ nanocomposite adsorbent. Symbolic regression via genetic programming (SR-GP) utilized to offer the symbolic regression QSPR model. The accuracy and predictive power of the SR-GP model compared with traditional linear and nonlinear regression models contain multiple linear regression (MLR) and support vector regression (SVR). Inspection the fitness parameters confirmed the superiority of SR-GP model over MLR, and SVR models. In SR-GP model, the correlation coefficient (R) was ۰.۹۳۰ and ۰.۸۹۰, and the root mean square errors (RMSE) were ۰.۰۴ and ۰.۰۵ for the training and test sets, respectively. These results can be used to predict the AE for other pesticides by MWCNT/PbO۲ adsorbent and designing a more efficient nano cartridge for SPE.

کلیدواژه ها:

Quantitative structure-property relationship ، Pesticides ، Adsorption efficiency ، MWCNT/PbO۲ ، Solid phase extraction ، Symbolic regression via genetic programming