Modeling and prediction of activity coefficient ratio of electrolytes in aqueous electrolyte solution containing amino acids using genetic programming

Genetic programming (GP) is one of the computer algorithms in the family of evolutionary-computational methods, which have been shown to provide reliable solutions to complex optimization problems. The genetic programming under discussion in this work relies on tree-like building blocks, and thus supports process modeling with varying structure. In this paper the systems containing amino acids + water + one electrolyte (NaCl, KCl, NaBr, KBr) are modeled by GP that can predict the mean ionic activity coefficient ratio of electrolytes in presence and in absence of amino acid in different mixtures better than the common polynomial equations proposed for this kind of predictions. The root mean square deviation (RMSD) of the designed GP model in prediction of the mean ionic activity coefficient ratio of electrolytes is less than 0.067 and proves the effectiveness of the GP in correlation and prediction of activity coefficients in the studied mixtures.