Prediction of standard chemical exergy by a three descriptors QSPR model

A new quantitative structure–property relationship (QSPR) three parameter correlation (R2 = 0.9977) of standard chemical exergy for a diverse set of 134 organic substances was developed by application of a genetic algorithm search. The descriptors are all calculated directly from the molecular structure, and the approach given is applicable, in principle, to all organic substances of regular structure. The application of the genetic algorithm in comparison with stepwise multi-variate linear regression (MLR) shows some advantages in required time for solving and in precision.