Determination of Parachor of Various Compounds Using an Artificial Neural Network␣Group Contribution Method
Résumé
In this communication, an Artificial Neural Network␣Group Contribution algorithm is applied to represent/predict the parachor of pure chemical compounds. To propose a reliable and predictive tool, 227 pure chemical compounds are investigated. Using the developed method, we obtain satisfactory results that are quantified by the following statistical parameters: absolute average deviations of the represented/predicted parachor values from existing experimental ones, %AAD = 1.2%; and squared correlation coefficient, R2 = 0.997.