Artificial neural network approach to predict the solubility of C-60 in various solvents

Citation
Iz. Kiss et al., Artificial neural network approach to predict the solubility of C-60 in various solvents, J PHYS CH A, 104(34), 2000, pp. 8081-8088
Citations number
14
Categorie Soggetti
Physical Chemistry/Chemical Physics
Journal title
JOURNAL OF PHYSICAL CHEMISTRY A
ISSN journal
10895639 → ACNP
Volume
104
Issue
34
Year of publication
2000
Pages
8081 - 8088
Database
ISI
SICI code
1089-5639(20000831)104:34<8081:ANNATP>2.0.ZU;2-H
Abstract
A multiparameter artificial neural network (ANN) approach was successfully utilized to predict the solubility of C-60 in different solvents. Molar vol ume, polarizability parameter, LUMO energy, saturated surface, and average polarizability molecular properties were chosen to be the most important fa ctors determining the solubilities, The results show that in a large number of solvents (126) the solubility decreases with increasing molar volumes o f the solvents and increases with their polarizability and saturated surfac e areas. A method is suggested to the approximate determination of experime ntally not easily measurable solubility related thermodynamic parameters, e .g., the Hildebrand parameter, based on reliable solubility measurements.