Prediction of molecular diffusivity of pure components into air: a QSPR approach

Mehdi Sattari; Farhad Gharagheizi

doi:10.1016/j.chemosphere.2008.04.049

Prediction of molecular diffusivity of pure components into air: a QSPR approach

Chemosphere. 2008 Jul;72(9):1298-302. doi: 10.1016/j.chemosphere.2008.04.049. Epub 2008 Jun 9.

Authors

Mehdi Sattari¹, Farhad Gharagheizi

Affiliation

¹ Department of Chemical Engineering, Faculty of Engineering, University of Tehran, PO Box 11365-4563, Tehran, Iran.

PMID: 18541286
DOI: 10.1016/j.chemosphere.2008.04.049

Abstract

The molecular diffusivity of 378 pure components into air was predicted using genetic algorithm-based multivariate linear regression (GA-MLR) and feed forward neural networks (FFNN). GA-MLR was used to select the molecular descriptors, as inputs for FFNN. The correlation coefficient (R2) of obtained multivariate linear seven-descriptor model by GA-MLR is 0.9334 and the same value for generated FFNN is 0.9643. These models can be applied for prediction of molecular diffusivity of pollutants into air in case of air pollution studies.

MeSH terms

Air / analysis
Air Pollutants / chemistry*
Air Pollution / statistics & numerical data*
Algorithms
Diffusion
Humans
Linear Models
Models, Statistical
Neural Networks, Computer
Quantitative Structure-Activity Relationship
Reproducibility of Results

Substances

Air Pollutants