Predicting soil sorption coefficients of organic chemicals using a neural network model
- Univ. of Cincinnati, OH (United States). Dept. of Chemical Engineering
- Environmental Protection Agency, Cincinnati, OH (United States)
The soil/sediment adsorption partition coefficient normalized to organic carbon (K{sub oc}) is extensively used to assess the fate of organic chemicals in hazardous waste sites. Several attempts have been made to estimate the value of K{sub oc} from chemical structure or its parameters. The primary purpose of this study was to develop a nonlinear model for estimating K{sub oc} applicable to polar and nonpolar organics based on artificial neural networks using the octanol/water partition coefficient (K{sub ow}) and water solubility (S). An analytic equation was obtained by starting with a neural network, converging the bias and weight values using the available data on water solubility, octanol/water partition coefficient, and the normalized soil/sediment adsorption partition coefficient, and then combining the equations for each node in the final neural network. For the 119 chemicals in the training set, estimates using the neural network equation lie outside the 2{sigma} region (the standard deviation for the training set, {sigma} = 0.52) for only five chemicals, while all the chemicals in the test set lie within the 2{sigma} region. It was concluded that the neural network equation outperforms the linear models in fitting the K{sub oc} values for the training set and predicting them for the test set.
- Sponsoring Organization:
- USDOE
- OSTI ID:
- 268013
- Journal Information:
- Environmental Toxicology and Chemistry, Journal Name: Environmental Toxicology and Chemistry Journal Issue: 7 Vol. 15; ISSN ETOCDK; ISSN 0730-7268
- Country of Publication:
- United States
- Language:
- English
Similar Records
Effects of organic matter composition on the partition behavior of polycyclic aromatic hydrocarbons (PAHs)
Attenuation of chlorocarbon compounds by clay liner materials of a waste disposal facility