Abdallaoui, A. and Badaoui, H.E. (2011) Prediction of toxic levels of heavy metals in sediments from the river Beht physico-chemical parameters prediction des teneurs en metaux lourds toxiques des sediments de l'oued Beht à partir des paramètres physico-chimiques. Physical and Chemical News, 58. pp. 90-97.

Full text not available from this repository.
Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....


In the present work, we were interested in a comparative study of the performances of two methods of modelling used for the prediction of the concentrations of heavy metals in Moroccan river sediments, from a certain number of physico-chemical parameters. Both used methods of modelling are the multiple linear regression and the networks of (formal) artificial neurones. The used data those are relative to the analysis of the samples of sediment taken during different campaigns, made at the level of a lots of stations of the pond paying (pouring) the oued Beht (104 observations). The dependent variables (to explain or to predict), which are in number of four, are the contents in heavy metals (Cd, Cr, Cu and Pb) sediments. This study showed that the predictive models established by the recent method, which is based on the principle of the networks of artificial neurones, are sharply more successful compared with those established by the method based on the multiple linear regression. This performance shows the existence of a non-linear relation between the physico-chemical studied characteristics (independent variables) and the contents in metals of sediments of the pond overturning of the oued Beht.

Item Type: Article
Subjects: Chemistry
Divisions: SCIENTIFIC PRODUCTION > Chemistry
Depositing User: Administrateur Eprints Administrateur Eprints
Last Modified: 31 Jan 2020 15:45
URI: http://eprints.umi.ac.ma/id/eprint/1981

Actions (login required)

View Item View Item