Contribution des réseaux de neurones artificiels (RNA) à la caractérisation des pollutions de sol. Exemples des pollutions en hydrocarbures aromatiques polycycliques (HAP)Artificial Neural Networks (ANNs) characterisation of soil pollution: the Polycyclic Aromatic Hydrocarbons (PAHs) case study
Centre d''informatique géologique, École nationale supérieure des mines de Paris, 35, rue Saint-Honoré, 77305 Fontainebleau cedex, France
Abstract:
We develop the ANNs (Artificial Neural Networks) method to explore contaminant concentration profiles observed in soils of polluted sites. ANNs are particularly efficient in simultaneous analysis of numerous parameters and in identification of complex relations involving field data. Applying the ANN models on a PAH (Polycyclic Aromatic Hydrocarbon) database, we extracted the most characteristic components of known contaminations and applied it to identify the source type of similar polluted sites. The performed tests prove the generalisation capability of the selected ANN model. To cite this article: A. Dan et al., C. R. Geoscience 334 (2002) 957–965.