Ecodynamique des éléments traces et caractérisation de l’exposition des sols contaminés : expérimentation et modélisation par les réseaux de neurones artificiels

摘要

Soils contaminated with potentially toxic trace elements (PTTE) often have serious consequences for terrestrial ecosystems. Several phytoremediaction have been developped to reclaim contaminated soils; however the efficiency and capacity of these techniques to reduce excessive concentrations of trace elements or their (phyto) availability in contaminated soils have to be assessed. The present work is focused on studying the effectiveness of two phyoremediation options such as phytostabilisation and phytoextraction assisted by organic and inorganic amendments to remediatethe high concentrations of PTTE in contaminated natural soils and technosoils. Total PTTE concentrations were determined in soil pore water (SPW) sampled by Rhizon soil moisture samplers. The soil exposure intensity was assessed by DGT (diffusive gradient in thin films) probes. The PTTE phytoavailability was characterized by growing dwarf beans on potted soils and analyzing their foliar PTTE concentrations. Then a model of artificial neural network was applied to understand the factors most relevant for the variability on the phytoavailability of trace elements. Both options were found to be able to reduce the concentrations or phytoavailability of PTTE in the presence of amendments. The artificial neural network has been very effective to predict missing results and to determine the control parameters of the variability of the PTTE phytoavailoability from the soil parameters.