Neural network and Monte Carlo simulation approach to investigate variability of copper concentration in phytoremediated contaminated soils
HAMBLI, Ridha
Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique [2008-2013] [PRISME]
Leer más >
Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique [2008-2013] [PRISME]
HAMBLI, Ridha
Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique [2008-2013] [PRISME]
< Leer menos
Laboratoire Pluridisciplinaire de Recherche en Ingénierie des Systèmes, Mécanique et Energétique [2008-2013] [PRISME]
Idioma
en
Article de revue
Este ítem está publicado en
Journal of Environmental Management. 2013, vol. 129, p. 134-142
Elsevier
Resumen en inglés
The statistical variation of soil properties and their stochastic combinations may affect the extent of soil contamination by metals. This paper describes a method for the stochastic analysis of the effects of the variation ...Leer más >
The statistical variation of soil properties and their stochastic combinations may affect the extent of soil contamination by metals. This paper describes a method for the stochastic analysis of the effects of the variation in some selected soil factors (pH, DOC and EC) on the concentration of copper in dwarf bean leaves (phytoavailability) grown in the laboratory on contaminated soils treated with different amendments. The method is based on a hybrid modeling technique that combines an artificial neural network (ANN) and Monte Carlo Simulations (MCS). Because the repeated analyses required by MCS are time-consuming, the ANN is employed to predict the copper concentration in dwarf bean leaves in response to stochastic (random) combinations of soil inputs. The input data for the ANN are a set of selected soil parameters generated randomly according to a Gaussian distribution to represent the parameter variabilities. The output is the copper concentration in bean leaves. The results obtained by the stochastic (hybrid) ANN-MCS method show that the proposed approach may be applied (i) to perform a sensitivity analysis of soil factors in order to quantify the most important soil parameters including soil properties and amendments on a given metal concentration, (ii) to contribute toward the development of decision-making processes at a large field scale such as the delineation of contaminated sites.< Leer menos
Palabras clave en italiano
Soil factors variability
Bean leaves
Copper
Monte Carlo simulation
Soil contamination
Artificial neural network
Proyecto ANR
Geofluids and Volatil elements – Earth, Atmosphere, Interfaces – Resources and Environment - ANR-10-LABX-0100
Orígen
Importado de HalCentros de investigación