Use of artificial neural network simulation metamodelling to assess groundwater contamination in a road project

The estimation of the extent of a polluted zone after an accidental spill occurred in road transport is essential to assess the risk of water resources contamination and to design remediation plans. This paper presents a metamodel based on artificial neural networks (ANN) for estimating the depth of the contaminated zone and the volume of pollutant infiltration in the soil in a two-layer soil (a silty cover layer protecting a chalky aquifer) after a pollutant discharge at the soil surface. The ANN database is generated using USEPA NAPL-Simulator. For each case the extent of contamination is computed as a function of cover layer permeability and thickness, water table depth and soil surface-pollutant contact time. Different feedforward artificial neural networks with error backpropagation (BPNN) are trained and tested using subsets of the database, and validated on yet another subset. Their performance is compared with a metamodelling method using multilinear regression approximation. The proposed ANN metamodel is used to assess the risk for a DNAPL pollution to reach the groundwater resource underneath the road axis of a highway project in the north of France.

[1]  Jack C. Parker,et al.  A parametric model for constitutive properties governing multiphase flow in porous media , 1987 .

[2]  K. Broholm,et al.  Dense chlorinated solvents and other DNAPLs in groundwater , 1996 .

[3]  R. Lenhard,et al.  Measurement and prediction of saturation-pressure relationships in three-phase porous media systems , 1987 .

[4]  M. Vanclooster,et al.  Metamodelling: Theory, concepts and application to nitrate leaching modelling , 2006 .

[5]  Y. Najjar,et al.  Predicting catchment flow in a semi‐arid region via an artificial neural network technique , 2004 .

[6]  Van Genuchten,et al.  A closed-form equation for predicting the hydraulic conductivity of unsaturated soils , 1980 .

[7]  S. Lallahem,et al.  A nonlinear rainfall-runoff model using neural network technique: example in fractured porous media , 2003 .

[8]  Linda Weiser Friedman,et al.  The Simulation Metamodel , 1995 .

[9]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[10]  I. Shahrour,et al.  Parametres gouvernant l'infiltration d'une pollution accidentelle d'hydrocarbures vers des ressources d'eaux souterraines , 2005 .

[11]  I A Basheer,et al.  Computational neural networks for predictive microbiology: I. Methodology. , 1997, International journal of food microbiology.

[12]  Yacoub M. Najjar,et al.  Site Characterization by Neuronets: An Application to the Landfill Siting Problem , 1996 .

[13]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[14]  Robert W. Blanning,et al.  The construction and implementation of metamodels , 1975 .

[15]  J. Kleijnen.  Statistical tools for simulation practitioners , 1986 .