Ann based approach to solve groundwater pollution inverse problem

This paper investigates the feasibility of solving the groundwater pollution inverse problem by using Artificial Neural Networks (ANNs). Different ANNs have been trained to solve the direct problem with the objective of associating the input patterns with the output patterns. In order to solve the inverse problem and to identify the unknown pollution source and their characteristics, the trained ANN is inverted. By fixing the output pattern of the ANN, the proposed procedure is able to reconstruct the corresponding input. The approach has been applied for a real case which deals with the contamination of the Rhine aquifer by carbon tetrachloride (CCl4) due to a tanker accident. This case is well adapted to the problem since numerous concentrations have been measured at different piezometers and at different time. The location of the source and the beginning of the contamination are known. The ANNs are used to identify the contamination source and the results are compared with the solution obtained with a different approach.