PARAMETER-ESTIMATION USING ARTIFICIAL NEURAL-NETWORK AND GENETIC ALGORITHM FOR FREE-PRODUCT MIGRATION AND RECOVERY

Artificial neural network (ANN) is considered to be a universal functi on approximator, and genetic algorithm (GA) is considered to be a robu st optimization technique. As such, ANN regression analysis and ANN-GA optimization techniques can be used to perform inverse groundwater mo deling for parameter estimation. In this manuscript the applicability of these two techniques in solving an inverse problem related to a lig ht-hydrocarbon-contaminated site is assessed. The critical parameters to be evaluated are grain-size distribution index a and saturated hydr aulic conductivity of water K-SW, since these parameters control free- product volume predictions and flow. A set of published data correspon ding to a light-hydrocarbon-contaminated unconfined aquifer was used a s the base case to determine the applicability of these methods under a variety of scenarios. Using limited monitoring-and recovery-well dat a under homogeneous and heterogeneous conditions, the critical paramet ers were evaluated. The results were used to determine the relative ef fectiveness of each method and corresponding limitations. The results of the work suggested that ANN regression analysis has limited utility , especially with heterogeneous soils, whereas the ANN-GA optimization can provide superior results with better computational efficiency. Fi nally, a general guideline for solving inverse problems using the two techniques is outlined.