TITLE:
Identification of Unknown Groundwater Pollution Sources and Determination of Optimal Well Locations Using ANN-GA Based Simulation-Optimization Model
AUTHORS:
Sophia Leichombam, Rajib Kumar Bhattacharjya
KEYWORDS:
Linked Simulation-Optimization, Groundwater Pollutant Source, Inverse Optimization, Artificial Neural Networks, Genetic Algorithm
JOURNAL NAME:
Journal of Water Resource and Protection,
Vol.8 No.3,
March
31,
2016
ABSTRACT: The linked simulation-optimization model can be used for solving a
complex groundwater pollution source identification problem. Advanced
simulators have been developed and successfully linked with numerous
optimization algorithms for identification of groundwater pollution sources.
However, the identification of pollution sources in a groundwater aquifer using
linked simulation-optimization model has proven to be computationally
expensive. To overcome this computational burden, an approximate simulator, the
artificial neural network (ANN) model can be used as a surrogate model to
replace the complex time-consuming numerical simulation model. However, for
large-scale aquifer system, the performance of the ANN-based surrogate model is
not satisfactory when a single ANN model is used to predict the concentration
at different observation locations. In such a situation, the model efficiency
can be enhanced by developing separate ANN model for each of the observation
locations. The number of ANN models is equal to the number of observation wells
in the aquifer. As a result, the complexity of the ANN-based simulation-optimization
model will be related to the number of observation wells. Thus, this study used
a modified formulation to find out the optimal numbers of observation wells
which will eventually reduce the computational time of the model. The
performance of the ANN-based simulation-optimization model is evaluated by
identifying the groundwater pollutant sources of a hypothetical study area. The
limited evaluation shows that the model has the potential for field
application.