期刊名称：Journal of Environmental Hydrology (ältere Jahrgänge)
印刷版ISSN：1058-3912
电子版ISSN：1996-7918
出版年度：2010
卷号：18
出版社：IAEH
摘要：A solution is proposed to the problem of finding the best monitoring network design for the detection of groundwater contamination from multiple areal sources with different leakage probabilities and amounts leaked. In large industrial plants or industrial areas the probability of occurrence, and the amount of contaminant released in a leak varies from place to place, which, in turn, makes the contamination plume spatial distribution stochastic. One way to model this randomness is by simulating the sources as random (models the cause); others include the Monte Carlo simulations of permeability and/or dispersivity fields (models the effect). In the method proposed here flow and transport modeling are coupled with the random simulation of the sources, followed by measuring the accuracy and precision of several candidate monitoring network designs by way of a specific objective function. As the selection of the locations is a very difficult combinatorial problem, a simulated annealing algorithm is proposed for the optimization. The method was applied to a hypothetical case study consisting of an unconfined porous aquifer with risk of contamination from an industrial area. Results show that the method proposed is highly preferable to stratified and clustered monitoring.
