Investigation of Constructed Wetlands Efficiency in Mercury Removal Using Genetically Generated Fuzzy Knowledge Bases

Wetlands have been known as an efficient and low-cost technology in treating wastewater. Current design approaches lack essential parameters necessary to evaluate the removal of metals contained in waters discharged to constructed wetlands. Research shows a combination of experimental and computation modeling to assess the efficiency of mercury removal. Experimental investigations were conducted to investigate the ability of wetland floating and rooted plants to uptake mercury from water. Numerical modeling investigations were then carried out to: a) expand the results obtained in the experimental phase by examining the distribution of mercury forms in water; b) evaluating the amount of bioavailable mercury for plant uptake; c) verify the effects of pH, temperature, and chloride concentrations in water on Hg speciation. A fuzzy knowledge base was used to assess efficiency of wetlands for various conditions of mercury discharge. A genetic algorithm (GA) has been developed to automatically construct the knowledge bases used by fuzzy decision support systems (FDSS). The GA produces an optimal approximation of a set of sampled data from a certain amount of input information. The main interest of this method is that it can be used to automatically generate (without the help of an expert) a fuzzy knowledge base---i.e., the fuzzy sets on the premises and conclusions, and the fuzzy rules---. The GA uses two main contradictory optimization criteria, i.e., the approximation error and the complexity level of the knowledge base. The approximation error is computed as the root mean square error between the sampled outputs and the answers of the FDSS Fuzzy-Flou (an FDSS developed at École Polytechnique de Montreal, Canada, and the Technical University of Silesia in Gliwice, Poland) at the corresponding sampled input data. The complexity level is computed as the number of fuzzy rules contained in the knowledge base. The GA deals with many other criteria, e.g., the probability of crossover, the probability of fuzzy-sets displacement, the probability of fuzzy-rules reduction and the probability of mutation, that also control the optimization process. The findings of this research can be applied to wetlands (natural and constructed) were purification of: a) municipal; b) industrial; c) acidic; and d) agricultural wastewater is performed and applied in preparing environmental risk or impact assessments.