Fuzzy Logic and Neuro-Fuzzy Networks for Environmental Hazard Assessment

Pollution and management of the environment are serious problems which concern the entire planet; the main responsibility should be attributed to human activities that contribute significantly to damage the environment, leading to an imbalance of natural ecosystems. In recent years, numerous studies focused on the three environmental compartments: soil, water and air. The pollution of groundwater is a widespread problem. The causes of pollution are often linked to human activities, including waste disposal. Solid waste management has become an important environmental issue in industrialized countries. The most serious problems are related to solid waste disposal. Landfill is still the most used disposal technique but not the safest. In fact, even controlled landfills could easily incur in the breakdown of containment elements. This breakdown could cause contamination of aquifer that is environmental pollution. Such contamination can be mitigated by performing remediation and environmental restoration. The assessment of environmental pollution risk can be performed with different degrees of detail and precision. Various statistical and mathematical models can be used for a qualitative risk assessment. The planning of a program for environmental remediation and restoration can be supported by expeditious methodologies that allow to obtain a hierarchical classification of contaminated sites. The literature offers some expeditious and qualitative methods including fuzzy logic (Zadeh, 1965), neural networks and neuro-fuzzy networks, which are more objective methods. The three artificial intelligence systems differ among themselves in some respects: fuzzy inference system learns knowledge of data only through the fuzzy rules; neural network is able to learn knowledge of data using the weights of synaptic connections; neuro-fuzzy systems are able to learn knowledge of neural data with neural paradigm and represent it in the form of fuzzy rules. Fuzzy logic was founded in 1965 by Zadeh. The first applications date back to the nineties. They were mainly used to control industrial processes, household electrical appliances and means of transport. Later, this approach was used in several fields including the environment. In fact it could be used for assessing environmental risk related to contamination of groundwater. The fuzzy approach is advantageous because it allows a quick assessment of the risk, but is disadvantageous because of the increasing complexity in the definition of fuzzy rules along with the increasing of the number of parameters. In many situations, when the number of parameters are considered high in the analysis, application of these techniques is cumbersome and complex and could be used for neuro-fuzzy models. These models reduce the complexity because they use training data. The neuro-fuzzy model were supported by a sensitivity analysis in order to address the problem of subjectivity and uncertainty of model input data.