Can Fuzzy Logic Formalism Bring Complex Environmental Issues into Focus?

Abstract

Information on the status and changing trends in environmental quality is necessary to formulate sound public policy and efficient implementation of environmental pollution abatement programs. In this quest, air and water quality indices are computed using US-EPA and US-NSF proposed methods for local and regional air/water quality management in many metro cities of the world, respectively. The procedure in vogue in the computation of these indices, however, does not include expert’s knowledge. We believe that the development of a method to quantify association between the pollutant and air/water borne diseases is an important step before classifying air/water quality. There exists aleatory uncertainty in the pollution parametric data and epistemic uncertainty in describing the pollutants by the domain experts in linguistic terms such as poor, good, very good, etc. Successes of probability theory have high visibility. But what is not widely not recognized is that these successes mask a fundamental limitation-the inability to operate on what may be called perception—based information. Fuzzy logic based formalism presented in this paper can model the two types of uncertainties, thereby straightway describing air/water quality in linguistic terms with a degree of certainty attached to each term.