Rule-based life cycle impact assessment using modified rough set induction methodology

Life cycle assessment (LCA) is a methodology for assessing environmental burdens of products or processes on a cradle-to-grave basis. The impact assessment phase necessitates use of decision analysis methods to account for multiple environmental criteria in the comparison of technological alternatives. Valuation or weighting of the impact criteria is usually accomplished by eliciting relative or absolute scores from an expert. This paper presents an alternative streamlined approach wherein heuristic rules are derived from a set of training data in the form of example alternatives ranked in order of preference by the expert. These decision rules are generated using an induction process based on rough set theory. The heuristic rules can subsequently be used to compare and rank new alternatives, and lead to a decision consistent with the expert preferences embodied in the training data.