Design of an Intelligent Geographic Information System for Multi-criteria Site Analysis

Spatial decision-making problems, such as site selection, require appropriate means for handling multiple socioeconomic factors while considering physical suitability. Traditional decision support techniques lack the ability to simultaneously take into account these factors and conditions. Similarly, geographic information systems, while recognized as useful decision support technologies, do not provide the means to handle multiple decision factors. With these issues in mind, this study was developed to provide a framework for integrating the strengths of geographic information systems, expert systems, and the analytic hierarchy process to incorporate the decision maker’s preferences on a range of factors used in finding optimally suitable sites. This study illustrates how the integrated system may be applied to industrial site selection. Thus, two perspectives on developing better decision capabilities of GIS can be identified: one by including a ‘decision’ module and the other by including a ‘prioritization’ capability. This study demonstrates how decision processes can be included into GIS by coupling them with the expert system’s programming capabilities based upon experts’ decision logic. Just as an expert possessing knowledge and experience in a specialized domain uses reasoning rules and expertise to solve a problem, an expert system can embody the logic of such expertise. Logical decision steps can be programmed into the computer to solve problems or provide information in a specialist’s domain. In addition to an expert system, this study employed a method for assigning priorities to conflicting decision criteria called the analytic hierarchy process (AHP) developed by Thomas Saaty. The AHP is a multi-criteria decision method that uses hierarchical structures to represent a problem and then develops priorities for alternatives based on the judgment of the user (Saaty 1987a). Saaty has shown that weighing activities in multi-criteria decision making can be effectively dealt with via hierarchical structuring and pairwise comparisons. Pairwise comparisons are based on forming judgments between two particular elements rather than attempting to prioritize an entire list of elements (Saaty 1980). Adding the prioritization module for setting priorities enhances existing GIS analyses and visualization capabilities. This study illustrates a method for constructing an integrated system of these three decision support tools (the GIS, the expert systems, and the AHP module), and applies it to an industrial site selection problem that searches for sites for manufacturing facilities in a regional scale. Remarks on GIS-integration Issues Although the capabilities of GIS have proved their usability in a multitude of applications, there has also been increasing interest in coupling GIS with other decision support systems. However,