Knowledge engineering approaches in developing expert simulation systems

Abstract

Two approaches to knowledge engineering are demonstrated using the soybean insect pest management expert simulation system SMARTSOY. SMARTSOY incorporates the soybean crop growth simulation model SOYGRO as part of its knowledge base. The positivistic approach to knowledge engineering attempts to duplicate thought processes of domain experts in order to arrive at conclusions while the normative approach attempts to duplicate the conclusions of domain experts without consideration of their thought processes. These contrasting approaches require different knowledge engineering techniques and validation procedures. Validation, evaluation and calibration of the two approaches are demonstrated using SMARTSOY for 84 field scenarios.