Integrating Cases and Models for Prediction in Biological Systems

Understanding of many complex biological systems is limited both by incomplete models and limited empirical data. Accurate prediction of the behavior of such systems requires exploitation of multiple, individually incomplete, knowledge sources. Model-based adaptation is a technique for integrating case-based reasoning with modelbased reasoning to predict the behavior of biological systems. This approach is implemented in CARMA, a system for rangeland grasshopper management advising that implements a process model derived from protocol analysis of human expert problemsolving episodes. CARMA’s ability to predict the forage consumption judgments of expert pest managers was empirically compared to that of case-based and model-based reasoning techniques in isolation. This evaluation provided initial confirmation for the hypothesis that an integration of model-based and case-based reasoning can lead to more accurate predictions than either technique individually. 1 Prediction in Biological Systems Decision-support in agriculture and natural resources management often requires prediction of the behavior of biological systems. For example, providing advice about the optimal planting time for a crop may require predicting the emergence date of important pests of that crop (Plant and Stone, 1991). Similarly, determining the most cost-effective response