APPLYING FUZZY-BASED INDUCTIVE REASONING TO ANALYZE QUALITATIVELY THEDYNAMIC BEHAVIOR OF AN ECOLOGICAL-SYSTEM

Qualitative reasoning methodologies are an alternative to quantitative modeling approaches if the knowledge about the system of interest is imprecise or incomplete, as is often the case with ecological systems. In Biosphere 2, a closed ecological system, the level of O-2 dropped and the CO2 level rose continuously during its closure between 1991 an d 1993. The mechanisms of carbon cycles have been subject to multiple research efforts and are therefore formulated as general rules in prin ciple. However, the structure of the carbon cycle in Biosphere 2 is no t well known, although abundant data exist on some of the important fl uxes and pools. While deductive methodologies require knowledge about the structure of the system to derive the behavior of the system, the fuzzy-based inductive reasoning methodology, FIR, derives a behavior m odel inductively by analyzing time series. The derived behavior model comprises cases and information about how to retrieve prototypical cas es that can be adapted to the given situation. Thus, FIR combines one- shot inductive and incremental case-based reasoning techniques to anal yze and forecast dynamic systems.