Hybrid fuzzy-mechanistic models for addressing parameter variability

A simulation approach which integrates mechanistic models and fuzzy logic in order to accommodate parameter variability is developed and explored. The approach modifies a mechanistic model, such as a runoff model, for which the values of the parameters are originally fixed. Fuzzy logic is used to redefine the parameter values by varying them as a function of meaningful system indicators, such as inflow, precipitation or temperature in the case of inflow modelling. The modification adds flexibility to the structure of the mechanistic model, by allowing the values of the parameters to be reset at every time step based on the current values of the system indicators. This approach is applied to two different models, a runoff model and an algal concentration model, in order to demonstrate its versatility. The results are indicative of improved performance with the hybrid fuzzy-mechanistic models compared with the purely mechanistic models. In the case of the runoff model, the resulting description of the parameter domain also indicates a possible deficiency of the model structure, that is, a lack of clear distinction between watershed runoff and water retention through routing. The approach may be data intensive, but its implementation is straightforward. A wide range of potential applications of this approach in environmental and natural resources descriptive modelling exists, including: snowmelt modelling, fish habitat modelling, transport modelling, and species migration modelling. However, one must be careful to identify parameter–system indicator relationships that are representative of the system under study, and to avoid extrapolations beyond the known system conditions.