Portal de Periódicos da CAPES

Accommodating structural change in environmental systems: The approach of qualitative simulation

1991; Wiley; Volume: 10; Issue: 1-2 Linguagem: Inglês

10.1002/for.3980100112

1099-131X

Júlia Seixas, António Câmara, Paula Antunes, Manuel Duarte Pinheiro,

Bayesian Modeling and Causal Inference

Abstract In environmental systems forecasting is particularly relevant if one is concerned with structural changes in the system. The term 'structure refers to how the components of a system are arranged together (Kuipers, 1985b). Each component has an associated behaviour and the behaviour of the system as a whole results from the interaction between these components through specified connections. The structure of the system is defined by a range of values for its components. If at least one component exceeds some value that bounds this component's range, a new structure is achieved. Environmental systems are prone to structural change, due to endogenous and usually exogenous agents. This paper introduces a method for considering structural change in the framework of dynamic qualitative simulation. Forecasting of structural change can, in principle, be accommodated by using learning mechanisms. An application to an environmental system is presented for illustrative purposes.