Environmental Engineering Reference
In-Depth Information
the parameterization of the model is often based on expert knowledge, without
sensitivity analysis or use of optimization techniques. On the one hand, the use of
personal knowledge and experience is an advantage for the fuzzy approach, as it
increases the quantity of information that is possible to include in a model. On the
other hand, it also includes subjectivity, which can be seen as a weakness of the
model.
Such aspects need improvement to create more reliable and scientifically sound
fuzzy ecological models. A possible strategy to achieve this goal is the hybridiza-
tion of the human-like reasoning style of fuzzy systems with other soft-computing
approaches. For example, neural networks, which are able to learn optimal mem-
bership functions and fuzzy rules from datasets. Such data-driven approaches
would improve model performance by taking into account non-linear membership
functions, complex model structures, alternative inference operators and defuzzifi-
cation strategies.
Another aspect that can be further developed in fuzzy ecological modelling is the
inclusion of biological variables (species, communities). Most of the published
models have been using only abiotic variables. Physical and chemical variables are
usually easier (and cheaper!) to measure and monitor. However, they might not
provide sufficient information on the investigated environment. Tingey (1989)
emphasized that “
there is no better indicator of the status of a species or a system
than the species or system itself
”. The inclusion of biotic variables, under the
direction of experienced biologists would help in designing more effective fuzzy
ecological models. This can only be achieved by improving the familiarity of
biologists to fuzzy logic techniques.
Further Readings
Adriaenssens V, De Baets B, Goethals PLM, De Pauw N (2004) Fuzzy rule-based models for
decision support in ecosystem management. Sci Total Env 319:1-12
Klir GJ, Yuan B (1995) Fuzzy sets and fuzzy logic: theory and applications. Prentice Hall, Upper
Saddle River, NJ
Shepard RB (2005) Quantifying environmental impact assessments using fuzzy logic. Springer,
New York
Silvert W (1997) Ecological impact classification with fuzzy sets. Ecol Model 96:1-10
Silvert W (2000) Fuzzy indices of environmental conditions. Ecol Model 130:111-119
Zadeh L (1965) Fuzzy sets. Inform Control 8(3):338-353
Zimmermann HJ (1991) Fuzzy set theory and its applications, 2nd edn. Kluwer, Dordrecht
