Geoscience Reference
In-Depth Information
Chapter 3
Environmental Decision-Making
3.1 Introduction
Environmental decisions are made based on different kinds of information. In a
speci
c decision-making situation the choice of the appropriate tool depends on the
decision context. In fact, there are numerous available tools which provide decision
support. Adoption and substantiation of decisions are essential parts of the whole set
of tasks related to arti
cial intelligence. Decision making procedures play a key role
as far as classi
cation and recognition tasks are concerned. In suppressing number of
cases, decision rules are synthesized under the assumption that characteristics
describing the objects for study are independent. In the case of environmental
monitoring, the characteristics of nature and man-made systems are strongly corre-
lated. Therefore, in this case, decision-making procedures have to be stable and take
into account evolution processes.
In arti
cial intelligence, an expert system is a computer system which emulates
the decision-making ability of a human expert (Jackson 1999; Murphy 2012; Russel
and Norvig 2009). Expert systems are designed to solve complex problems by
reasoning about knowledge, like an expert, and not by following the procedure of a
developer as in the case of conventional programming. Both knowledge base and
decision making procedures are crucial in expert system technology. Expert sys-
tems operate like a human brain and thus they offer many advantages for users
when compared to traditional programs.
Every expert system has a major flaw, which explains its low success despite the
principles on which it is based having existed for 70 years: knowledge collection
and its interpretation into rules, or knowledge engineering. Most developers have
no automated method to perform this task; instead they work manually, increasing
the likelihood of errors. Expert knowledge is generally not well understood. For
instance, rules may either be contradictory or poorly written and as a result unus-
able, or they even may not exist. Worse still, most expert systems use a compu-
tational engine incapable of reasoning. As a result, an expert system often works
Search WWH ::
Custom Search