Expert systems in geological exploration: Can they be cost effective
Michael G. Walker · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 1988
What is a good approach for building practical expert systems Despite claims in the popular press, no formal evaluation and supporting data have been published that demonstrate the cost effectiveness of any expert system in geologic exploration. Mistakes are most common in underestimating the effort required to develop a knowledge base, and in choosing to build a prototype in isolation from the environment in which it must ultimately perform. An expert system is most likely to be cost effective if it is an integrated part of an existing system, the knowledge base is small and stable, the program can be validated and trusted, and it can be used at the decision site.