Abstract
This paper presents the design and development of a Geochemical Expert System prototype (GES) for analyzing solution-mineral interactions in nature. The emphasis is placed on expert system design and knowledge representation. One of the most challenging and research-intensive steps was the identification of the key geochemical characteristics that would enable the expert system to identify salient features of any user-defined geochemical composition. Moreover, developing a system to create geochemical interpretations similar to those written by expert geochemists proved to be difficult. Important geochemical characteristics and their interrelationships which were "discovered" during knowledge acquisition and conceptualization are presented. These characteristics have been organized and documented within the expert system to emulate the skills of an expert geochemist. Examples of expert system-generated analyses are presented.
| Original language | English |
|---|---|
| Pages (from-to) | 53-60 |
| Number of pages | 8 |
| Journal | Computers and Geosciences |
| Volume | 19 |
| Issue number | 1 |
| DOIs | |
| State | Published - Jan 1993 |
| Externally published | Yes |
Funding
Acknowledgment--Sponsored by the Subsurface Science Program, Ecological Research Division, Office of Health and Environmental Research, U.S. Department of Energy under Contract DE-AC05-84OR21400 with Martin Marietta Energy Systems, Inc. Publication No. 3933, Environmental Sciences Division, ORNL
Keywords
- Artificial Intelligence (AI)
- Expert systems
- Geochemical Expert System (GES)
- Geochemical modeling
- Geochemistry
- MINEQL