TIRM 89 - 934 , Turing Institute

This paper describes a prototype system for the prediction of parameters associated with a geological prospect, required for assessing the likelihood of hydrocarbons at the prospect. A principle characteristic of expert reasoning in this domain involves the recall and use of previous examples (`exemplars') of similar, already-drilled wells in addition to the use of general rules concerning known parameters of the prospect. Such reasoning is a common feature of human problem-solving, and involves generation and use of generalisations at run-time when a performance task is known, in contrast to an exhaustive enumeration of generalisations from examples before the performance task is known as performed by many rule induction systems. In this paper we describe the mechanisms for such exemplar-based reasoning in the prototype system, and discuss the characteristics of the problem domain which suggest the appropriateness of this approach.