Pattern recognition applied to uranium prospecting

Abstract

PATTERN recognition techniques provide one way of uniting quantitative and descriptive geologic data for mineral prospecting. A quantified decision process using computer-selected patterns of geologic data has the potential of selecting areas with undiscovered deposits of uranium or other minerals. When a natural resource is mined more rapidly than it is discovered, its continued production becomes increasingly difficult. For example, Lieberman¹ has noted that, although a considerable uranium reserve may remain in the U.S.A., the discovery rate for uranium is decreasing exponentially with cumulative exploration footage drilled. Pattern recognition methods of organising geologic information for prospecting may provide new predictive power as well as insight into the occurrence of uranium ore deposits. Often the task of prospecting consists of three stages of information processing: (1) collection of data on known ore deposits; (2) noting any regularities common to the known examples of an ore; (3) selection of new exploration targets based on the results of the second stage. Here we describe a logical pattern recognition algorithm that implements this geologic procedure to demonstrate the possibility of building a quantified uranium prospecting guide from diverse geologic data.