Predicting production using a neural network (artificial intelligence beats human intelligence)

摘要

Petroleum professionals, that is engineers and geoscientist, routinely make recommendations to drill wells. This process requires the generation of a production profile, oil producing rate versus time, which is a key component in the final economic decision of whether or not to drill the well. The success of the drillingprogram, and possibly the professional's career, rests, to a high degree, upon the accuracy of this predicted production profile. The more accurate this prediction the more certain the economic value of the recommended drilling location. This paper looks at this predictive process as used in the Vacuum Field of New Mexico. It explores the predictive methods used in the past and reports on their accuracy. A new method, using artificial intelligence, is presented which improves upon the accuracy of this process.