An Integrated Partial Least Square-Monte Carlo Model for risk Assessment of Petroleum Development

摘要

A quantitative assessment of the petroleuM development risk has been a difficult issue in domestic and foreign researches. By deeply analysis of traditional risk assessment methods, this paper suggests a PLS-MC model to assessment the risk of petroleum development for the first time, which integrated partial least squares and Monte Carlo technique. Through PLS algorithm, a regression model was constructed between NPV and uncertain variables, which not only avoid the harmful effects of multicollinearity, but also considered some important quality factors that always neglected. Then, Monte Carlo technique was used to simulate the change scope of NPV. So the results of this new method are more accurate, rational and objective. By using the example of the Xinchang gas field in Sichuan, this article indicated that the PLS-MC model is feasible and useful for reference to the congener research.