The paper describes the main approaches used in the development of predictive analytics algorithms, both of a general nature and in the field of well drilling. When describing the algorithms used, the basic assumptions of each and the ensuing limitations of the developed model are explained. The necessity of building hybrid models, involving the full amount of information collected, including calculations carried out during the construction of the well, both from the engineering and geological sides, is shown. The paper discusses the culture of working with data in the oil and gas field in general and in particular well drilling. The current level does not allow companies to create scalable solutions of predictive analysis. As a result of the work done, the basic rules were proposed, the first step was taken towards standardizing the process of collecting and analyzing information flow arising during the construction of wells.
SUMMARY
Researchers base their analysis on basic drilling parameters obtained during mud logging and demonstrate impressive results. However, due to limitations imposed by data quality often present during drilling, those solutions often tend to lose their stability and high levels of predictivity. In this work, the concept of hybrid modeling was introduced which allows to integrate the analytical correlations with algorithms of machine learning for obtaining stable solutions consistent from one data set to another.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.