Identifying Applications of Machine Learning and Data Analytics Based Approaches for Optimization of Upstream Petroleum Operations

Authors:
Publisher website
Google Scholar
Abstract
Over the past few years, machine learning and data analytics have gained tremendous attention as emerging trends in the oil and gas industry. The usage of modern tools and high‐end technologies produces a large amount of heterogeneous data. The processing and managing of this data at higher speed for performance analysis and prediction for field development and planning has become a significant area of research. Several challenges that are encountered in forecasting the operational characteristics using the traditional approaches have led to research based on implementation of machine learning and data analytics techniques in exploration and production activities to attain higher accuracy, which allows making informed choices. Herein, a review is presented to evaluate the applications and scope of machine learning and data analytics in the oil and gas industry to optimize the upstream operations, including exploration, drilling, reservoir, and production. The challenges associated with traditional methods for forecasting the operational parameters are identified and case studies associated with performance optimization using predictive models that have aided in improving the decision‐making process are discussed.

This publication has 56 references indexed in Scilit: