Accelerating Unconventional Well Completion Optimization Through Data Analytics and Machine Learning Tied to Reservoir Characterization

Abstract

In today’s data-driven economy, operators that integrate vast stores of fundamental reservoir and production data with the high-performance predictive analytics solutions can emerge as winners in the contest of maximizing EUR. The scope of this study is to demonstrate new workflow coupling earth sciences with data analytics to operationalize well completion optimization. The workflow aims to build a robust model that allows user to perform sensitivity analysis on completion designs within a few hours.

Less than 5% of the wells fractured in North America are designed using advanced simulation due to the required level of data, skillset and long computing times. Breaking these limitations through parallel fracture and reservoir simulations on cloud, and combining it with analytics and algorithms helped develop a powerful solution that creates models for fast yet effective completion design.

As a case study, the approach was executed on Permian and Eagle Ford wells. Over 1500 data points were collected with completion sensitivity performed on multithreaded cluster environment on these wells. Advanced machine learning and data mining algorithms of data analytics such as Random Forest, Gradient Boost, Liner Regression etc. were applied on the data points to create a proxy model for the frac and the production simulator. With Gradient Boost technique over 90% accuracy was achieved between the proxy model and the actual results. Hence, the proxy model could predict the wellbore productivity fairly accurately for any given change in completion design. Evaluating the impact of completion parameters on production and economics was fast-tracked and almost real time. The approach can be replicated for varying geological and geomechanical properties as operations move from pad to pad. While the heavy computing resource, simulation skillset and long run times were now story of past when applying this new approach, regular QA/QC of the model through manual simulations makes the process more robust and reliable.

The methodology provides an integrated approach to bridge the traditional reservoir understanding and simulation approach to the new big data approach to create proxies which allows operators to make quicker decisions for completion optimization. The technique presented in this paper can be extended for other domains of wellsite operations such as well drilling, artificial lift, etc. and help operators evaluate the most economical scenario in almost real-time.

AAPG Datapages/Search and Discovery Article #90323 ©2018 AAPG Annual Convention and Exhibition, Salt Lake City, Utah, May 20-23, 2018