Contact Info
San Juan Capistrano, CA
[email protected]
(844) OSPREY-NOW (677-7396)
Follow Us

What Can AI Bring To Oil and Gas Production

Artificial Intelligence in Oil and Gas has become a very popular topic. MIT’s Sloan School of Management’s article, “Reshaping Business with Artificial Intelligence,” recently found that that 85% of corporate executives surveyed believe that AI will help their businesses gain or sustain competitive advantages. What might that look like for oil and gas production operations? The following is a summary of key solutions that artificial intelligence can target for problems facing most oil and gas organizations utilizing artificial lift. Each problem represents an opportunity for production improvements for organizations that navigate the delivery of an artificial intelligence solution.

Avoiding downtime by understanding operational triggers: The solution is to detect problems earlier and faster. The organization moves from being reactive to preventative with failure. At a minimum, this improves response time to failures, which reduces downtime. This increases production and bottom line profits.

Efficiently optimizing a large number of wells: Optimizing a large number of wells is time consuming and usually incorporates many “rules of thumb” practices versus real well evaluation. Leveraging a combination of physics- based models and machine learning enables continuous review and allows for evaluation of the optimum operating parameters for all wells.

Accurately estimating production: Tracking production is an essential part of well operations and overall field management. Today, we see that much of the production is allocated back to the wells from sales or tank levels. These estimates are based on stale well test data. Effective field management requires more detailed production values to assess impacts and to drive proper prioritization of field resources.

Driving to a demonstrated ROI with an IoT, artificial intelligence or machine learning project is not simply installing more sensors, upgrading telemetry and applying the latest analytic software. The key is improving data quality, and that approach is a marathon, not a sprint.  Over the next few months, we will be addressing the impacts of data quality and source data. These solutions will not be implemented overnight, but the effect on production and operations in an organization will be substantial and worth the effort. We hope that you will join in on the journey with us as we provoke our community to great discussions around this topic.

If you can’t wait for us to round out these discussions over the next few months, feel free to get a head start by requesting our white paper entitled “Data Quality Fuels the AI Race.”  Feel free to comment or ask questions about our white paper below in our comments section.  We would love to hear your thoughts and begin a conversation.