DSDE: In Practice

The authors use machine-learning methods combined with geomechanical, wellbore-trajectory, and completion data sets to develop models that predict which stages will experience difficulties during completion.

The company’s newest product will combine with Amazon Web Service’s efforts to ease access to data from the Open Subsurface Data Universe.

Laboratory formation damage testing is often used to help select optimal drilling and completion fluids, but predicting the overall effect of formation damage on well performance requires further interpretation. Paper SPE 199268 presents a case for use of CFD to upscale laboratory data to quantify that effect.

A plunger lift optimization software has been developed that enables set-point optimization at scale.

Have our institutions become too complex to secure?

Recent advances could make feasible the deployment of networks of methane sensors to detect the greenhouse gas at large facilities.

At Equinor’s giant new North Sea oil field, thousands of sensors feed into Data Gumbo’s novel blockchain platform—encoding an immutable record of operations, the better to automate contracts, pay vendors, and (in the not too distant future) even measure carbon emissions.

The proposed solution is a good candidate for real-time burner-efficiency monitoring and automatic alarm triggering and optimization.

The authors develop an innovative machine-learning method to determine salt structures directly from gravity data.

The work and the provided methodology provide a significant improvement in facies classification.