This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 201699, “Predicting Trouble Stages With Geomechanical Measurements and Machine Learning: A Case Study of Southern Midland Basin Horizontal Completions,” by Eric Romberg, SPE, Keban Engineering; Aaron Fisher, Tracker Resources; and Joel Mazza, SPE, Fracture ID, et al., prepared for the 2020 SPE Annual Technical Conference and Exhibition, originally scheduled to be held in Denver, 5–7 October. The paper has not been peer reviewed.
Unexpected problems during completion create costs that can cause a well to be outside its planned authorization for expenditure, even uneconomic. These problems range from experiencing abnormally high pressures during treatment to casing failures. The authors of the complete paper 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.
Field Modeling and Well Planning
The operator’s acreage is in the southeastern portion of the Midland Basin. In this area of the basin, the Wolfcamp B and C intervals often contain a significant amount of slope sediments and carbonate debris flows because of the proximity of the eastern shelf. These intervals cause significant drilling and completion issues.
During the past 5 years, the operator acquired and licensed approximately 130 sq mile of 3D seismic data. In addition, the operator cored three wells, drilled six pilot wells with complete log suites, licensed 40 wells with a triple/quad combination, acquired data and surveys on 112 existing horizontal wells, and has 347 vertical wells with formation tops for depth control. This rich data set yielded a robust 3D reservoir model that was used to map a sequence of stacked, high-quality landing targets.
Model-Aided Well-Completion Strategy.
The operator often encountered difficult stages in the form of high breakdown pressures, high pumping pressures, and the inability to place proppant. On a few occasions, drilling out all plugs was not possible because of casing obstructions possibly related to fault activation during the stimulation. The operator began analyzing curvature and similarity volumes for potential fault/fracture identification near the difficult completion stages and compromised casing intervals.
Drillbit geomechanics data collection was planned for all lateral wells. The geomechanical properties recorded were used to reduce risks during completions further by informing the plug and perforation stage design. Stages were planned to reduce variation in minimum horizontal stress (Shmin) within each stage. The geomechanical data also identified carbonate debris flows within the well path, allowing completion engineers to bypass rock considered unproductive.
Completion Issues and Other Factors Contributing to Casing Deformation.
From February 2017 through November 2019, the operator drilled and completed 28 Wolfcamp horizontal wells. The plug-and-perforation completion technique was used on all 28 wells.
While drilling out composite fracturing plugs, casing obstruction was encountered in six of 28 wells. These obstructions limited the working internal diameter of the production casing and either prevented or inhibited access beyond the obstruction. In two of the Phase 1 wells, conventional drillout assemblies were not able to pass the obstructions.