Data analytics quickly predict number of fracture stages in horizontal wells

Ahmed Alzahabi, Ahmed Kamel, A. Alexandre Trindade, Wade Baustian

Research output: Contribution to conferencePaper

Abstract

The Wolfcamp Shale in the Permian Basin is one of the most active plays in unconventional reservoir development. Multiple efforts have been devised to design horizontal wells completion methods to effectively develop the Wolfcamp. We introduce a model to predict the number of fracture stages of the Wolfcamp Shale formation. A simple technique was devised for determining the future number of fracture stages in horizontal wells. The main input parameters into the model are county; reservoir type; overlap between horizontal wells’ drainage volume; age of the well in production; depth; injected fluid per stage in bbls,; proppants in lb.; Estimated Ultimate Recovery (EUR) of oil; EUR of gas; initial production (IP) 30 oil and IP gas. Completion variables of the horizontal wells directly affect performance of the producing wells. These variables include: depth; fluids in bbls; horizontal well completion configurations; stages per well; fracture type; average water requirement; proppant type; fluid type; proppant size; average rate; hydraulic horsepower (HHP) per stage; lb/ft^2 of proppants per stage; number of stages, clusters; cluster spacing, and lateral length (completed interval) of horizontal wells. Relationships among these variables were studied according to recent developments in multivariate regression (supervised machine learning), which allow for the group-wise inclusion/exclusion of factor variables. The proposed analysis was performed on 201 horizontal wells of the Wolfcamp shale play, for which the data were available. The analysis identified key parameters that may be used to predict the number of fracture stages. Three additional models were introduced to answer the following questions: How many clusters per fracture stages? How many perforations per cluster? What is the spacing between clusters? The models may be used to predict completion strategies in new wells of the old or new shale play.

Original languageEnglish
StatePublished - Jan 1 2019
Event53rd U.S. Rock Mechanics/Geomechanics Symposium - Brooklyn, United States
Duration: Jun 23 2019Jun 26 2019

Conference

Conference53rd U.S. Rock Mechanics/Geomechanics Symposium
CountryUnited States
CityBrooklyn
Period06/23/1906/26/19

Fingerprint Dive into the research topics of 'Data analytics quickly predict number of fracture stages in horizontal wells'. Together they form a unique fingerprint.

  • Cite this

    Alzahabi, A., Kamel, A., Trindade, A. A., & Baustian, W. (2019). Data analytics quickly predict number of fracture stages in horizontal wells. Paper presented at 53rd U.S. Rock Mechanics/Geomechanics Symposium, Brooklyn, United States.