From face detection to fractured reservoir characterization

Big data analytics for restimulation candidate selection

Research output: Contribution to conferencePaper

Abstract

In recent years, there has been a proliferation of massive subsurface data from instrumented wells. This places significant challenges on traditional production data analysis methods for extracting useful information, in support of reservoir management and decision-making. Additionally, with increased exploration interest in unconventional shale gas reservoirs, there is a heightened need for improved techniques and technologies to enhance understanding of induced and natural fracture characteristics in the subsurface, as well as their associated impacts on fluid flow and transport. The above challenges have the potential to be addressed by developing Big Data analytic tools that focus on uncovering masked trends related to fracture properties from large volumes of subsurface data, through the application of pattern recognition techniques. We present a new framework for fast and robust production data classification, which is adapted from a real-time face detection algorithm. This is achieved by generalizing production data as vectorized 1-D images with pixel values indicating rate magnitudes. Using simulated shale gas production data, we train a boosted binary classification algorithm which is capable of providing probabilistic predictions. We demonstrate the viability of this approach for identifying hydraulically fractured wells which have the potential to benefit from restimulation treatment. The results show significant improvements over existing type-curve based approaches for recognizing favorable candidate wells, using solely gas rate profiles.

Original languageEnglish (US)
StatePublished - Jan 1 2017
EventSPE Annual Technical Conference and Exhibition 2017 - San Antonio, United States
Duration: Oct 9 2017Oct 11 2017

Other

OtherSPE Annual Technical Conference and Exhibition 2017
CountryUnited States
CitySan Antonio
Period10/9/1710/11/17

Fingerprint

Face recognition
Reservoir management
Pattern recognition
Flow of fluids
Decision making
Pixels
Big data
Gases
Shale gas

All Science Journal Classification (ASJC) codes

  • Fuel Technology
  • Energy Engineering and Power Technology

Cite this

Udegbe, E., Morgan, E. C., & Srinivasan, S. (2017). From face detection to fractured reservoir characterization: Big data analytics for restimulation candidate selection. Paper presented at SPE Annual Technical Conference and Exhibition 2017, San Antonio, United States.
Udegbe, Egbadon ; Morgan, Eugene C. ; Srinivasan, Sanjay. / From face detection to fractured reservoir characterization : Big data analytics for restimulation candidate selection. Paper presented at SPE Annual Technical Conference and Exhibition 2017, San Antonio, United States.
@conference{0b52b0c3cbaf46fb85b499240d5d4b62,
title = "From face detection to fractured reservoir characterization: Big data analytics for restimulation candidate selection",
abstract = "In recent years, there has been a proliferation of massive subsurface data from instrumented wells. This places significant challenges on traditional production data analysis methods for extracting useful information, in support of reservoir management and decision-making. Additionally, with increased exploration interest in unconventional shale gas reservoirs, there is a heightened need for improved techniques and technologies to enhance understanding of induced and natural fracture characteristics in the subsurface, as well as their associated impacts on fluid flow and transport. The above challenges have the potential to be addressed by developing Big Data analytic tools that focus on uncovering masked trends related to fracture properties from large volumes of subsurface data, through the application of pattern recognition techniques. We present a new framework for fast and robust production data classification, which is adapted from a real-time face detection algorithm. This is achieved by generalizing production data as vectorized 1-D images with pixel values indicating rate magnitudes. Using simulated shale gas production data, we train a boosted binary classification algorithm which is capable of providing probabilistic predictions. We demonstrate the viability of this approach for identifying hydraulically fractured wells which have the potential to benefit from restimulation treatment. The results show significant improvements over existing type-curve based approaches for recognizing favorable candidate wells, using solely gas rate profiles.",
author = "Egbadon Udegbe and Morgan, {Eugene C.} and Sanjay Srinivasan",
year = "2017",
month = "1",
day = "1",
language = "English (US)",
note = "SPE Annual Technical Conference and Exhibition 2017 ; Conference date: 09-10-2017 Through 11-10-2017",

}

Udegbe, E, Morgan, EC & Srinivasan, S 2017, 'From face detection to fractured reservoir characterization: Big data analytics for restimulation candidate selection' Paper presented at SPE Annual Technical Conference and Exhibition 2017, San Antonio, United States, 10/9/17 - 10/11/17, .

From face detection to fractured reservoir characterization : Big data analytics for restimulation candidate selection. / Udegbe, Egbadon; Morgan, Eugene C.; Srinivasan, Sanjay.

2017. Paper presented at SPE Annual Technical Conference and Exhibition 2017, San Antonio, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - From face detection to fractured reservoir characterization

T2 - Big data analytics for restimulation candidate selection

AU - Udegbe, Egbadon

AU - Morgan, Eugene C.

AU - Srinivasan, Sanjay

PY - 2017/1/1

Y1 - 2017/1/1

N2 - In recent years, there has been a proliferation of massive subsurface data from instrumented wells. This places significant challenges on traditional production data analysis methods for extracting useful information, in support of reservoir management and decision-making. Additionally, with increased exploration interest in unconventional shale gas reservoirs, there is a heightened need for improved techniques and technologies to enhance understanding of induced and natural fracture characteristics in the subsurface, as well as their associated impacts on fluid flow and transport. The above challenges have the potential to be addressed by developing Big Data analytic tools that focus on uncovering masked trends related to fracture properties from large volumes of subsurface data, through the application of pattern recognition techniques. We present a new framework for fast and robust production data classification, which is adapted from a real-time face detection algorithm. This is achieved by generalizing production data as vectorized 1-D images with pixel values indicating rate magnitudes. Using simulated shale gas production data, we train a boosted binary classification algorithm which is capable of providing probabilistic predictions. We demonstrate the viability of this approach for identifying hydraulically fractured wells which have the potential to benefit from restimulation treatment. The results show significant improvements over existing type-curve based approaches for recognizing favorable candidate wells, using solely gas rate profiles.

AB - In recent years, there has been a proliferation of massive subsurface data from instrumented wells. This places significant challenges on traditional production data analysis methods for extracting useful information, in support of reservoir management and decision-making. Additionally, with increased exploration interest in unconventional shale gas reservoirs, there is a heightened need for improved techniques and technologies to enhance understanding of induced and natural fracture characteristics in the subsurface, as well as their associated impacts on fluid flow and transport. The above challenges have the potential to be addressed by developing Big Data analytic tools that focus on uncovering masked trends related to fracture properties from large volumes of subsurface data, through the application of pattern recognition techniques. We present a new framework for fast and robust production data classification, which is adapted from a real-time face detection algorithm. This is achieved by generalizing production data as vectorized 1-D images with pixel values indicating rate magnitudes. Using simulated shale gas production data, we train a boosted binary classification algorithm which is capable of providing probabilistic predictions. We demonstrate the viability of this approach for identifying hydraulically fractured wells which have the potential to benefit from restimulation treatment. The results show significant improvements over existing type-curve based approaches for recognizing favorable candidate wells, using solely gas rate profiles.

UR - http://www.scopus.com/inward/record.url?scp=85040449329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040449329&partnerID=8YFLogxK

M3 - Paper

ER -

Udegbe E, Morgan EC, Srinivasan S. From face detection to fractured reservoir characterization: Big data analytics for restimulation candidate selection. 2017. Paper presented at SPE Annual Technical Conference and Exhibition 2017, San Antonio, United States.