Evaluating proxies for the drivers of natural gas productivity using machine-learning models
- National Energy Technology Lab. (NETL), Pittsburgh, PA (United States). Support contractor
- Oak Ridge Inst. for Science and Education (ORISE), Oak Ridge, TN (United States); Univ. of Pittsburgh, PA (United States)
- National Energy Technology Laboratory, Department of Energy, Pittsburgh, Pennsylvania 15236-0940, USA..
- Univ. of Pittsburgh, PA (United States); DiGioia Gray Consulting Engineers & Scientists, Pittsburgh, PA (United States)
- Oak Ridge Inst. for Science and Education (ORISE), Oak Ridge, TN (United States)
- DiGioia Gray Consulting Engineers & Scientists, Pittsburgh, PA (United States); West Virginia Univ., Morgantown, WV (United States)
We report the extensive development of unconventional reservoirs using horizontal drilling and multistage hydraulic fracturing has generated large volumes of reservoir characterization and production data. The analysis of this abundant data using statistical methods and advanced machine-learning (ML) techniques can provide data-driven insights into well performance. Most predictive modeling studies have focused on the impact that different well completion and stimulation strategies have on well production but have not fully exploited the available in situ rock property data to determine its role in reservoir productivity. We have used machine-learning techniques to rank rock mechanical properties, microseismic attributes, and stimulation parameters in the order of their significance for predicting natural gas production from an unconventional reservoir. The data for this study came from a hydraulically fractured well in the Marcellus Shale in Monongalia County, West Virginia. The data classes included measurements aggregated by well completion stage that included (1) gas production, (2) well-log-derived measurements including bulk density, elastic moduli, shear impedance, compressional impedance, brittleness, and gamma measurements, (3) microseismic attributes, (4) long-period long-duration (LPLD) event counts, (5) fracture counts, and (6) stimulation parameters that included the fluid injection volume and average pumping pressure. To identify observable proxies for the drivers of gas production, we evaluated five commonly used ML approaches including multivariate adaptive regression spline, Gaussian mixture model, random forest, gradient boosting, and neural network. We selected five variables including LPLD event count, seismogenic b-value, hydraulic diffusivity, cumulative moment, and fluid volume as the features most likely to impact gas productivity at the stage level in the study area. The data-driven selection of these parameters for their importance in determining gas production can help reservoir engineers design more effective hydraulic-fracture treatments in the Marcellus Shale and other similar unconventional reservoirs. Plain language summary: We use machine-learning methods and data-driven selection of reservoir parameters to rank and better understand their importance in determining gas production, which can help reservoir engineers design more effective hydraulic-fracture treatments in the Marcellus Shale and other similar unconventional reservoirs.
- Research Organization:
- National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)
- Sponsoring Organization:
- USDOE Office of Fossil Energy (FE)
- Grant/Contract Number:
- 89243318CFE000003
- OSTI ID:
- 1869701
- Journal Information:
- Interpretation, Vol. 9, Issue 4; ISSN 2324-8858
- Publisher:
- Society of Exploration GeophysicistsCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Integrating distributed acoustic sensing, borehole 3C geophone array, and surface seismic array data to identify long-period long-duration seismic events during stimulation of a Marcellus Shale gas reservoir
Machine learning-informed ensemble framework for evaluating shale gas production potential: Case study in the Marcellus Shale